{"id":"bb911791996cd23456290e63f78f22a06b767964edb2773471731e3222615043","title":"Asang Dani and Shailesh R Sathe study Cross Lingual Abstractive Summarization for Marathi","argument":"Asang Dani and Shailesh R Sathe study cross-lingual summarization for Marathi, a task they say remains relatively underexplored for Indic languages. They construct cross-lingual training data from the monolingual Marathi MahaSum corpus, combine it with the smaller cross-lingual PMIndiaSum dataset, and fine-tune IndicTrans2, an Indic neural machine translation model. The authors evaluate the resulting models with ROUGE, chrF and chrF++ metrics, focusing primarily on Marathi-to-English summarization because of computational constraints; they also discuss the English-to-Marathi direction. They report that their approach yields substantially better summarization performance than IndicBART and mBART-50 based baselines reported in previous work. Escape Meridian interpretation: the study offers a specific route for building and evaluating Marathi summarization systems from existing corpora and a pretrained translation model. The abstract does not give the metric scores behind that comparison.","topicIds":["intelligence-and-discovery"],"domain":"science","claimType":"attributed reading","limits":"The abstract does not provide the metric scores behind its reported performance comparison. The evaluation focuses primarily on Marathi-to-English summarization because of computational constraints; the abstract discusses, but does not report evaluation results for, English-to-Marathi summarization.","speaker":{"name":"Dani, Asang, Sathe, Shailesh R","roleAtSource":"Article author"},"source":{"title":"Cross Lingual Abstractive Summarization for Marathi","publisher":"arXiv cs.AI","format":"Article","url":"https://arxiv.org/abs/2610.38267","publishedAt":"2026-10-28","dateBasis":"Date basis not provided."},"evidence":[{"text":"The authors say monolingual and cross-lingual summarization remain relatively underexplored for Indic languages.","excerpt":"both monolingual summarization (MS) and cross-lingual summarization (CLS) remain relatively underexplored for these languages.","url":"https://arxiv.org/abs/2610.38267","relationship":"Source-stated"},{"text":"The study builds cross-lingual training data from MahaSum and combines it with PMIndiaSum to fine-tune IndicTrans2.","excerpt":"we construct cross-lingual training data from the monolingual Marathi MahaSum corpus and combine it with the smaller cross-lingual PMIndiaSum dataset to fine-tune IndicTrans2","url":"https://arxiv.org/abs/2610.38267","relationship":"Source-stated"},{"text":"The evaluation focuses primarily on Marathi-to-English summarization because of computational constraints, and also discusses English-to-Marathi.","excerpt":"focusing primarily on Marathi-to-English summarization due to computational constraints. We also discuss the applicability of our approach to the English-to-Marathi direction.","url":"https://arxiv.org/abs/2610.38267","relationship":"Source-stated"},{"text":"The authors report better summarization performance than the IndicBART and mBART-50 based baselines reported in previous work.","excerpt":"yields substantially better summarization performance than the IndicBART and mBART-50 based baselines reported in previous work on cross-lingual summarization.","url":"https://arxiv.org/abs/2610.38267","relationship":"Source-stated"},{"text":"The approach provides a route for constructing and evaluating Marathi summarization systems using existing corpora and a pretrained translation model.","excerpt":"construct cross-lingual training data from the monolingual Marathi MahaSum corpus and combine it with the smaller cross-lingual PMIndiaSum dataset to fine-tune IndicTrans2","url":"https://arxiv.org/abs/2610.38267","relationship":"Escape Meridian interpretation"}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2610.38267","checkedAt":"2026-11-11T12:42:11.968Z","items":[],"note":"No suitable media was found by the supported page extraction."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"How large were the reported gains on the evaluation metrics?