{"id":"17753969af582bab0d583013ec36fae09dbb3faf369ec264e4d9ddf31dfe9b1b","title":"Anduin: A sybil-resistant agentic marketplace reputation system","argument":"The authors propose Anduin, a way to rate service providers in permissionless onchain markets using existing payment histories rather than relying on human curation, identity credentials or voluntary reviews. They argue that simple rankings by transaction volume can be manipulated through Sybil attacks, in which an attacker uses multiple identities to distort a system. Anduin models payments as a bipartite graph linking buyers and providers, then derives a provider’s rating from graph paths connected to a buyer’s trusted network. The paper describes three rating algorithms: a max-flow rating and two relaxed algorithms intended to improve rating performance.\n\nIn tests against simulated adversaries, the authors report that manipulating ratings costs 20% of the buyers’ total spend and is around 23 times harder than manipulating the standard similarity rule, collaborative filtering. Escape Meridian interpretation: the proposal matters because it tries to turn payment records that already exist into a signal for choosing unfamiliar providers, while making manipulation costly. These results are from simulations, not evidence that the system will work equally well in live markets. The abstract does not establish how well the ratings predict service quality, or how the approach performs when real payment networks and adversaries differ from the simulated ones.","topicIds":["intelligence-and-discovery"],"domain":"science","claimType":"attributed reading","limits":"The supplied evidence is the arXiv abstract, not the full paper; it does not provide the algorithms’ details or the simulation setup. The reported manipulation results are against simulated adversaries and do not establish performance in live markets. The abstract does not report whether the ratings predict service quality.","speaker":{"name":"Ramji, Reza, Vos, Preston Vander, Zeng, Ziming, Le, Duc V.","roleAtSource":"Article author"},"source":{"title":"Anduin: A sybil-resistant agentic marketplace reputation system","publisher":"arXiv cs.AI","format":"Article","url":"https://arxiv.org/abs/2611.05586","publishedAt":"2026-11-03","dateBasis":"Date basis not provided."},"evidence":[{"text":"The paper proposes deriving provider ratings from payment-history graph paths linked to a buyer’s trusted network.","excerpt":"A provider's rating is derived from graph paths linked to a buyer's existing trusted network.","url":"https://arxiv.org/abs/2611.05586","relationship":"Source-stated"},{"text":"The authors evaluate three proposed Sybil-resistant rating algorithms: one max-flow method and two relaxed alternatives.","excerpt":"We propose three Sybil-resistant rating algorithms: a max-flow rating and two relaxed algorithms optimized for stronger rating performance.","url":"https://arxiv.org/abs/2611.05586","relationship":"Source-stated"},{"text":"In simulations, the authors report that rating manipulation costs 20% of the evaluated buyers’ total spend and is around 23 times harder than under collaborative filtering.","excerpt":"we show that rating manipulation costs 20% of those buyers' total spend and is around 23x harder to manipulate than the standard similarity rule (collaborative filtering).","url":"https://arxiv.org/abs/2611.05586","relationship":"Source-stated"},{"text":"The reported results concern simulated adversaries, rather than a demonstrated deployment in live markets.","excerpt":"Evaluating these algorithms against simulated adversaries across 813 buyers","url":"https://arxiv.org/abs/2611.05586","relationship":"Escape Meridian interpretation"}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2611.05586","checkedAt":"2026-11-10T02:34:07.746Z","items":[],"note":"No suitable media was found by the supported page extraction."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"How well do the proposed ratings identify provider quality in live markets, beyond resisting the simulated manipulation described in the abstract?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Anduin: A sybil-resistant agentic marketplace reputation system","summary":"The authors propose Anduin, a way to rate service providers in permissionless onchain markets using existing payment histories rather than relying on human curation, identity credentials or voluntary reviews. They argue that simple rankings by transaction volume can be manipulated through Sybil attacks, in which an attacker uses multiple identities to distort a system. Anduin models payments as a bipartite graph linking buyers and providers, then derives a provider’s rating from graph paths connected to a buyer’s trusted network. The paper describes three rating algorithms: a max-flow rating and two relaxed algorithms intended to improve rating performance.