{"id":"df677f5994b58aacd50a6edea4c2b25c2e6a04bef23acd59072b2853d84aa49a","title":"Vivek Acharya’s Two-Ledger Model links AI costs to business transactions","argument":"Vivek Acharya argues that enterprise billing data cannot answer a practical question: what did a particular order, claim, or case cost in AI? Providers bill at settlement grain—by SKU and charge period—while businesses need costs associated with individual transactions. Acharya proposes joining a settlement ledger of FOCUS-conformant billing data with an attribution ledger of invocation-grain usage records built on OpenTelemetry GenAI telemetry. A layered correlation spine uses trace context, A2A/MCP metadata, business-key correlation, and probabilistic matching to assign records to transactions, recording the method and confidence. A versioned rate card prices usage near real time; period reconciliation compares both ledgers with the invoice, with the unexplained residual identifying possible shadow AI. The model also proposes reporting costs per order, claim, or outcome and using mid-flight gating to limit transaction costs. In a simulation with known ground truth, Acharya reports cost coverage above 99% even when trace propagation falls to zero, recovery of planted unmetered spend within 0.24 percentage points, and p99 transaction-cost reductions of up to 61% with a 2-4% false-pause rate. These are simulation results, not evidence of performance in deployed enterprise systems. Acharya proposes the attribution ledger as an invocation-grain FOCUS profile for standardization.","topicIds":["intelligence-and-discovery"],"domain":"science","claimType":"attributed reading","limits":"The reported performance figures come from a simulation with known ground truth; the supplied abstract does not report results from deployed enterprise systems. The supplied evidence is the paper’s abstract and does not provide the simulation setup or further methodological detail.","speaker":{"name":"Acharya, Vivek","roleAtSource":"Article author"},"source":{"title":"The Two-Ledger Model: Transaction-Grain Cost Accounting for Multi-Agent AI Systems Across Clouds, Models, and Systems of Record","publisher":"arXiv cs.AI","format":"Article","url":"https://arxiv.org/abs/2611.06989","publishedAt":"2026-11-04","dateBasis":"Date basis not provided."},"evidence":[{"text":"Acharya argues that billing data cannot answer what an individual business transaction cost in AI because providers do not see enterprise transaction boundaries.","excerpt":"The business question (what did this order, claim, or case cost in AI?) cannot be answered from billing data, because providers never see enterprise transaction boundaries.","url":"https://arxiv.org/abs/2611.06989","relationship":"Source-stated"},{"text":"The proposed Two-Ledger Model joins settlement-grain billing data with invocation-grain usage records to attribute AI costs to business transactions.","excerpt":"a settlement ledger of FOCUS-conformant billing data joined to an attribution ledger of invocation-grain usage records built on OpenTelemetry GenAI telemetry.","url":"https://arxiv.org/abs/2611.06989","relationship":"Source-stated"},{"text":"In a simulation with known ground truth, the authors report cost coverage above 99% even when trace propagation falls to zero.","excerpt":"A simulation with known ground truth shows the spine sustaining cost coverage above 99% as trace propagation falls to zero","url":"https://arxiv.org/abs/2611.06989","relationship":"Source-stated"},{"text":"In that simulation, mid-flight gating cut p99 transaction cost by up to 61%, with a 2-4% false-pause rate.","excerpt":"mid-flight gating cutting p99 transaction cost by up to 61% at a 2-4% false-pause rate.","url":"https://arxiv.org/abs/2611.06989","relationship":"Source-stated"},{"text":"Acharya proposes the attribution ledger as an invocation-grain FOCUS profile for standardization.","excerpt":"We propose the attribution ledger as an invocation-grain FOCUS profile for standardization.","url":"https://arxiv.org/abs/2611.06989","relationship":"Source-stated"}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2611.06989","checkedAt":"2026-11-09T03:56:09.316Z","items":[],"note":"No suitable media was found by the supported page extraction."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"How would the model’s reported simulation results compare with results from enterprise systems handling real transactions and billing data?