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Asang Dani and Shailesh R Sathe study Cross Lingual Abstractive Summarization for Marathi","summary":"Asang Dani and Shailesh R Sathe study cross-lingual summarization for Marathi, a task they say remains relatively underexplored for Indic languages. They construct cross-lingual training data from the monolingual Marathi MahaSum corpus, combine it with the smaller cross-lingual PMIndiaSum dataset, and fine-tune IndicTrans2, an Indic neural machine translation model. The authors evaluate the resulting models with ROUGE, chrF and chrF++ metrics, focusing primarily on Marathi-to-English summarization because of computational constraints; they also discuss the English-to-Marathi direction. They report that their approach yields substantially better summarization performance than IndicBART and mBART-50 based baselines reported in previous work. Escape Meridian interpretation: the study offers a specific route for building and evaluating Marathi summarization systems from existing corpora and a pretrained translation model. The abstract does not give the metric scores behind that comparison.","question":"How large were the reported gains on the evaluation metrics?","claims":[{"text":"The authors say monolingual and cross-lingual summarization remain relatively underexplored for Indic languages.","excerpt":"both monolingual summarization (MS) and cross-lingual summarization (CLS) remain relatively underexplored for these languages.","support":"source-stated"},{"text":"The study builds cross-lingual training data from MahaSum and combines it with PMIndiaSum to fine-tune IndicTrans2.","excerpt":"we construct cross-lingual training data from the monolingual Marathi MahaSum corpus and combine it with the smaller cross-lingual PMIndiaSum dataset to fine-tune IndicTrans2","support":"source-stated"},{"text":"The evaluation focuses primarily on Marathi-to-English summarization because of computational constraints, and also discusses English-to-Marathi.","excerpt":"focusing primarily on Marathi-to-English summarization due to computational constraints. We also discuss the applicability of our approach to the English-to-Marathi direction.","support":"source-stated"},{"text":"The authors report better summarization performance than the IndicBART and mBART-50 based baselines reported in previous work.","excerpt":"yields substantially better summarization performance than the IndicBART and mBART-50 based baselines reported in previous work on cross-lingual summarization.","support":"source-stated"},{"text":"The approach provides a route for constructing and evaluating Marathi summarization systems using existing corpora and a pretrained translation model.","excerpt":"construct cross-lingual training data from the monolingual Marathi MahaSum corpus and combine it with the smaller cross-lingual PMIndiaSum dataset to fine-tune IndicTrans2","support":"interpretation"}],"limitations":["The abstract does not provide the metric scores behind its reported performance comparison.","The evaluation focuses primarily on Marathi-to-English summarization because of computational constraints; the abstract discusses, but does not report evaluation results for, English-to-Marathi summarization."],"mediaId":"7df49c5cd42e33c07bba1023c7217220083c3a78c4415e8d5e9832d99e599a4e","correctionReason":null,"id":"bb911791996cd23456290e63f78f22a06b767964edb2773471731e3222615043","publicationId":"143d8a6e-12c8-41ad-853e-93541e69ed1d","version":1,"sourceUrl":"https://arxiv.org/abs/2610.38267","sourceTitle":"Cross Lingual Abstractive Summarization for Marathi","publisher":"arXiv cs.AI","publishedAt":null,"originalPublished":{"value":"2026-10-28","precision":"day","basis":"publisher_citation_date"},"firstObservedAt":"2026-10-30T06:45:31.410Z","createdAt":"2026-11-11T12:11:11.423Z","historical":true,"entityIds":["arxiv"],"topicIds":["intelligence-and-discovery"],"media":[{"id":"7df49c5cd42e33c07bba1023c7217220083c3a78c4415e8d5e9832d99e599a4e","kind":"article","url":"https://arxiv.org/abs/2610.38267","sourceUrl":"https://arxiv.org/abs/2610.38267","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-10-31T10:02:13.542Z","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/2610.38267","checkedAt":"2026-11-11T12:42:11.968Z","items":[],"note":"No suitable media was found by the supported page extraction."