\n\nIn tests against simulated adversaries, the authors report that manipulating ratings costs 20% of the buyers’ total spend and is around 23 times harder than manipulating the standard similarity rule, collaborative filtering. Escape Meridian interpretation: the proposal matters because it tries to turn payment records that already exist into a signal for choosing unfamiliar providers, while making manipulation costly. These results are from simulations, not evidence that the system will work equally well in live markets. The abstract does not establish how well the ratings predict service quality, or how the approach performs when real payment networks and adversaries differ from the simulated ones.","question":"How well do the proposed ratings identify provider quality in live markets, beyond resisting the simulated manipulation described in the abstract?","claims":[{"text":"The paper proposes deriving provider ratings from payment-history graph paths linked to a buyer’s trusted network.","excerpt":"A provider's rating is derived from graph paths linked to a buyer's existing trusted network.","support":"source-stated"},{"text":"The authors evaluate three proposed Sybil-resistant rating algorithms: one max-flow method and two relaxed alternatives.","excerpt":"We propose three Sybil-resistant rating algorithms: a max-flow rating and two relaxed algorithms optimized for stronger rating performance.","support":"source-stated"},{"text":"In simulations, the authors report that rating manipulation costs 20% of the evaluated buyers’ total spend and is around 23 times harder than under collaborative filtering.","excerpt":"we show that rating manipulation costs 20% of those buyers' total spend and is around 23x harder to manipulate than the standard similarity rule (collaborative filtering).","support":"source-stated"},{"text":"The reported results concern simulated adversaries, rather than a demonstrated deployment in live markets.","excerpt":"Evaluating these algorithms against simulated adversaries across 813 buyers","support":"interpretation"}],"limitations":["The supplied evidence is the arXiv abstract, not the full paper; it does not provide the algorithms’ details or the simulation setup.","The reported manipulation results are against simulated adversaries and do not establish performance in live markets.","The abstract does not report whether the ratings predict service quality."],"mediaId":"833e9eaf617aca9be82ddfc4c02f9a27f06680c184d666854badd0d6886d5a18","correctionReason":null,"id":"17753969af582bab0d583013ec36fae09dbb3faf369ec264e4d9ddf31dfe9b1b","publicationId":"a4a851a4-6b52-441e-8fc5-90733b02379c","version":1,"sourceUrl":"https://arxiv.org/abs/2611.05586","sourceTitle":"Anduin: A sybil-resistant agentic marketplace reputation system","publisher":"arXiv cs.AI","publishedAt":null,"originalPublished":{"value":"2026-11-03","precision":"day","basis":"publisher_citation_date"},"firstObservedAt":"2026-11-05T05:06:28.765Z","createdAt":"2026-11-10T02:03:38.068Z","historical":true,"entityIds":["arxiv"],"topicIds":["intelligence-and-discovery"],"media":[{"id":"833e9eaf617aca9be82ddfc4c02f9a27f06680c184d666854badd0d6886d5a18","kind":"article","url":"https://arxiv.org/abs/2611.05586","sourceUrl":"https://arxiv.org/abs/2611.05586","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-11-10T02:02:55.642Z","method":"acquired_source","contentType":"text/html"},"recommendationReason":"Recommended by Jev for understanding this source; checked by Luna."}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2611.05586","checkedAt":"2026-11-10T02:34:07.746Z","items":[],"note":"No suitable media was found by the supported page extraction."