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Vivek Acharya’s Two-Ledger Model links AI costs to business transactions","summary":"Vivek Acharya argues that enterprise billing data cannot answer a practical question: what did a particular order, claim, or case cost in AI? Providers bill at settlement grain—by SKU and charge period—while businesses need costs associated with individual transactions. Acharya proposes joining a settlement ledger of FOCUS-conformant billing data with an attribution ledger of invocation-grain usage records built on OpenTelemetry GenAI telemetry. A layered correlation spine uses trace context, A2A/MCP metadata, business-key correlation, and probabilistic matching to assign records to transactions, recording the method and confidence. A versioned rate card prices usage near real time; period reconciliation compares both ledgers with the invoice, with the unexplained residual identifying possible shadow AI. The model also proposes reporting costs per order, claim, or outcome and using mid-flight gating to limit transaction costs. In a simulation with known ground truth, Acharya reports cost coverage above 99% even when trace propagation falls to zero, recovery of planted unmetered spend within 0.24 percentage points, and p99 transaction-cost reductions of up to 61% with a 2-4% false-pause rate. These are simulation results, not evidence of performance in deployed enterprise systems. Acharya proposes the attribution ledger as an invocation-grain FOCUS profile for standardization.","question":"How would the model’s reported simulation results compare with results from enterprise systems handling real transactions and billing data?","claims":[{"text":"Acharya argues that billing data cannot answer what an individual business transaction cost in AI because providers do not see enterprise transaction boundaries.","excerpt":"The business question (what did this order, claim, or case cost in AI?) cannot be answered from billing data, because providers never see enterprise transaction boundaries.","support":"source-stated"},{"text":"The proposed Two-Ledger Model joins settlement-grain billing data with invocation-grain usage records to attribute AI costs to business transactions.","excerpt":"a settlement ledger of FOCUS-conformant billing data joined to an attribution ledger of invocation-grain usage records built on OpenTelemetry GenAI telemetry.","support":"source-stated"},{"text":"In a simulation with known ground truth, the authors report cost coverage above 99% even when trace propagation falls to zero.","excerpt":"A simulation with known ground truth shows the spine sustaining cost coverage above 99% as trace propagation falls to zero","support":"source-stated"},{"text":"In that simulation, mid-flight gating cut p99 transaction cost by up to 61%, with a 2-4% false-pause rate.","excerpt":"mid-flight gating cutting p99 transaction cost by up to 61% at a 2-4% false-pause rate.","support":"source-stated"},{"text":"Acharya proposes the attribution ledger as an invocation-grain FOCUS profile for standardization.","excerpt":"We propose the attribution ledger as an invocation-grain FOCUS profile for standardization.","support":"source-stated"}],"limitations":["The reported performance figures come from a simulation with known ground truth; the supplied abstract does not report results from deployed enterprise systems.","The supplied evidence is the paper’s abstract and does not provide the simulation setup or further methodological detail."],"mediaId":"62aa0e581fddffbbe4618dcf19fc740cacf844467ab1f0b04529f93070fdffda","correctionReason":null,"id":"df677f5994b58aacd50a6edea4c2b25c2e6a04bef23acd59072b2853d84aa49a","publicationId":"abf09e61-e171-4682-8e8c-5e8291a8c86f","version":1,"sourceUrl":"https://arxiv.org/abs/2611.06989","sourceTitle":"The Two-Ledger Model: Transaction-Grain Cost Accounting for Multi-Agent AI Systems Across Clouds, Models, and Systems of Record","publisher":"arXiv cs.AI","publishedAt":null,"originalPublished":{"value":"2026-11-04","precision":"day","basis":"publisher_citation_date"},"firstObservedAt":"2026-11-06T05:12:37.316Z","createdAt":"2026-11-09T02:53:16.090Z","historical":true,"entityIds":["arxiv"],"topicIds":["intelligence-and-discovery"],"media":[{"id":"62aa0e581fddffbbe4618dcf19fc740cacf844467ab1f0b04529f93070fdffda","kind":"article","url":"https://arxiv.org/abs/2611.06989","sourceUrl":"https://arxiv.org/abs/2611.06989","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-11-09T02:40:06.451Z","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/2611.06989","checkedAt":"2026-11-09T03:56:09.316Z","items":[],"note":"No suitable media was found by the supported page extraction."