{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:35ZAZEDUT7VWEDNUNWYC5P53UU","short_pith_number":"pith:35ZAZEDU","schema_version":"1.0","canonical_sha256":"df720c90749feb620db46db02ebfbba53ea951d84a3a28b830cfac24ed9efad7","source":{"kind":"arxiv","id":"2305.06988","version":2},"attestation_state":"computed","paper":{"title":"Self-Chained Image-Language Model for Video Localization and Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jaemin Cho, Mohit Bansal, Prateek Yadav, Shoubin Yu","submitted_at":"2023-05-11T17:23:00Z","abstract_excerpt":"Recent studies have shown promising results on utilizing large pre-trained image-language models for video question answering. While these image-language models can efficiently bootstrap the representation learning of video-language models, they typically concatenate uniformly sampled video frames as visual inputs without explicit language-aware, temporal modeling. When only a portion of a video input is relevant to the language query, such uniform frame sampling can often lead to missing important visual cues. Although humans often find a video moment to focus on and rewind the moment to answ"},"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":"2305.06988","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-11T17:23:00Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"a7e39dfd67e1c7d5cf59c33bc70a1df92aadaa6e6817edeb89615e8abd5050c6","abstract_canon_sha256":"b13e199f52780a05af897bb6d2de52aa8f508399b8cf31792a51899ab36a89c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:18:26.489002Z","signature_b64":"k+6XnUc1ZfzhZgraVgK9R6ACODqY5hntNyTtBzjWrrWuxgN0L21daKOFsXVz8mFESduvCnTz77m5B1lgknWlBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df720c90749feb620db46db02ebfbba53ea951d84a3a28b830cfac24ed9efad7","last_reissued_at":"2026-07-05T07:18:26.488550Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:18:26.488550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Chained Image-Language Model for Video Localization and Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jaemin Cho, Mohit Bansal, Prateek Yadav, Shoubin Yu","submitted_at":"2023-05-11T17:23:00Z","abstract_excerpt":"Recent studies have shown promising results on utilizing large pre-trained image-language models for video question answering. While these image-language models can efficiently bootstrap the representation learning of video-language models, they typically concatenate uniformly sampled video frames as visual inputs without explicit language-aware, temporal modeling. When only a portion of a video input is relevant to the language query, such uniform frame sampling can often lead to missing important visual cues. Although humans often find a video moment to focus on and rewind the moment to answ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.06988","kind":"arxiv","version":2},"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/2305.06988/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":"2305.06988","created_at":"2026-07-05T07:18:26.488604+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.06988v2","created_at":"2026-07-05T07:18:26.488604+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.06988","created_at":"2026-07-05T07:18:26.488604+00:00"},{"alias_kind":"pith_short_12","alias_value":"35ZAZEDUT7VW","created_at":"2026-07-05T07:18:26.488604+00:00"},{"alias_kind":"pith_short_16","alias_value":"35ZAZEDUT7VWEDNU","created_at":"2026-07-05T07:18:26.488604+00:00"},{"alias_kind":"pith_short_8","alias_value":"35ZAZEDU","created_at":"2026-07-05T07:18:26.488604+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27920","citing_title":"Rethinking Video-Language Model from the Language Input Perspective","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2312.11805","citing_title":"Gemini: A Family of Highly Capable Multimodal Models","ref_index":128,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/35ZAZEDUT7VWEDNUNWYC5P53UU","json":"https://pith.science/pith/35ZAZEDUT7VWEDNUNWYC5P53UU.json","graph_json":"https://pith.science/api/pith-number/35ZAZEDUT7VWEDNUNWYC5P53UU/graph.json","events_json":"https://pith.science/api/pith-number/35ZAZEDUT7VWEDNUNWYC5P53UU/events.json","paper":"https://pith.science/paper/35ZAZEDU"},"agent_actions":{"view_html":"https://pith.science/pith/35ZAZEDUT7VWEDNUNWYC5P53UU","download_json":"https://pith.science/pith/35ZAZEDUT7VWEDNUNWYC5P53UU.json","view_paper":"https://pith.science/paper/35ZAZEDU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.06988&json=true","fetch_graph":"https://pith.science/api/pith-number/35ZAZEDUT7VWEDNUNWYC5P53UU/graph.json","fetch_events":"https://pith.science/api/pith-number/35ZAZEDUT7VWEDNUNWYC5P53UU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/35ZAZEDUT7VWEDNUNWYC5P53UU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/35ZAZEDUT7VWEDNUNWYC5P53UU/action/storage_attestation","attest_author":"https://pith.science/pith/35ZAZEDUT7VWEDNUNWYC5P53UU/action/author_attestation","sign_citation":"https://pith.science/pith/35ZAZEDUT7VWEDNUNWYC5P53UU/action/citation_signature","submit_replication":"https://pith.science/pith/35ZAZEDUT7VWEDNUNWYC5P53UU/action/replication_record"}},"created_at":"2026-07-05T07:18:26.488604+00:00","updated_at":"2026-07-05T07:18:26.488604+00:00"}