},"editorialDecision":{"outcome":"accept","reasonCodes":["material_development"],"rubricVersion":"stream-admission-v5","mediaId":"833e9eaf617aca9be82ddfc4c02f9a27f06680c184d666854badd0d6886d5a18","confidence":0.76,"provider":"typesafe","model":"jev-1.13.0","inputHash":"f0e10d2c08b459578f1159f9f7988b8f2a8aba492ad357b27376b3d6a9cd0743","decidedAt":"2026-11-10T02:02:56.540Z"},"provenance":{"textHash":"c55b0ec138d469903f45ef78cea95b7de3798a42508546560f50efa635109b95","observationId":"8c5f800259984f606ca01c4103375371ea17a96e4dd1c7052a75cbbf14b8b7c1","retrievedAt":"2026-11-10T02:02:55.531Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"de055a9c-10d5-4225-8129-3736845e0e35"},"reviewer":{"model":"gpt-6-luna","runId":"6c60ba70-ea70-4a21-8363-d5ae5b419bf5"}},"audit":{"status":"uncertain","reviewedAt":"2026-11-10T02:03:38.068Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Ramji, Reza","url":null,"kind":"unknown"},{"name":"Vos, Preston Vander","url":null,"kind":"unknown"},{"name":"Zeng, Ziming","url":null,"kind":"unknown"},{"name":"Le, Duc V.","url":null,"kind":"unknown"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Ramji, Reza","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Ramji, Reza","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.05586","locator":"head/meta[name=author|citation_author]"},"assertionId":"8c7253c1e189fc953001d993bf316c0565d99deece4c2d86878dff2a5876d8f5:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T02:34:07.746Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"8c7253c1e189fc953001d993bf316c0565d99deece4c2d86878dff2a5876d8f5","sourceUrl":"https://arxiv.org/abs/2611.05586","contentSha256":"b06061efd79cb49eb5cdb628740457aeb1bff5b56762d4e445082fb602ef3f0b","textHash":"c55b0ec138d469903f45ef78cea95b7de3798a42508546560f50efa635109b95","observedAt":"2026-11-10T02:34:07.746Z"}},{"actor":{"name":"Vos, Preston Vander","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Vos, Preston Vander","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.05586","locator":"head/meta[name=author|citation_author]"},"assertionId":"8c7253c1e189fc953001d993bf316c0565d99deece4c2d86878dff2a5876d8f5:participation:1","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T02:34:07.746Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"8c7253c1e189fc953001d993bf316c0565d99deece4c2d86878dff2a5876d8f5","sourceUrl":"https://arxiv.org/abs/2611.05586","contentSha256":"b06061efd79cb49eb5cdb628740457aeb1bff5b56762d4e445082fb602ef3f0b","textHash":"c55b0ec138d469903f45ef78cea95b7de3798a42508546560f50efa635109b95","observedAt":"2026-11-10T02:34:07.746Z"}},{"actor":{"name":"Zeng, Ziming","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Zeng, Ziming","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.05586","locator":"head/meta[name=author|citation_author]"},"assertionId":"8c7253c1e189fc953001d993bf316c0565d99deece4c2d86878dff2a5876d8f5:participation:2","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T02:34:07.746Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"8c7253c1e189fc953001d993bf316c0565d99deece4c2d86878dff2a5876d8f5","sourceUrl":"https://arxiv.org/abs/2611.05586","contentSha256":"b06061efd79cb49eb5cdb628740457aeb1bff5b56762d4e445082fb602ef3f0b","textHash":"c55b0ec138d469903f45ef78cea95b7de3798a42508546560f50efa635109b95","observedAt":"2026-11-10T02:34:07.746Z"}},{"actor":{"name":"Le, Duc V.","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Le, Duc V.","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.05586","locator":"head/meta[name=author|citation_author]"},"assertionId":"8c7253c1e189fc953001d993bf316c0565d99deece4c2d86878dff2a5876d8f5:participation:3","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T02:34:07.746Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"8c7253c1e189fc953001d993bf316c0565d99deece4c2d86878dff2a5876d8f5","sourceUrl":"https://arxiv.org/abs/2611.05586","contentSha256":"b06061efd79cb49eb5cdb628740457aeb1bff5b56762d4e445082fb602ef3f0b","textHash":"c55b0ec138d469903f45ef78cea95b7de3798a42508546560f50efa635109b95","observedAt":"2026-11-10T02:34:07.746Z"}}],"participationCoverage":{"total":4,"returned":4,"complete":true,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":null,"sourceUrl":"https://arxiv.org/abs/2611.05586","snapshotId":"8c7253c1e189fc953001d993bf316c0565d99deece4c2d86878dff2a5876d8f5","contentSha256":"b06061efd79cb49eb5cdb628740457aeb1bff5b56762d4e445082fb602ef3f0b","textHash":"c55b0ec138d469903f45ef78cea95b7de3798a42508546560f50efa635109b95","observedAt":"2026-11-10T02:34:07.746Z","basis":"publisher-page-metadata","sourceLinks":42,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/17753969af582bab0d583013ec36fae09dbb3faf369ec264e4d9ddf31dfe9b1b/source"}},"canonicalUrl":"https://escapemeridian.com/readings/anduin-a-sybil-resistant-agentic-marketplace-reputation-system-17753969","formats":{"html":"/readings/anduin-a-sybil-resistant-agentic-marketplace-reputation-system-17753969","markdown":"/readings/anduin-a-sybil-resistant-agentic-marketplace-reputation-system-17753969.md","json":"/readings/anduin-a-sybil-resistant-agentic-marketplace-reputation-system-17753969.json"},"attribution":"Headline