},"editorialDecision":{"outcome":"accept","reasonCodes":["material_development"],"rubricVersion":"stream-admission-v5","mediaId":"62aa0e581fddffbbe4618dcf19fc740cacf844467ab1f0b04529f93070fdffda","confidence":0.8500000000000001,"provider":"typesafe","model":"jev-1.13.0","inputHash":"77b428aa599ec985d964854966158568fcdfbfaf5f9bd2b095bd87deb2c63b32","decidedAt":"2026-11-09T02:40:07.588Z"},"provenance":{"textHash":"96c9fb8a7821f9308005ac591ad3bdd0400a521b9ea8cfad3997b01fcf813d28","observationId":"e9b849dda32745647976eabac2fc50492ae618138a97cc1e7a40e6b0c4a6bdba","retrievedAt":"2026-11-09T02:40:06.288Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"5d52de43-3842-4919-89a7-bbecb5f8695d"},"reviewer":{"model":"gpt-6-luna","runId":"f3116010-e832-4cda-869a-b5085d533dea"}},"audit":{"status":"passed","reviewedAt":"2026-11-09T02:53:16.090Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Acharya, Vivek","url":null,"kind":"unknown"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Acharya, Vivek","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Acharya, Vivek","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06989","locator":"head/meta[name=author|citation_author]"},"assertionId":"c43f712166b9a20a8816506c8c5edd59a795cc1574faa7c9f06988e1690de5d9:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T03:56:09.316Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"c43f712166b9a20a8816506c8c5edd59a795cc1574faa7c9f06988e1690de5d9","sourceUrl":"https://arxiv.org/abs/2611.06989","contentSha256":"8fc69268d611c4eaf2a349fe584501c0d42062d41d5dea006b75bdb0b99ee531","textHash":"96c9fb8a7821f9308005ac591ad3bdd0400a521b9ea8cfad3997b01fcf813d28","observedAt":"2026-11-09T03:56:09.316Z"}}],"participationCoverage":{"total":1,"returned":1,"complete":true,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":null,"sourceUrl":"https://arxiv.org/abs/2611.06989","snapshotId":"c43f712166b9a20a8816506c8c5edd59a795cc1574faa7c9f06988e1690de5d9","contentSha256":"8fc69268d611c4eaf2a349fe584501c0d42062d41d5dea006b75bdb0b99ee531","textHash":"96c9fb8a7821f9308005ac591ad3bdd0400a521b9ea8cfad3997b01fcf813d28","observedAt":"2026-11-09T03:56:09.316Z","basis":"publisher-page-metadata","sourceLinks":45,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/df677f5994b58aacd50a6edea4c2b25c2e6a04bef23acd59072b2853d84aa49a/source"}},"canonicalUrl":"https://escapemeridian.com/readings/vivek-acharya-s-two-ledger-model-links-ai-costs-to-business-df677f59","formats":{"html":"/readings/vivek-acharya-s-two-ledger-model-links-ai-costs-to-business-df677f59","markdown":"/readings/vivek-acharya-s-two-ledger-model-links-ai-costs-to-business-df677f59.md","json":"/readings/vivek-acharya-s-two-ledger-model-links-ai-costs-to-business-df677f59.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":[],"entities":[{"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"},{"id":"time","name":"TIME","kind":"organization","context":"TIME is a news magazine publishing reporting on world affairs, business, technology and the workers behind digital services.","referenceUrls":["https://time.com/"],"path":"/entities/time","json":"/entities/time.json","markdown":"/entities/time.md"}]},"researchQuestions":[],"withdrawn":false,"references":{"schemaVersion":1,"target":{"type":"reading","id":"df677f5994b58aacd50a6edea4c2b25c2e6a04bef23acd59072b2853d84aa49a","revision":"abf09e61-e171-4682-8e8c-5e8291a8c86f","revisionKind":"publication-id","title":"Vivek Acharya’s Two-Ledger Model links AI costs to business transactions","url":"https://escapemeridian.com/readings/vivek-acharya-s-two-ledger-model-links-ai-costs-to-business-df677f59"},"source":{"type":"source","id":"https://arxiv.org/abs/2611.06989","revision":"96c9fb8a7821f9308005ac591ad3bdd0400a521b9ea8cfad3997b01fcf813d28","revisionKind":"sha256-source-text","title":"The Two-Ledger Model: Transaction-Grain Cost Accounting for Multi-Agent AI Systems Across Clouds, Models, and Systems of Record","url":"https://arxiv.org/abs/2611.06989"},"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":"df677f5994b58aacd50a6edea4c2b25c2e6a04bef23acd59072b2853d84aa49a","title":"Vivek Acharya’s Two-Ledger Model links AI costs to business transactions","argument":"Vivek Acharya argues that enterprise billing data cannot answer a practical question: what did a particular order, claim, or case cost in