},"editorialDecision":{"outcome":"accept","reasonCodes":["material_development"],"rubricVersion":"stream-admission-v5","mediaId":"7df49c5cd42e33c07bba1023c7217220083c3a78c4415e8d5e9832d99e599a4e","confidence":0.74,"provider":"typesafe","model":"jev-1.13.0","inputHash":"7d7e709f8f64162002203969d9ed7d22fd962bf7857b4d3e9cb45b48bebe5974","decidedAt":"2026-10-31T10:02:15.248Z","redecided":{"from":"stream-admission-v5","under":"stream-admission-v5+confidence-0.5"}},"provenance":{"textHash":"1034e158faf20fe17285d2fe4bd605f4e20e52192f6ead9d539c2f9fc8b0c04e","observationId":"8986e5762ae895f0b4d10e3946581cf3c8fa1b915557685fbdac5fb2c2c21a65","retrievedAt":"2026-10-31T10:02:13.192Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"ef4bc5f1-2b8a-4341-855b-cbbd3a3f2411"},"reviewer":{"model":"gpt-6-luna","runId":"7f3eac71-fb6d-4d48-8f3b-5ec35415b722"}},"audit":{"status":"uncertain","reviewedAt":"2026-11-11T12:11:11.423Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Dani, Asang","url":null,"kind":"unknown"},{"name":"Sathe, Shailesh R","url":null,"kind":"unknown"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Dani, Asang","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Dani, Asang","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2610.38267","locator":"head/meta[name=author|citation_author]"},"assertionId":"6ed82ae891453e7e932f645c9633302388cb0692fba7b5cc378872e978582c0c:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-11T12:42:11.968Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"6ed82ae891453e7e932f645c9633302388cb0692fba7b5cc378872e978582c0c","sourceUrl":"https://arxiv.org/abs/2610.38267","contentSha256":"7e86cd11a2232ab5f8ff1f7ca2bb902605fd0d36b731afa458549bbbf6aba175","textHash":"1034e158faf20fe17285d2fe4bd605f4e20e52192f6ead9d539c2f9fc8b0c04e","observedAt":"2026-11-11T12:42:11.968Z"}},{"actor":{"name":"Sathe, Shailesh R","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Sathe, Shailesh R","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2610.38267","locator":"head/meta[name=author|citation_author]"},"assertionId":"6ed82ae891453e7e932f645c9633302388cb0692fba7b5cc378872e978582c0c:participation:1","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-11T12:42:11.968Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"6ed82ae891453e7e932f645c9633302388cb0692fba7b5cc378872e978582c0c","sourceUrl":"https://arxiv.org/abs/2610.38267","contentSha256":"7e86cd11a2232ab5f8ff1f7ca2bb902605fd0d36b731afa458549bbbf6aba175","textHash":"1034e158faf20fe17285d2fe4bd605f4e20e52192f6ead9d539c2f9fc8b0c04e","observedAt":"2026-11-11T12:42:11.968Z"}}],"participationCoverage":{"total":2,"returned":2,"complete":true,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":null,"sourceUrl":"https://arxiv.org/abs/2610.38267","snapshotId":"6ed82ae891453e7e932f645c9633302388cb0692fba7b5cc378872e978582c0c","contentSha256":"7e86cd11a2232ab5f8ff1f7ca2bb902605fd0d36b731afa458549bbbf6aba175","textHash":"1034e158faf20fe17285d2fe4bd605f4e20e52192f6ead9d539c2f9fc8b0c04e","observedAt":"2026-11-11T12:42:11.968Z","basis":"publisher-page-metadata","sourceLinks":41,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/bb911791996cd23456290e63f78f22a06b767964edb2773471731e3222615043/source"}},"canonicalUrl":"https://escapemeridian.com/readings/asang-dani-and-shailesh-r-sathe-study-cross-lingual-abstractive-bb911791","formats":{"html":"/readings/asang-dani-and-shailesh-r-sathe-study-cross-lingual-abstractive-bb911791","markdown":"/readings/asang-dani-and-shailesh-r-sathe-study-cross-lingual-abstractive-bb911791.md","json":"/readings/asang-dani-and-shailesh-r-sathe-study-cross-lingual-abstractive-bb911791.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-fine-tuning","name":"Fine-tuning","explanation":"Further training of an existing model to adapt it to a particular task or use.","referenceUrl":"https://developers.google.com/machine-learning/glossary#fine-tuning"},{"id":"term-pre-training","name":"Pre-training","explanation":"A model's initial training on a large dataset, before further adaptation for particular uses.","referenceUrl":"https://developers.google.com/machine-learning/glossary#pre-training"}],"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"}]},"researchQuestions":[],"withdrawn":false,"references":{"schemaVersion":1,"target":{"type":"reading","id":"bb911791996cd23456290e63f78f22a06b767964edb2773471731e3222615043","revision":"143d8a6e-12c8-41ad-853e-93541e69ed1d","revisionKind":"publication-id","title":"Asang Dani and Shailesh R Sathe study Cross Lingual Abstractive Summarization for Marathi","url":"https://escapemeridian.com/readings/asang-dani-and-shailesh-r-sathe-study-cross-lingual-abstractive-bb911791"},"source":{"type":"source","id":"https://arxiv.org/abs/2610.38267","revision":"1034e158faf20fe17285d2fe4bd605f4e20e52192f6ead9d539c2f9fc8b0c04e","revisionKind":"sha256-source-text","title":"Cross Lingual Abstractive Summarization for Marathi","url":"https://arxiv.org/abs/2610.38267"},"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":"bb911791996cd23456290e63f78f22a06b767964edb2773471731e3222615043","title":"Asang Dani and Shailesh R Sathe study Cross Lingual Abstractive Summarization for Marathi","argument":"Asang Dani and Shailesh R Sathe