and summary by Escape Meridian, prepared by Luna from the attributed source. A source check is not independent confirmation of the source’s claims.","maintainedGuideLinks":[],"readerContext":{"version":"reader-context-v1","attribution":"Reference context selected by Escape Meridian; separate from source evidence. Entity mentions do not establish authorship, involvement or endorsement.","terms":[{"id":"term-agentic","name":"Agentic AI","explanation":"AI systems that plan and carry out a series of steps toward a goal, often by using other software, rather than giving one answer.","referenceUrl":"https://developers.google.com/machine-learning/glossary#agentic"}],"entities":[{"id":"marketplace","name":"Marketplace","kind":"organization","context":"Marketplace is a public radio business news outlet publishing reporting on the economy, companies, technology and work.","referenceUrls":["https://www.marketplace.org/"],"path":"/entities/marketplace","json":"/entities/marketplace.json","markdown":"/entities/marketplace.md"},{"id":"arxiv","name":"arXiv","kind":"organization","context":"arXiv is a research manuscript repository where authors share papers that may not yet have been peer reviewed.","referenceUrls":["https://arxiv.org/","https://info.arxiv.org/help/api/index.html"],"path":"/entities/arxiv","json":"/entities/arxiv.json","markdown":"/entities/arxiv.md"}]},"researchQuestions":[],"withdrawn":false,"references":{"schemaVersion":1,"target":{"type":"reading","id":"17753969af582bab0d583013ec36fae09dbb3faf369ec264e4d9ddf31dfe9b1b","revision":"a4a851a4-6b52-441e-8fc5-90733b02379c","revisionKind":"publication-id","title":"Anduin: A sybil-resistant agentic marketplace reputation system","url":"https://escapemeridian.com/readings/anduin-a-sybil-resistant-agentic-marketplace-reputation-system-17753969"},"source":{"type":"source","id":"https://arxiv.org/abs/2611.05586","revision":"c55b0ec138d469903f45ef78cea95b7de3798a42508546560f50efa635109b95","revisionKind":"sha256-source-text","title":"Anduin: A sybil-resistant agentic marketplace reputation system","url":"https://arxiv.org/abs/2611.05586"},"status":"available","items":[],"next":null,"scope":"Explicit citations in public readings and public file attachments to this reading. Shared topics are not citations. Other artifact types need an explicit reference adapter."},"revisions":[{"id":"17753969af582bab0d583013ec36fae09dbb3faf369ec264e4d9ddf31dfe9b1b","title":"Anduin: A sybil-resistant agentic marketplace reputation system","argument":"The authors propose Anduin, a way to rate service providers in permissionless onchain markets using existing payment histories rather than relying on human curation, identity credentials or voluntary reviews. They argue that simple rankings by transaction volume can be manipulated through Sybil attacks, in which an attacker uses multiple identities to distort a system. Anduin models payments as a bipartite graph linking buyers and providers, then derives a provider’s rating from graph paths connected to a buyer’s trusted network. The paper describes three rating algorithms: a max-flow rating and two relaxed algorithms intended to improve rating performance.\n\nIn tests against simulated adversaries, the authors report that manipulating ratings costs 20% of the buyers’ total spend and is around 23 times harder than manipulating the standard similarity rule, collaborative filtering. Escape Meridian interpretation: the proposal matters because it tries to turn payment records that already exist into a signal for choosing unfamiliar providers, while making manipulation costly. These results are from simulations, not evidence that the system will work equally well in live markets. The abstract does not establish how well the ratings predict service quality, or how the approach performs when real payment networks and adversaries differ from the simulated ones.","topicIds":["intelligence-and-discovery"],"domain":"science","claimType":"attributed reading","limits":"The supplied evidence is the arXiv abstract, not the full paper; it does not provide the algorithms’ details or the simulation setup. The reported manipulation results are against simulated adversaries and do not establish performance in live markets. The abstract does not report whether the ratings predict service quality.","speaker":{"name":"Ramji, Reza, Vos, Preston Vander, Zeng, Ziming, Le, Duc V.","roleAtSource":"Article author"},"source":{"title":"Anduin: A sybil-resistant agentic marketplace reputation system","publisher":"arXiv cs.AI","format":"Article","url":"https://arxiv.org/abs/2611.05586","publishedAt":"2026-11-03","dateBasis":"Date basis not provided."