{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6XX3AHPIV2ZGHTZ2PBVPSTPV2X","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ae9a04f6ca7c0a01921c4417dc7553ab174fbd1366cfdc61e07f9019cf7fcdd7","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-12T10:36:55Z","title_canon_sha256":"3a921d7675f17f221eebd47939098682a7d7af5b342e662eeaadf32453c16c8c"},"schema_version":"1.0","source":{"id":"2502.08279","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.08279","created_at":"2026-07-05T11:09:08Z"},{"alias_kind":"arxiv_version","alias_value":"2502.08279v4","created_at":"2026-07-05T11:09:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08279","created_at":"2026-07-05T11:09:08Z"},{"alias_kind":"pith_short_12","alias_value":"6XX3AHPIV2ZG","created_at":"2026-07-05T11:09:08Z"},{"alias_kind":"pith_short_16","alias_value":"6XX3AHPIV2ZGHTZ2","created_at":"2026-07-05T11:09:08Z"},{"alias_kind":"pith_short_8","alias_value":"6XX3AHPI","created_at":"2026-07-05T11:09:08Z"}],"graph_snapshots":[{"event_id":"sha256:efd98ab3b010121514ac718e6f2774021af7ccead0369ba5a4fa944b9a40770f","target":"graph","created_at":"2026-07-05T11:09:08Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2502.08279/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chenxi Whitehouse, Dongqi Liu, Louis Mahon, Mirella Lapata, Rohit Saxena, Vera Demberg, Xi Yu, Yifu Qiu, Zheng Zhao","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-12T10:36:55Z","title":"What Is That Talk About? A Video-to-Text Summarization Dataset for Scientific Presentations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08279","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d369218c2e7e73c95422f851d428e726039f28d1f60364ad4620d275975d8503","target":"record","created_at":"2026-07-05T11:09:08Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ae9a04f6ca7c0a01921c4417dc7553ab174fbd1366cfdc61e07f9019cf7fcdd7","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-12T10:36:55Z","title_canon_sha256":"3a921d7675f17f221eebd47939098682a7d7af5b342e662eeaadf32453c16c8c"},"schema_version":"1.0","source":{"id":"2502.08279","kind":"arxiv","version":4}},"canonical_sha256":"f5efb01de8aeb263cf3a786af94df5d5db2374f4bf2c6e11ca144ae6d9de54a9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5efb01de8aeb263cf3a786af94df5d5db2374f4bf2c6e11ca144ae6d9de54a9","first_computed_at":"2026-07-05T11:09:08.142033Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:08.142033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eolbdEKfCTbmZN/3HzjzdxKK4Qqn8Z03RGfCBQlqo5wrzuniKGbn+ZrQBusetjyp2kr7XcMIQuxyHyuy5gLrDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:08.142500Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.08279","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d369218c2e7e73c95422f851d428e726039f28d1f60364ad4620d275975d8503","sha256:efd98ab3b010121514ac718e6f2774021af7ccead0369ba5a4fa944b9a40770f"],"state_sha256":"1f60c57d287025e3e1a771edbdd0d1928b82f830bf987e9e29d7440d109db3d8"}