study cross-lingual summarization for Marathi, a task they say remains relatively underexplored for Indic languages. They construct cross-lingual training data from the monolingual Marathi MahaSum corpus, combine it with the smaller cross-lingual PMIndiaSum dataset, and fine-tune IndicTrans2, an Indic neural machine translation model. The authors evaluate the resulting models with ROUGE, chrF and chrF++ metrics, focusing primarily on Marathi-to-English summarization because of computational constraints; they also discuss the English-to-Marathi direction. They report that their approach yields substantially better summarization performance than IndicBART and mBART-50 based baselines reported in previous work. Escape Meridian interpretation: the study offers a specific route for building and evaluating Marathi summarization systems from existing corpora and a pretrained translation model. The abstract does not give the metric scores behind that comparison.","topicIds":["intelligence-and-discovery"],"domain":"science","claimType":"attributed reading","limits":"The abstract does not provide the metric scores behind its reported performance comparison. The evaluation focuses primarily on Marathi-to-English summarization because of computational constraints; the abstract discusses, but does not report evaluation results for, English-to-Marathi summarization.","speaker":{"name":"Dani, Asang, Sathe, Shailesh R","roleAtSource":"Article author"},"source":{"title":"Cross Lingual Abstractive Summarization for Marathi","publisher":"arXiv cs.AI","format":"Article","url":"https://arxiv.org/abs/2610.38267","publishedAt":"2026-10-28","dateBasis":"Date basis not provided."},"evidence":[{"text":"The authors say monolingual and cross-lingual summarization remain relatively underexplored for Indic languages.","excerpt":"both monolingual summarization (MS) and cross-lingual summarization (CLS) remain relatively underexplored for these languages.","url":"https://arxiv.org/abs/2610.38267","relationship":"Source-stated"},{"text":"The study builds cross-lingual training data from MahaSum and combines it with PMIndiaSum to fine-tune IndicTrans2.","excerpt":"we construct cross-lingual training data from the monolingual Marathi MahaSum corpus and combine it with the smaller cross-lingual PMIndiaSum dataset to fine-tune IndicTrans2","url":"https://arxiv.org/abs/2610.38267","relationship":"Source-stated"},{"text":"The evaluation focuses primarily on Marathi-to-English summarization because of computational constraints, and also discusses English-to-Marathi.","excerpt":"focusing primarily on Marathi-to-English summarization due to computational constraints. We also discuss the applicability of our approach to the English-to-Marathi direction.","url":"https://arxiv.org/abs/2610.38267","relationship":"Source-stated"},{"text":"The authors report better summarization performance than the IndicBART and mBART-50 based baselines reported in previous work.","excerpt":"yields substantially better summarization performance than the IndicBART and mBART-50 based baselines reported in previous work on cross-lingual summarization.","url":"https://arxiv.org/abs/2610.38267","relationship":"Source-stated"},{"text":"The approach provides a route for constructing and evaluating Marathi summarization systems using existing corpora and a pretrained translation model.","excerpt":"construct cross-lingual training data from the monolingual Marathi MahaSum corpus and combine it with the smaller cross-lingual PMIndiaSum dataset to fine-tune IndicTrans2","url":"https://arxiv.org/abs/2610.38267","relationship":"Escape Meridian interpretation"}],"sourceMedia":{"status":"not_found","sourceUrl":"https://arxiv.org/abs/2610.38267","checkedAt":"2026-11-11T12:42:11.968Z","items":[],"note":"No suitable media was found by the supported page extraction."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"How large were the reported gains on the evaluation metrics?