},"evidence":[{"text":"The paper proposes deriving provider ratings from payment-history graph paths linked to a buyer’s trusted network.","excerpt":"A provider's rating is derived from graph paths linked to a buyer's existing trusted network.","url":"https://arxiv.org/abs/2611.05586","relationship":"Source-stated"},{"text":"The authors evaluate three proposed Sybil-resistant rating algorithms: one max-flow method and two relaxed alternatives.","excerpt":"We propose three Sybil-resistant rating algorithms: a max-flow rating and two relaxed algorithms optimized for stronger rating performance.","url":"https://arxiv.org/abs/2611.05586","relationship":"Source-stated"},{"text":"In simulations, the authors report that rating manipulation costs 20% of the evaluated buyers’ total spend and is around 23 times harder than under collaborative filtering.","excerpt":"we show that rating manipulation costs 20% of those buyers' total spend and is around 23x harder to manipulate than the standard similarity rule (collaborative filtering).","url":"https://arxiv.org/abs/2611.05586","relationship":"Source-stated"},{"text":"The reported results concern simulated adversaries, rather than a demonstrated deployment in live markets.","excerpt":"Evaluating these algorithms against simulated adversaries across 813 buyers","url":"https://arxiv.org/abs/2611.05586","relationship":"Escape Meridian interpretation"}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2611.05586","checkedAt":"2026-11-10T02:34:07.746Z","items":[],"note":"No suitable media was found by the supported page extraction."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"How well do the proposed ratings identify provider quality in live markets, beyond resisting the simulated manipulation described in the abstract?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Anduin: A sybil-resistant agentic marketplace reputation system","summary":"The authors propose Anduin, a way to rate service providers in permissionless onchain markets using existing payment histories rather than relying on human curation, identity credentials or voluntary reviews. They argue that simple rankings by transaction volume can be manipulated through Sybil attacks, in which an attacker uses multiple identities to distort a system. Anduin models payments as a bipartite graph linking buyers and providers, then derives a provider’s rating from graph paths connected to a buyer’s trusted network. The paper describes three rating algorithms: a max-flow rating and two relaxed algorithms intended to improve rating performance.\n\nIn tests against simulated adversaries, the authors report that manipulating ratings costs 20% of the buyers’ total spend and is around 23 times harder than manipulating the standard similarity rule, collaborative filtering. Escape Meridian interpretation: the proposal matters because it tries to turn payment records that already exist into a signal for choosing unfamiliar providers, while making manipulation costly. These results are from simulations, not evidence that the system will work equally well in live markets. The abstract does not establish how well the ratings predict service quality, or how the approach performs when real payment networks and adversaries differ from the simulated ones.","question":"How well do the proposed ratings identify provider quality in live markets, beyond resisting the simulated manipulation described in the abstract?","claims":[{"text":"The paper proposes deriving provider ratings from payment-history graph paths linked to a buyer’s trusted network.","excerpt":"A provider's rating is derived from graph paths linked to a buyer's existing trusted network.","support":"source-stated"},{"text":"The authors evaluate three proposed Sybil-resistant rating algorithms: one max-flow method and two relaxed alternatives.","excerpt":"We propose three Sybil-resistant rating algorithms: a max-flow rating and two relaxed algorithms optimized for stronger rating performance.","support":"source-stated"},{"text":"In simulations, the authors report that rating manipulation costs 20% of the evaluated buyers’ total spend and is around 23 times harder than under collaborative filtering.","excerpt":"we show that rating manipulation