AI? Providers bill at settlement grain—by SKU and charge period—while businesses need costs associated with individual transactions. Acharya proposes joining a settlement ledger of FOCUS-conformant billing data with an attribution ledger of invocation-grain usage records built on OpenTelemetry GenAI telemetry. A layered correlation spine uses trace context, A2A/MCP metadata, business-key correlation, and probabilistic matching to assign records to transactions, recording the method and confidence. A versioned rate card prices usage near real time; period reconciliation compares both ledgers with the invoice, with the unexplained residual identifying possible shadow AI. The model also proposes reporting costs per order, claim, or outcome and using mid-flight gating to limit transaction costs. In a simulation with known ground truth, Acharya reports cost coverage above 99% even when trace propagation falls to zero, recovery of planted unmetered spend within 0.24 percentage points, and p99 transaction-cost reductions of up to 61% with a 2-4% false-pause rate. These are simulation results, not evidence of performance in deployed enterprise systems. Acharya proposes the attribution ledger as an invocation-grain FOCUS profile for standardization.","topicIds":["intelligence-and-discovery"],"domain":"science","claimType":"attributed reading","limits":"The reported performance figures come from a simulation with known ground truth; the supplied abstract does not report results from deployed enterprise systems. The supplied evidence is the paper’s abstract and does not provide the simulation setup or further methodological detail.","speaker":{"name":"Acharya, Vivek","roleAtSource":"Article author"},"source":{"title":"The Two-Ledger Model: Transaction-Grain Cost Accounting for Multi-Agent AI Systems Across Clouds, Models, and Systems of Record","publisher":"arXiv cs.AI","format":"Article","url":"https://arxiv.org/abs/2611.06989","publishedAt":"2026-11-04","dateBasis":"Date basis not provided."},"evidence":[{"text":"Acharya argues that billing data cannot answer what an individual business transaction cost in AI because providers do not see enterprise transaction boundaries.","excerpt":"The business question (what did this order, claim, or case cost in AI?) cannot be answered from billing data, because providers never see enterprise transaction boundaries.","url":"https://arxiv.org/abs/2611.06989","relationship":"Source-stated"},{"text":"The proposed Two-Ledger Model joins settlement-grain billing data with invocation-grain usage records to attribute AI costs to business transactions.","excerpt":"a settlement ledger of FOCUS-conformant billing data joined to an attribution ledger of invocation-grain usage records built on OpenTelemetry GenAI telemetry.","url":"https://arxiv.org/abs/2611.06989","relationship":"Source-stated"},{"text":"In a simulation with known ground truth, the authors report cost coverage above 99% even when trace propagation falls to zero.","excerpt":"A simulation with known ground truth shows the spine sustaining cost coverage above 99% as trace propagation falls to zero","url":"https://arxiv.org/abs/2611.06989","relationship":"Source-stated"},{"text":"In that simulation, mid-flight gating cut p99 transaction cost by up to 61%, with a 2-4% false-pause rate.","excerpt":"mid-flight gating cutting p99 transaction cost by up to 61% at a 2-4% false-pause rate.","url":"https://arxiv.org/abs/2611.06989","relationship":"Source-stated"},{"text":"Acharya proposes the attribution ledger as an invocation-grain FOCUS profile for standardization.","excerpt":"We propose the attribution ledger as an invocation-grain FOCUS profile for standardization.","url":"https://arxiv.org/abs/2611.06989","relationship":"Source-stated"}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2611.06989","checkedAt":"2026-11-09T03:56:09.316Z","items":[],"note":"No suitable media was found by the supported page extraction."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"How would the model’s reported simulation results compare with results from enterprise systems handling real transactions and billing data?