{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:L2QBZSOICXYGFML3OL76UIFEDR","short_pith_number":"pith:L2QBZSOI","schema_version":"1.0","canonical_sha256":"5ea01cc9c815f062b17b72ffea20a41c558c294e917de5264c0482248358fd2d","source":{"kind":"arxiv","id":"2312.05269","version":3},"attestation_state":"computed","paper":{"title":"LifelongMemory: Leveraging LLMs for Answering Queries in Long-form Egocentric Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Mengye Ren, Yanlai Yang, Ying Wang","submitted_at":"2023-12-07T19:19:25Z","abstract_excerpt":"In this paper we introduce LifelongMemory, a new framework for accessing long-form egocentric videographic memory through natural language question answering and retrieval. LifelongMemory generates concise video activity descriptions of the camera wearer and leverages the zero-shot capabilities of pretrained large language models to perform reasoning over long-form video context. Furthermore, LifelongMemory uses a confidence and explanation module to produce confident, high-quality, and interpretable answers. Our approach achieves state-of-the-art performance on the EgoSchema benchmark for que"},"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":"2312.05269","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-07T19:19:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"41ad74f4784ba96a7a84f2f26b6d237b3288f253658b0edf0d6dbbe1a738e453","abstract_canon_sha256":"b4ce662eb59f919788b138961267fe9016f6867a1021e00046d5cf3ab238c82f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:29.231909Z","signature_b64":"GRTlf3Y1V82jrBTtfwfQ/h6kj2OTTXk/fo4rXojhLQVprwcLljLg4bWMODWLTE0gaTWDaK/Fh95wuao5hqtqAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ea01cc9c815f062b17b72ffea20a41c558c294e917de5264c0482248358fd2d","last_reissued_at":"2026-07-05T09:31:29.229852Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:29.229852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LifelongMemory: Leveraging LLMs for Answering Queries in Long-form Egocentric Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Mengye Ren, Yanlai Yang, Ying Wang","submitted_at":"2023-12-07T19:19:25Z","abstract_excerpt":"In this paper we introduce LifelongMemory, a new framework for accessing long-form egocentric videographic memory through natural language question answering and retrieval. LifelongMemory generates concise video activity descriptions of the camera wearer and leverages the zero-shot capabilities of pretrained large language models to perform reasoning over long-form video context. Furthermore, LifelongMemory uses a confidence and explanation module to produce confident, high-quality, and interpretable answers. Our approach achieves state-of-the-art performance on the EgoSchema benchmark for que"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.05269","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/2312.05269/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":"2312.05269","created_at":"2026-07-05T09:31:29.231324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.05269v3","created_at":"2026-07-05T09:31:29.231324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.05269","created_at":"2026-07-05T09:31:29.231324+00:00"},{"alias_kind":"pith_short_12","alias_value":"L2QBZSOICXYG","created_at":"2026-07-05T09:31:29.231324+00:00"},{"alias_kind":"pith_short_16","alias_value":"L2QBZSOICXYGFML3","created_at":"2026-07-05T09:31:29.231324+00:00"},{"alias_kind":"pith_short_8","alias_value":"L2QBZSOI","created_at":"2026-07-05T09:31:29.231324+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22804","citing_title":"CoVStream: Edge-Cloud Collaboration for Understanding of Long Video Streams","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21734","citing_title":"HPP: Hierarchical Programmatic Probing for Long Video Understanding by Decoupling Perception and Reasoning","ref_index":92,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19341","citing_title":"Native Active Perception as Reasoning for Omni-Modal Understanding","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05917","citing_title":"MemoryCard: Topic-Aware Multi-Modal Clue Compression for Long-Video Question Answering","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03920","citing_title":"Benchmarking Visual State Tracking in Multimodal Video Understanding","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24456","citing_title":"EgoProx: Evaluating MLLMs on Egocentric 3D Proximity Reasoning Across a Cognitive Hierarchy","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17262","citing_title":"EgoIntrospect: An Egocentric Dataset and Benchmark for User-Centric Internal State Reasoning","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2509.24943","citing_title":"Perceive, Verify and Understand Long Video: Multi-Granular Perception and Active Verification via Interactive Agents","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2601.15724","citing_title":"VideoThinker: Building Agentic VideoLLMs with LLM-Guided Tool Reasoning","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2602.22455","citing_title":"Exploring Multimodal LMMs for Online Episodic Memory Question Answering on the Edge","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10936","citing_title":"Personal Visual Context Learning in Large Multimodal Models","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04227","citing_title":"Pro$^2$Assist: Continuous Step-aware Proactive Assistance with Multi-modal Egocentric Perception for Long-horizon Procedural Tasks","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21444","citing_title":"HiCrew: Hierarchical Reasoning for Long-Form Video Understanding via Question-Aware Multi-Agent Collaboration","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L2QBZSOICXYGFML3OL76UIFEDR","json":"https://pith.science/pith/L2QBZSOICXYGFML3OL76UIFEDR.json","graph_json":"https://pith.science/api/pith-number/L2QBZSOICXYGFML3OL76UIFEDR/graph.json","events_json":"https://pith.science/api/pith-number/L2QBZSOICXYGFML3OL76UIFEDR/events.json","paper":"https://pith.science/paper/L2QBZSOI"},"agent_actions":{"view_html":"https://pith.science/pith/L2QBZSOICXYGFML3OL76UIFEDR","download_json":"https://pith.science/pith/L2QBZSOICXYGFML3OL76UIFEDR.json","view_paper":"https://pith.science/paper/L2QBZSOI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.05269&json=true","fetch_graph":"https://pith.science/api/pith-number/L2QBZSOICXYGFML3OL76UIFEDR/graph.json","fetch_events":"https://pith.science/api/pith-number/L2QBZSOICXYGFML3OL76UIFEDR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L2QBZSOICXYGFML3OL76UIFEDR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L2QBZSOICXYGFML3OL76UIFEDR/action/storage_attestation","attest_author":"https://pith.science/pith/L2QBZSOICXYGFML3OL76UIFEDR/action/author_attestation","sign_citation":"https://pith.science/pith/L2QBZSOICXYGFML3OL76UIFEDR/action/citation_signature","submit_replication":"https://pith.science/pith/L2QBZSOICXYGFML3OL76UIFEDR/action/replication_record"}},"created_at":"2026-07-05T09:31:29.231324+00:00","updated_at":"2026-07-05T09:31:29.231324+00:00"}