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Asang Dani and Shailesh R Sathe study Cross Lingual Abstractive Summarization for Marathi","summary":"Asang Dani and Shailesh R Sathe study cross-lingual summarization for Marathi, a task they say remains relatively underexplored for Indic languages. They construct cross-lingual training data from the monolingual Marathi MahaSum corpus, combine it with the smaller cross-lingual PMIndiaSum dataset, and fine-tune IndicTrans2, an Indic neural machine translation model. The authors evaluate the resulting models with ROUGE, chrF and chrF++ metrics, focusing primarily on Marathi-to-English summarization because of computational constraints; they also discuss the English-to-Marathi direction. They report that their approach yields substantially better summarization performance than IndicBART and mBART-50 based baselines reported in previous work. Escape Meridian interpretation: the study offers a specific route for building and evaluating Marathi summarization systems from existing corpora and a pretrained translation model. The abstract does not give the metric scores behind that comparison.","question":"How large were the reported gains on the evaluation metrics?","claims":[{"text":"The authors say monolingual and cross-lingual summarization remain relatively underexplored for Indic languages.","excerpt":"both monolingual summarization (MS) and cross-lingual summarization (CLS) remain relatively underexplored for these languages.","support":"source-stated"},{"text":"The study builds cross-lingual training data from MahaSum and combines it with PMIndiaSum to fine-tune IndicTrans2.","excerpt":"we construct cross-lingual training data from the monolingual Marathi MahaSum corpus and combine it with the smaller cross-lingual PMIndiaSum dataset to fine-tune IndicTrans2","support":"source-stated"},{"text":"The evaluation focuses primarily on Marathi-to-English summarization because of computational constraints, and also discusses English-to-Marathi.","excerpt":"focusing primarily on Marathi-to-English summarization due to computational constraints. We also discuss the applicability of our approach to the English-to-Marathi direction.","support":"source-stated"},{"text":"The authors report better summarization performance than the IndicBART and mBART-50 based baselines reported in previous work.","excerpt":"yields substantially better summarization performance than the IndicBART and mBART-50 based baselines reported in previous work on cross-lingual summarization.","support":"source-stated"},{"text":"The approach provides a route for constructing and evaluating Marathi summarization systems using existing corpora and a pretrained translation model.","excerpt":"construct cross-lingual training data from the monolingual Marathi MahaSum corpus and combine it with the smaller cross-lingual PMIndiaSum dataset to fine-tune IndicTrans2","support":"interpretation"}],"limitations":["The abstract does not provide the metric scores behind its reported performance comparison.","The evaluation focuses primarily on Marathi-to-English summarization because of computational constraints; the abstract discusses, but does not report evaluation results for, English-to-Marathi summarization."],"mediaId":"7df49c5cd42e33c07bba1023c7217220083c3a78c4415e8d5e9832d99e599a4e","correctionReason":null,"id":"bb911791996cd23456290e63f78f22a06b767964edb2773471731e3222615043","publicationId":"143d8a6e-12c8-41ad-853e-93541e69ed1d","version":1,"sourceUrl":"https://arxiv.org/abs/2610.38267","sourceTitle":"Cross Lingual Abstractive Summarization for Marathi","publisher":"arXiv cs.AI","publishedAt":null,"originalPublished":{"value":"2026-10-28","precision":"day","basis":"publisher_citation_date"},"firstObservedAt":"2026-10-30T06:45:31.410Z","createdAt":"2026-11-11T12:11:11.423Z","historical":true,"entityIds":["arxiv"],"topicIds":["intelligence-and-discovery"],"media":[{"id":"7df49c5cd42e33c07bba1023c7217220083c3a78c4415e8d5e9832d99e599a4e","kind":"article","url":"https://arxiv.org/abs/2610.38267","sourceUrl":"https://arxiv.org/abs/2610.38267","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-10-31T10:02:13.542Z","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/2610.38267","checkedAt":"2026-11-11T12:42:11.968Z","items":[],"note":"No suitable media was found by the supported page extraction."},"editorialDecision":{"outcome":"accept","reasonCodes":["material_development"],"rubricVersion":"stream-admission-v5","mediaId":"7df49c5cd42e33c07bba1023c7217220083c3a78c4415e8d5e9832d99e599a4e","confidence":0.74,"provider":"typesafe","model":"jev-1.13.0","inputHash":"7d7e709f8f64162002203969d9ed7d22fd962bf7857b4d3e9cb45b48bebe5974","decidedAt":"2026-10-31T10:02:15.248Z","redecided":{"from":"stream-admission-v5","under":"stream-admission-v5+confidence-0.5"}},"provenance":{"textHash":"1034e158faf20fe17285d2fe4bd605f4e20e52192f6ead9d539c2f9fc8b0c04e","observationId":"8986e5762ae895f0b4d10e3946581cf3c8fa1b915557685fbdac5fb2c2c21a65","retrievedAt":"2026-10-31T10:02:13.192Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"ef4bc5f1-2b8a-4341-855b-cbbd3a3f2411"},"reviewer":{"model":"gpt-6-luna","runId":"7f3eac71-fb6d-4d48-8f3b-5ec35415b722"}},"audit":{"status":"uncertain","reviewedAt":"2026-11-11T12:11:11.423Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Dani, Asang","url":null,"kind":"unknown"},{"name":"Sathe, Shailesh