{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:35ZAZEDUT7VWEDNUNWYC5P53UU","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":"b13e199f52780a05af897bb6d2de52aa8f508399b8cf31792a51899ab36a89c0","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-11T17:23:00Z","title_canon_sha256":"a7e39dfd67e1c7d5cf59c33bc70a1df92aadaa6e6817edeb89615e8abd5050c6"},"schema_version":"1.0","source":{"id":"2305.06988","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.06988","created_at":"2026-07-05T07:18:26Z"},{"alias_kind":"arxiv_version","alias_value":"2305.06988v2","created_at":"2026-07-05T07:18:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.06988","created_at":"2026-07-05T07:18:26Z"},{"alias_kind":"pith_short_12","alias_value":"35ZAZEDUT7VW","created_at":"2026-07-05T07:18:26Z"},{"alias_kind":"pith_short_16","alias_value":"35ZAZEDUT7VWEDNU","created_at":"2026-07-05T07:18:26Z"},{"alias_kind":"pith_short_8","alias_value":"35ZAZEDU","created_at":"2026-07-05T07:18:26Z"}],"graph_snapshots":[{"event_id":"sha256:b41813aa533347601cf4121be15c34f112f7f312f14cef409baab170fe9390ee","target":"graph","created_at":"2026-07-05T07:18:26Z","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/2305.06988/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jaemin Cho, Mohit Bansal, Prateek Yadav, Shoubin Yu","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-11T17:23:00Z","title":"Self-Chained Image-Language Model for Video Localization and Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.06988","kind":"arxiv","version":2},"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":"sha256:33eda93782ba526a6560ff7d922f141e6dac46e8780c9b32a57740e7bf6303ba","target":"record","created_at":"2026-07-05T07:18:26Z","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":"b13e199f52780a05af897bb6d2de52aa8f508399b8cf31792a51899ab36a89c0","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-11T17:23:00Z","title_canon_sha256":"a7e39dfd67e1c7d5cf59c33bc70a1df92aadaa6e6817edeb89615e8abd5050c6"},"schema_version":"1.0","source":{"id":"2305.06988","kind":"arxiv","version":2}},"canonical_sha256":"df720c90749feb620db46db02ebfbba53ea951d84a3a28b830cfac24ed9efad7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df720c90749feb620db46db02ebfbba53ea951d84a3a28b830cfac24ed9efad7","first_computed_at":"2026-07-05T07:18:26.488550Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:18:26.488550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k+6XnUc1ZfzhZgraVgK9R6ACODqY5hntNyTtBzjWrrWuxgN0L21daKOFsXVz8mFESduvCnTz77m5B1lgknWlBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:18:26.489002Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.06988","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:33eda93782ba526a6560ff7d922f141e6dac46e8780c9b32a57740e7bf6303ba","sha256:b41813aa533347601cf4121be15c34f112f7f312f14cef409baab170fe9390ee"],"state_sha256":"482f2c8a066aeeb62e877a9754c3cc5f53db294f8e3250cbf0903e8a34c00a82"}