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Vivek Acharya’s Two-Ledger Model links AI costs to business transactions","summary":"Vivek Acharya argues that enterprise billing data cannot answer a practical question: what did a particular order, claim, or case cost in AI? Providers bill at settlement grain—by SKU and charge period—while businesses need costs associated with individual transactions. Acharya proposes joining a settlement ledger of FOCUS-conformant billing data with an attribution ledger of invocation-grain usage records built on OpenTelemetry GenAI telemetry. A layered correlation spine uses trace context, A2A/MCP metadata, business-key correlation, and probabilistic matching to assign records to transactions, recording the method and confidence. A versioned rate card prices usage near real time; period reconciliation compares both ledgers with the invoice, with the unexplained residual identifying possible shadow AI. The model also proposes reporting costs per order, claim, or outcome and using mid-flight gating to limit transaction costs. In a simulation with known ground truth, Acharya reports cost coverage above 99% even when trace propagation falls to zero, recovery of planted unmetered spend within 0.24 percentage points, and p99 transaction-cost reductions of up to 61% with a 2-4% false-pause rate. These are simulation results, not evidence of performance in deployed enterprise systems. Acharya proposes the attribution ledger as an invocation-grain FOCUS profile for standardization.","question":"How would the model’s reported simulation results compare with results from enterprise systems handling real transactions and billing data?","claims":[{"text":"Acharya argues that billing data cannot answer what an individual business transaction cost in AI because providers do not see enterprise transaction boundaries.","excerpt":"The business question (what did this order, claim, or case cost in AI?) cannot be answered from billing data, because providers never see enterprise transaction boundaries.","support":"source-stated"},{"text":"The proposed Two-Ledger Model joins settlement-grain billing data with invocation-grain usage records to attribute AI costs to business transactions.","excerpt":"a settlement ledger of FOCUS-conformant billing data joined to an attribution ledger of invocation-grain usage records built on OpenTelemetry GenAI telemetry.","support":"source-stated"},{"text":"In a simulation with known ground truth, the authors report cost coverage above 99% even when trace propagation falls to zero.","excerpt":"A simulation with known ground truth shows the spine sustaining cost coverage above 99% as trace propagation falls to zero","support":"source-stated"},{"text":"In that simulation, mid-flight gating cut p99 transaction cost by up to 61%, with a 2-4% false-pause rate.","excerpt":"mid-flight gating cutting p99 transaction cost by up to 61% at a 2-4% false-pause rate.","support":"source-stated"},{"text":"Acharya proposes the attribution ledger as an invocation-grain FOCUS profile for standardization.","excerpt":"We propose the attribution ledger as an invocation-grain FOCUS profile for standardization.","support":"source-stated"}],"limitations":["The reported performance figures come from a simulation with known ground truth; the supplied abstract does not report results from deployed enterprise systems.","The supplied evidence is the paper’s abstract and does not provide the simulation setup or further methodological detail."],"mediaId":"62aa0e581fddffbbe4618dcf19fc740cacf844467ab1f0b04529f93070fdffda","correctionReason":null,"id":"df677f5994b58aacd50a6edea4c2b25c2e6a04bef23acd59072b2853d84aa49a","publicationId":"abf09e61-e171-4682-8e8c-5e8291a8c86f","version":1,"sourceUrl":"https://arxiv.org/abs/2611.06989","sourceTitle":"The Two-Ledger Model: Transaction-Grain Cost Accounting for Multi-Agent AI Systems Across Clouds, Models, and Systems of Record","publisher":"arXiv cs.AI","publishedAt":null,"originalPublished":{"value":"2026-11-04","precision":"day","basis":"publisher_citation_date"},"firstObservedAt":"2026-11-06T05:12:37.316Z","createdAt":"2026-11-09T02:53:16.090Z","historical":true,"entityIds":["arxiv"],"topicIds":["intelligence-and-discovery"],"media":[{"id":"62aa0e581fddffbbe4618dcf19fc740cacf844467ab1f0b04529f93070fdffda","kind":"article","url":"https://arxiv.org/abs/2611.06989","sourceUrl":"https://arxiv.org/abs/2611.06989","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-11-09T02:40:06.451Z","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/2611.06989","checkedAt":"2026-11-09T03:56:09.316Z","items":[],"note":"No suitable media was found by the supported page extraction."