R","url":null,"kind":"unknown"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Dani, Asang","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Dani, Asang","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2610.38267","locator":"head/meta[name=author|citation_author]"},"assertionId":"6ed82ae891453e7e932f645c9633302388cb0692fba7b5cc378872e978582c0c:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-11T12:42:11.968Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"6ed82ae891453e7e932f645c9633302388cb0692fba7b5cc378872e978582c0c","sourceUrl":"https://arxiv.org/abs/2610.38267","contentSha256":"7e86cd11a2232ab5f8ff1f7ca2bb902605fd0d36b731afa458549bbbf6aba175","textHash":"1034e158faf20fe17285d2fe4bd605f4e20e52192f6ead9d539c2f9fc8b0c04e","observedAt":"2026-11-11T12:42:11.968Z"}},{"actor":{"name":"Sathe, Shailesh R","url":null,"kind":"unknown","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Sathe, Shailesh R","status":"stated","provenance":{"basis":"head-meta","sourceUrl":"https://arxiv.org/abs/2610.38267","locator":"head/meta[name=author|citation_author]"},"assertionId":"6ed82ae891453e7e932f645c9633302388cb0692fba7b5cc378872e978582c0c:participation:1","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-11T12:42:11.968Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"6ed82ae891453e7e932f645c9633302388cb0692fba7b5cc378872e978582c0c","sourceUrl":"https://arxiv.org/abs/2610.38267","contentSha256":"7e86cd11a2232ab5f8ff1f7ca2bb902605fd0d36b731afa458549bbbf6aba175","textHash":"1034e158faf20fe17285d2fe4bd605f4e20e52192f6ead9d539c2f9fc8b0c04e","observedAt":"2026-11-11T12:42:11.968Z"}}],"participationCoverage":{"total":2,"returned":2,"complete":true,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":null,"sourceUrl":"https://arxiv.org/abs/2610.38267","snapshotId":"6ed82ae891453e7e932f645c9633302388cb0692fba7b5cc378872e978582c0c","contentSha256":"7e86cd11a2232ab5f8ff1f7ca2bb902605fd0d36b731afa458549bbbf6aba175","textHash":"1034e158faf20fe17285d2fe4bd605f4e20e52192f6ead9d539c2f9fc8b0c04e","observedAt":"2026-11-11T12:42:11.968Z","basis":"publisher-page-metadata","sourceLinks":41,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/bb911791996cd23456290e63f78f22a06b767964edb2773471731e3222615043/source"}}}],"audits":[{"publicationId":"143d8a6e-12c8-41ad-853e-93541e69ed1d","verdict":"uncertain","findings":[{"dimension":"attribution","status":"pass","explanation":"The reading correctly attributes the work to Asang Dani and Shailesh R Sathe. It frames the underexplored-status claim and the performance comparison as the authors' assertions.","excerpt":"Authors:Asang Dani, Shailesh R Sathe"},{"dimension":"summary","status":"uncertain","explanation":"The reading tracks the abstract faithfully, but its central terms are not explained for a non-specialist. It never says that cross-lingual summarization means summarizing text written in one language into another language. It does not say that Marathi is an Indian language or what abstractive summarization is. ROUGE, chrF and chrF++ go unexplained. Smallest repair: add plain-language glosses, or term-library tooltips, for cross-lingual summarization, Marathi and the metrics.","excerpt":"both monolingual summarization (MS) and cross-lingual summarization (CLS) remain relatively underexplored for these languages."},{"dimension":"date","status":"pass","explanation":"The originalPublished value of 2026-10-28 matches the v1 submission date shown on the arXiv page. The feed date is later and is correctly not used.","excerpt":"[Submitted on 28 Oct 2026]"},{"dimension":"support","status":"pass","explanation":"Each claim matches the abstract. The interpretation is explicitly labeled and modest. The limitations accurately note that no scores are given in the abstract and that English-to-Marathi is only discussed. The question follows from the missing scores and does not lead the reader.","excerpt":"yields substantially better summarization performance than the IndicBART and mBART-50 based baselines reported in previous work on cross-lingual summarization."},{"dimension":"media","status":"pass","explanation":"The selected media is the verified direct link to the original arXiv abstract page, which is the most direct way to access the source.","excerpt":null}],"createdAt":"2026-11-11T12:11:11.423Z","model":"anthropic/claude-opus-5.5"}],"correctionUrl":"https://escapemeridian.com/corrections/"}