costs 20% of those buyers' total spend and is around 23x harder to manipulate than the standard similarity rule (collaborative filtering).","support":"source-stated"},{"text":"The reported results concern simulated adversaries, rather than a demonstrated deployment in live markets.","excerpt":"Evaluating these algorithms against simulated adversaries across 813 buyers","support":"interpretation"}],"limitations":["The supplied evidence is the arXiv abstract, not the full paper; it does not provide the algorithms’ details or the simulation setup.","The reported manipulation results are against simulated adversaries and do not establish performance in live markets.","The abstract does not report whether the ratings predict service quality."],"mediaId":"833e9eaf617aca9be82ddfc4c02f9a27f06680c184d666854badd0d6886d5a18","correctionReason":null,"id":"17753969af582bab0d583013ec36fae09dbb3faf369ec264e4d9ddf31dfe9b1b","publicationId":"a4a851a4-6b52-441e-8fc5-90733b02379c","version":1,"sourceUrl":"https://arxiv.org/abs/2611.05586","sourceTitle":"Anduin: A sybil-resistant agentic marketplace reputation system","publisher":"arXiv cs.AI","publishedAt":null,"originalPublished":{"value":"2026-11-03","precision":"day","basis":"publisher_citation_date"},"firstObservedAt":"2026-11-05T05:06:28.765Z","createdAt":"2026-11-10T02:03:38.068Z","historical":true,"entityIds":["arxiv"],"topicIds":["intelligence-and-discovery"],"media":[{"id":"833e9eaf617aca9be82ddfc4c02f9a27f06680c184d666854badd0d6886d5a18","kind":"article","url":"https://arxiv.org/abs/2611.05586","sourceUrl":"https://arxiv.org/abs/2611.05586","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-11-10T02:02:55.642Z","method":"acquired_source","contentType":"text/html"},"recommendationReason":"Recommended by Jev for understanding this source; checked by Luna."}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2611.05586","checkedAt":"2026-11-10T02:34:07.746Z","items":[],"note":"No suitable media was found by the supported page extraction."},"editorialDecision":{"outcome":"accept","reasonCodes":["material_development"],"rubricVersion":"stream-admission-v5","mediaId":"833e9eaf617aca9be82ddfc4c02f9a27f06680c184d666854badd0d6886d5a18","confidence":0.76,"provider":"typesafe","model":"jev-1.13.0","inputHash":"f0e10d2c08b459578f1159f9f7988b8f2a8aba492ad357b27376b3d6a9cd0743","decidedAt":"2026-11-10T02:02:56.540Z"},"provenance":{"textHash":"c55b0ec138d469903f45ef78cea95b7de3798a42508546560f50efa635109b95","observationId":"8c5f800259984f606ca01c4103375371ea17a96e4dd1c7052a75cbbf14b8b7c1","retrievedAt":"2026-11-10T02:02:55.531Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"de055a9c-10d5-4225-8129-3736845e0e35"},"reviewer":{"model":"gpt-6-luna","runId":"6c60ba70-ea70-4a21-8363-d5ae5b419bf5"}},"audit":{"status":"uncertain","reviewedAt":"2026-11-10T02:03:38.068Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Ramji, Reza","url":null,"kind":"unknown"},{"name":"Vos, Preston Vander","url":null,"kind":"unknown"},{"name":"Zeng, Ziming","url":null,"kind":"unknown"},{"name":"Le, Duc V.","url":null,"kind":"unknown"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Ramji, Reza","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Ramji, Reza","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.05586","locator":"head/meta[name=author|citation_author]"},"assertionId":"8c7253c1e189fc953001d993bf316c0565d99deece4c2d86878dff2a5876d8f5:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T02:34:07.746Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"8c7253c1e189fc953001d993bf316c0565d99deece4c2d86878dff2a5876d8f5","sourceUrl":"https://arxiv.org/abs/2611.05586","contentSha256":"b06061efd79cb49eb5cdb628740457aeb1bff5b56762d4e445082fb602ef3f0b","textHash":"c55b0ec138d469903f45ef78cea95b7de3798a42508546560f50efa635109b95","observedAt":"2026-11-10T02:34:07.746Z"}},{"actor":{"name":"Vos, Preston Vander","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Vos, Preston