{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4FYAHYDJBCDQT4QXYABCOQ2JT3","short_pith_number":"pith:4FYAHYDJ","schema_version":"1.0","canonical_sha256":"e17003e069088709f217c0022743499ed8cce6d772b5730337ea75aede0b4728","source":{"kind":"arxiv","id":"2601.18157","version":3},"attestation_state":"computed","paper":{"title":"Agentic Very Long Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aniket Rege, Arka Sadhu, Hyo Jin Kim, Kejie Li, Ramya Korlakai Vinayak, Yong Jae Lee, Yuliang Li, Yuning Chai","submitted_at":"2026-01-26T05:20:47Z","abstract_excerpt":"The advent of always-on personal AI assistants, enabled by all-day wearable devices such as smart glasses, demands a new level of contextual understanding, one that goes beyond short, isolated events to encompass the continuous, longitudinal stream of egocentric video. Achieving this vision requires advances in long-horizon video understanding, where systems must interpret and recall visual and audio information spanning days or even weeks. Existing methods, including large language models and retrieval-augmented generation, are constrained by limited context windows and lack the ability to pe"},"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":"2601.18157","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-01-26T05:20:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cf14ff1f79742748c439632d1a0738412e235553ee9f6a2ed7096007d63d4f19","abstract_canon_sha256":"26f5786d6170ec23e2d0d72f909840f0aee7f2486ab3fb745bf25805d48d6980"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:17:17.328199Z","signature_b64":"9gcw2kXc+sR7HLMmgfymPexaAEwUYrK7rShC/lObPKMwz9JEbYHwD6dHQMPnuI25xWie2Le7GKibX4cchQzDBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e17003e069088709f217c0022743499ed8cce6d772b5730337ea75aede0b4728","last_reissued_at":"2026-07-07T02:17:17.327282Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:17:17.327282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Agentic Very Long Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aniket Rege, Arka Sadhu, Hyo Jin Kim, Kejie Li, Ramya Korlakai Vinayak, Yong Jae Lee, Yuliang Li, Yuning Chai","submitted_at":"2026-01-26T05:20:47Z","abstract_excerpt":"The advent of always-on personal AI assistants, enabled by all-day wearable devices such as smart glasses, demands a new level of contextual understanding, one that goes beyond short, isolated events to encompass the continuous, longitudinal stream of egocentric video. Achieving this vision requires advances in long-horizon video understanding, where systems must interpret and recall visual and audio information spanning days or even weeks. Existing methods, including large language models and retrieval-augmented generation, are constrained by limited context windows and lack the ability to pe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.18157","kind":"arxiv","version":3},"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/2601.18157/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":"2601.18157","created_at":"2026-07-07T02:17:17.327429+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.18157v3","created_at":"2026-07-07T02:17:17.327429+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.18157","created_at":"2026-07-07T02:17:17.327429+00:00"},{"alias_kind":"pith_short_12","alias_value":"4FYAHYDJBCDQ","created_at":"2026-07-07T02:17:17.327429+00:00"},{"alias_kind":"pith_short_16","alias_value":"4FYAHYDJBCDQT4QX","created_at":"2026-07-07T02:17:17.327429+00:00"},{"alias_kind":"pith_short_8","alias_value":"4FYAHYDJ","created_at":"2026-07-07T02:17:17.327429+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2606.13141","citing_title":"Rethinking RAG in Long Videos: What to Retrieve and How to Use It?","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2606.07433","citing_title":"Watch, Remember, Reason: Human-View Video Understanding with MLLMs","ref_index":146,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13228","citing_title":"ReTool-Video: Recursive Tool-Using Video Agents with Meta-Augmented Tool Grounding","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10936","citing_title":"Personal Visual Context Learning in Large Multimodal Models","ref_index":61,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4FYAHYDJBCDQT4QXYABCOQ2JT3","json":"https://pith.science/pith/4FYAHYDJBCDQT4QXYABCOQ2JT3.json","graph_json":"https://pith.science/api/pith-number/4FYAHYDJBCDQT4QXYABCOQ2JT3/graph.json","events_json":"https://pith.science/api/pith-number/4FYAHYDJBCDQT4QXYABCOQ2JT3/events.json","paper":"https://pith.science/paper/4FYAHYDJ"},"agent_actions":{"view_html":"https://pith.science/pith/4FYAHYDJBCDQT4QXYABCOQ2JT3","download_json":"https://pith.science/pith/4FYAHYDJBCDQT4QXYABCOQ2JT3.json","view_paper":"https://pith.science/paper/4FYAHYDJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.18157&json=true","fetch_graph":"https://pith.science/api/pith-number/4FYAHYDJBCDQT4QXYABCOQ2JT3/graph.json","fetch_events":"https://pith.science/api/pith-number/4FYAHYDJBCDQT4QXYABCOQ2JT3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4FYAHYDJBCDQT4QXYABCOQ2JT3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4FYAHYDJBCDQT4QXYABCOQ2JT3/action/storage_attestation","attest_author":"https://pith.science/pith/4FYAHYDJBCDQT4QXYABCOQ2JT3/action/author_attestation","sign_citation":"https://pith.science/pith/4FYAHYDJBCDQT4QXYABCOQ2JT3/action/citation_signature","submit_replication":"https://pith.science/pith/4FYAHYDJBCDQT4QXYABCOQ2JT3/action/replication_record"}},"created_at":"2026-07-07T02:17:17.327429+00:00","updated_at":"2026-07-07T02:17:17.327429+00:00"}