{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6XX3AHPIV2ZGHTZ2PBVPSTPV2X","short_pith_number":"pith:6XX3AHPI","schema_version":"1.0","canonical_sha256":"f5efb01de8aeb263cf3a786af94df5d5db2374f4bf2c6e11ca144ae6d9de54a9","source":{"kind":"arxiv","id":"2502.08279","version":4},"attestation_state":"computed","paper":{"title":"What Is That Talk About? A Video-to-Text Summarization Dataset for Scientific Presentations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Chenxi Whitehouse, Dongqi Liu, Louis Mahon, Mirella Lapata, Rohit Saxena, Vera Demberg, Xi Yu, Yifu Qiu, Zheng Zhao","submitted_at":"2025-02-12T10:36:55Z","abstract_excerpt":"Transforming recorded videos into concise and accurate textual summaries is a growing challenge in multimodal learning. This paper introduces VISTA, a dataset specifically designed for video-to-text summarization in scientific domains. VISTA contains 18,599 recorded AI conference presentations paired with their corresponding paper abstracts. We benchmark the performance of state-of-the-art large models and apply a plan-based framework to better capture the structured nature of abstracts. Both human and automated evaluations confirm that explicit planning enhances summary quality and factual co"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2502.08279","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-12T10:36:55Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"3a921d7675f17f221eebd47939098682a7d7af5b342e662eeaadf32453c16c8c","abstract_canon_sha256":"ae9a04f6ca7c0a01921c4417dc7553ab174fbd1366cfdc61e07f9019cf7fcdd7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:08.142500Z","signature_b64":"eolbdEKfCTbmZN/3HzjzdxKK4Qqn8Z03RGfCBQlqo5wrzuniKGbn+ZrQBusetjyp2kr7XcMIQuxyHyuy5gLrDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5efb01de8aeb263cf3a786af94df5d5db2374f4bf2c6e11ca144ae6d9de54a9","last_reissued_at":"2026-07-05T11:09:08.142033Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:08.142033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What Is That Talk About? A Video-to-Text Summarization Dataset for Scientific Presentations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Chenxi Whitehouse, Dongqi Liu, Louis Mahon, Mirella Lapata, Rohit Saxena, Vera Demberg, Xi Yu, Yifu Qiu, Zheng Zhao","submitted_at":"2025-02-12T10:36:55Z","abstract_excerpt":"Transforming recorded videos into concise and accurate textual summaries is a growing challenge in multimodal learning. This paper introduces VISTA, a dataset specifically designed for video-to-text summarization in scientific domains. VISTA contains 18,599 recorded AI conference presentations paired with their corresponding paper abstracts. We benchmark the performance of state-of-the-art large models and apply a plan-based framework to better capture the structured nature of abstracts. Both human and automated evaluations confirm that explicit planning enhances summary quality and factual co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08279","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2502.08279/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2502.08279","created_at":"2026-07-05T11:09:08.142090+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.08279v4","created_at":"2026-07-05T11:09:08.142090+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08279","created_at":"2026-07-05T11:09:08.142090+00:00"},{"alias_kind":"pith_short_12","alias_value":"6XX3AHPIV2ZG","created_at":"2026-07-05T11:09:08.142090+00:00"},{"alias_kind":"pith_short_16","alias_value":"6XX3AHPIV2ZGHTZ2","created_at":"2026-07-05T11:09:08.142090+00:00"},{"alias_kind":"pith_short_8","alias_value":"6XX3AHPI","created_at":"2026-07-05T11:09:08.142090+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6XX3AHPIV2ZGHTZ2PBVPSTPV2X","json":"https://pith.science/pith/6XX3AHPIV2ZGHTZ2PBVPSTPV2X.json","graph_json":"https://pith.science/api/pith-number/6XX3AHPIV2ZGHTZ2PBVPSTPV2X/graph.json","events_json":"https://pith.science/api/pith-number/6XX3AHPIV2ZGHTZ2PBVPSTPV2X/events.json","paper":"https://pith.science/paper/6XX3AHPI"},"agent_actions":{"view_html":"https://pith.science/pith/6XX3AHPIV2ZGHTZ2PBVPSTPV2X","download_json":"https://pith.science/pith/6XX3AHPIV2ZGHTZ2PBVPSTPV2X.json","view_paper":"https://pith.science/paper/6XX3AHPI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.08279&json=true","fetch_graph":"https://pith.science/api/pith-number/6XX3AHPIV2ZGHTZ2PBVPSTPV2X/graph.json","fetch_events":"https://pith.science/api/pith-number/6XX3AHPIV2ZGHTZ2PBVPSTPV2X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6XX3AHPIV2ZGHTZ2PBVPSTPV2X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6XX3AHPIV2ZGHTZ2PBVPSTPV2X/action/storage_attestation","attest_author":"https://pith.science/pith/6XX3AHPIV2ZGHTZ2PBVPSTPV2X/action/author_attestation","sign_citation":"https://pith.science/pith/6XX3AHPIV2ZGHTZ2PBVPSTPV2X/action/citation_signature","submit_replication":"https://pith.science/pith/6XX3AHPIV2ZGHTZ2PBVPSTPV2X/action/replication_record"}},"created_at":"2026-07-05T11:09:08.142090+00:00","updated_at":"2026-07-05T11:09:08.142090+00:00"}