Vander","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.05586","locator":"head/meta[name=author|citation_author]"},"assertionId":"8c7253c1e189fc953001d993bf316c0565d99deece4c2d86878dff2a5876d8f5:participation:1","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T02:34:07.746Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"8c7253c1e189fc953001d993bf316c0565d99deece4c2d86878dff2a5876d8f5","sourceUrl":"https://arxiv.org/abs/2611.05586","contentSha256":"b06061efd79cb49eb5cdb628740457aeb1bff5b56762d4e445082fb602ef3f0b","textHash":"c55b0ec138d469903f45ef78cea95b7de3798a42508546560f50efa635109b95","observedAt":"2026-11-10T02:34:07.746Z"}},{"actor":{"name":"Zeng, Ziming","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Zeng, Ziming","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.05586","locator":"head/meta[name=author|citation_author]"},"assertionId":"8c7253c1e189fc953001d993bf316c0565d99deece4c2d86878dff2a5876d8f5:participation:2","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T02:34:07.746Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"8c7253c1e189fc953001d993bf316c0565d99deece4c2d86878dff2a5876d8f5","sourceUrl":"https://arxiv.org/abs/2611.05586","contentSha256":"b06061efd79cb49eb5cdb628740457aeb1bff5b56762d4e445082fb602ef3f0b","textHash":"c55b0ec138d469903f45ef78cea95b7de3798a42508546560f50efa635109b95","observedAt":"2026-11-10T02:34:07.746Z"}},{"actor":{"name":"Le, Duc V.","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Le, Duc V.","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.05586","locator":"head/meta[name=author|citation_author]"},"assertionId":"8c7253c1e189fc953001d993bf316c0565d99deece4c2d86878dff2a5876d8f5:participation:3","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T02:34:07.746Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"8c7253c1e189fc953001d993bf316c0565d99deece4c2d86878dff2a5876d8f5","sourceUrl":"https://arxiv.org/abs/2611.05586","contentSha256":"b06061efd79cb49eb5cdb628740457aeb1bff5b56762d4e445082fb602ef3f0b","textHash":"c55b0ec138d469903f45ef78cea95b7de3798a42508546560f50efa635109b95","observedAt":"2026-11-10T02:34:07.746Z"}}],"participationCoverage":{"total":4,"returned":4,"complete":true,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":null,"sourceUrl":"https://arxiv.org/abs/2611.05586","snapshotId":"8c7253c1e189fc953001d993bf316c0565d99deece4c2d86878dff2a5876d8f5","contentSha256":"b06061efd79cb49eb5cdb628740457aeb1bff5b56762d4e445082fb602ef3f0b","textHash":"c55b0ec138d469903f45ef78cea95b7de3798a42508546560f50efa635109b95","observedAt":"2026-11-10T02:34:07.746Z","basis":"publisher-page-metadata","sourceLinks":42,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/17753969af582bab0d583013ec36fae09dbb3faf369ec264e4d9ddf31dfe9b1b/source"}}}],"audits":[{"publicationId":"a4a851a4-6b52-441e-8fc5-90733b02379c","verdict":"uncertain","findings":[{"dimension":"attribution","status":"pass","explanation":"The draft attributes the proposal, algorithms and reported results to the paper's authors, consistent with the arXiv listing. Its interpretive passage is explicitly labeled as Escape Meridian interpretation.","excerpt":"Authors:Reza Ramji, Preston Vander Vos, Ziming Zeng, Duc V. Le"},{"dimension":"summary","status":"uncertain","explanation":"The summary never says the marketplace participants are autonomous AI agents, which is the source's central framing and its link to EM's scope. Smallest repair: open with the setting of AI agents choosing service providers. It also omits that the method was tested on a real dataset of 66M agentic transactions across 16 blockchains. Without that, the line about real payment networks differing from simulated ones is misleading. Key terms such as permissionless onchain markets, bipartite graph and max-flow are left unexplained for general readers. Suggest term-library tooltips rather than paraphrase.","excerpt":"As autonomous AI agents enter permissionless onchain markets, selecting new service providers remains a core challenge."},{"dimension":"date","status":"pass","explanation":"originalPublished 2026-11-03 matches the v1 submission date shown on arXiv. The feed date of Nov 5 is later and correctly not used.","excerpt":"[Submitted on 3 Nov 2026]"},{"dimension":"support","status":"pass","explanation":"The claims about graph-path ratings, the three algorithms, and the 20% cost and roughly 23x figures quote the abstract accurately. The simulated-adversary caveat and the unknown link to service quality are supported limits and are appropriately conditional. The draft does not claim live deployment or proven benefits.","excerpt":"we show that rating manipulation costs 20% of those buyers' total spend and is around 23x harder to manipulate than the standard similarity rule (collaborative filtering)."},{"dimension":"media","status":"pass","explanation":"The selected media is the verified arXiv abstract page itself, which is the direct original source.","excerpt":null}],"createdAt":"2026-11-10T02:03:38.068Z","model":"anthropic/claude-opus-5.5"}],"correctionUrl":"https://escapemeridian.com/corrections/"}