},"editorialDecision":{"outcome":"accept","reasonCodes":["material_development"],"rubricVersion":"stream-admission-v5","mediaId":"62aa0e581fddffbbe4618dcf19fc740cacf844467ab1f0b04529f93070fdffda","confidence":0.8500000000000001,"provider":"typesafe","model":"jev-1.13.0","inputHash":"77b428aa599ec985d964854966158568fcdfbfaf5f9bd2b095bd87deb2c63b32","decidedAt":"2026-11-09T02:40:07.588Z"},"provenance":{"textHash":"96c9fb8a7821f9308005ac591ad3bdd0400a521b9ea8cfad3997b01fcf813d28","observationId":"e9b849dda32745647976eabac2fc50492ae618138a97cc1e7a40e6b0c4a6bdba","retrievedAt":"2026-11-09T02:40:06.288Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"5d52de43-3842-4919-89a7-bbecb5f8695d"},"reviewer":{"model":"gpt-6-luna","runId":"f3116010-e832-4cda-869a-b5085d533dea"}},"audit":{"status":"passed","reviewedAt":"2026-11-09T02:53:16.090Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Acharya, Vivek","url":null,"kind":"unknown"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Acharya, Vivek","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Acharya, Vivek","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2611.06989","locator":"head/meta[name=author|citation_author]"},"assertionId":"c43f712166b9a20a8816506c8c5edd59a795cc1574faa7c9f06988e1690de5d9:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-09T03:56:09.316Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"c43f712166b9a20a8816506c8c5edd59a795cc1574faa7c9f06988e1690de5d9","sourceUrl":"https://arxiv.org/abs/2611.06989","contentSha256":"8fc69268d611c4eaf2a349fe584501c0d42062d41d5dea006b75bdb0b99ee531","textHash":"96c9fb8a7821f9308005ac591ad3bdd0400a521b9ea8cfad3997b01fcf813d28","observedAt":"2026-11-09T03:56:09.316Z"}}],"participationCoverage":{"total":1,"returned":1,"complete":true,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":null,"sourceUrl":"https://arxiv.org/abs/2611.06989","snapshotId":"c43f712166b9a20a8816506c8c5edd59a795cc1574faa7c9f06988e1690de5d9","contentSha256":"8fc69268d611c4eaf2a349fe584501c0d42062d41d5dea006b75bdb0b99ee531","textHash":"96c9fb8a7821f9308005ac591ad3bdd0400a521b9ea8cfad3997b01fcf813d28","observedAt":"2026-11-09T03:56:09.316Z","basis":"publisher-page-metadata","sourceLinks":45,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/df677f5994b58aacd50a6edea4c2b25c2e6a04bef23acd59072b2853d84aa49a/source"}}}],"audits":[{"publicationId":"abf09e61-e171-4682-8e8c-5e8291a8c86f","verdict":"passed","findings":[{"dimension":"attribution","status":"pass","explanation":"The source lists a single author, Vivek Acharya, and the reading attributes the argument, proposal and simulation results to him. One claim says 'the authors report,' which is a minor wording slip for a single-author paper; it does not misattribute the work. The smallest repair is to change it to 'Acharya reports.'","excerpt":"Authors:Vivek Acharya"},{"dimension":"summary","status":"pass","explanation":"The reading leads with the actor and his central problem: billing cannot show the AI cost of an order, claim or case. It explains settlement grain and keeps the technical terms exact; terms such as FOCUS, OpenTelemetry, A2A/MCP, p99 and shadow AI suit tooltips. The proposal and its simulation caveat are faithful. Small fidelity repairs: mention that these are multi-agent AI systems spanning clouds and models, and note that the residual also flags provider billing errors. 'Possible shadow AI' slightly softens the source's 'identifies shadow AI.'","excerpt":"Enterprises run business transactions through multi-agent AI systems spanning clouds, large language models (LLMs), orchestration harnesses, and systems of record."},{"dimension":"date","status":"pass","explanation":"The originalPublished date, 2026-11-04, matches the arXiv v1 submission date. The feed date of 2026-11-06 is later and correctly not used.","excerpt":"[Submitted on 4 Nov 2026]"},{"dimension":"support","status":"pass","explanation":"Each claim quotes the abstract verbatim. The reading frames the figures as simulation results rather than evidence from deployed systems, and the question about real-world performance follows from that gap without implying an answer. No unsupported benefits or costs are added.","excerpt":"A simulation with known ground truth shows the spine sustaining cost coverage above 99% as trace propagation falls to zero"},{"dimension":"media","status":"pass","explanation":"The selected media is the verified arXiv abstract page for this paper, which is the direct original source.","excerpt":null}],"createdAt":"2026-11-09T02:53:16.090Z","model":"anthropic/claude-opus-5.5"}],"correctionUrl":"https://escapemeridian.com/corrections/"}