{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:7YCT6GPLDBNFAPUYRWAIQTDHXO","short_pith_number":"pith:7YCT6GPL","schema_version":"1.0","canonical_sha256":"fe053f19eb185a503e988d80884c67bbbad349cdb98b380cf8e59144ac93d3c3","source":{"kind":"arxiv","id":"2212.04501","version":1},"attestation_state":"computed","paper":{"title":"Learning Video Representations from Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ishan Misra, Philipp Kr\\\"ahenb\\\"uhl, Rohit Girdhar, Yue Zhao","submitted_at":"2022-12-08T18:59:59Z","abstract_excerpt":"We introduce LaViLa, a new approach to learning video-language representations by leveraging Large Language Models (LLMs). We repurpose pre-trained LLMs to be conditioned on visual input, and finetune them to create automatic video narrators. Our auto-generated narrations offer a number of advantages, including dense coverage of long videos, better temporal synchronization of the visual information and text, and much higher diversity of text. The video-text embedding learned contrastively with these additional auto-generated narrations outperforms the previous state-of-the-art on multiple firs"},"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":"2212.04501","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-08T18:59:59Z","cross_cats_sorted":[],"title_canon_sha256":"b58d3176bf6cc16350c745a2532095f345e721cb837ef9360429ea5eff9d6df3","abstract_canon_sha256":"a07019e0d71558c444ea819d1e492d6cc8f75cb06bdc2ba3410b94dbe4eff650"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:23:41.594680Z","signature_b64":"hbMMpzlG8WgbjjK9S4UQ3Yanxogz/aNgg0Z4DwDZ6Urhibjf5C+PsW99G0mgdhvu0hutjCxPYkIviw2SJ5BEAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe053f19eb185a503e988d80884c67bbbad349cdb98b380cf8e59144ac93d3c3","last_reissued_at":"2026-07-05T05:23:41.593748Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:23:41.593748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Video Representations from Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ishan Misra, Philipp Kr\\\"ahenb\\\"uhl, Rohit Girdhar, Yue Zhao","submitted_at":"2022-12-08T18:59:59Z","abstract_excerpt":"We introduce LaViLa, a new approach to learning video-language representations by leveraging Large Language Models (LLMs). We repurpose pre-trained LLMs to be conditioned on visual input, and finetune them to create automatic video narrators. Our auto-generated narrations offer a number of advantages, including dense coverage of long videos, better temporal synchronization of the visual information and text, and much higher diversity of text. The video-text embedding learned contrastively with these additional auto-generated narrations outperforms the previous state-of-the-art on multiple firs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.04501","kind":"arxiv","version":1},"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/2212.04501/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":"2212.04501","created_at":"2026-07-05T05:23:41.593811+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.04501v1","created_at":"2026-07-05T05:23:41.593811+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.04501","created_at":"2026-07-05T05:23:41.593811+00:00"},{"alias_kind":"pith_short_12","alias_value":"7YCT6GPLDBNF","created_at":"2026-07-05T05:23:41.593811+00:00"},{"alias_kind":"pith_short_16","alias_value":"7YCT6GPLDBNFAPUY","created_at":"2026-07-05T05:23:41.593811+00:00"},{"alias_kind":"pith_short_8","alias_value":"7YCT6GPL","created_at":"2026-07-05T05:23:41.593811+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29445","citing_title":"Bridging VideoQA and Video-Guided Agentic Tasks via Generalized Keyframe Extraction","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2507.04736","citing_title":"ChipSeek: Optimizing Verilog Generation via EDA-Integrated Reinforcement Learning","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2401.03568","citing_title":"Agent AI: Surveying the Horizons of Multimodal Interaction","ref_index":213,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7YCT6GPLDBNFAPUYRWAIQTDHXO","json":"https://pith.science/pith/7YCT6GPLDBNFAPUYRWAIQTDHXO.json","graph_json":"https://pith.science/api/pith-number/7YCT6GPLDBNFAPUYRWAIQTDHXO/graph.json","events_json":"https://pith.science/api/pith-number/7YCT6GPLDBNFAPUYRWAIQTDHXO/events.json","paper":"https://pith.science/paper/7YCT6GPL"},"agent_actions":{"view_html":"https://pith.science/pith/7YCT6GPLDBNFAPUYRWAIQTDHXO","download_json":"https://pith.science/pith/7YCT6GPLDBNFAPUYRWAIQTDHXO.json","view_paper":"https://pith.science/paper/7YCT6GPL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.04501&json=true","fetch_graph":"https://pith.science/api/pith-number/7YCT6GPLDBNFAPUYRWAIQTDHXO/graph.json","fetch_events":"https://pith.science/api/pith-number/7YCT6GPLDBNFAPUYRWAIQTDHXO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7YCT6GPLDBNFAPUYRWAIQTDHXO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7YCT6GPLDBNFAPUYRWAIQTDHXO/action/storage_attestation","attest_author":"https://pith.science/pith/7YCT6GPLDBNFAPUYRWAIQTDHXO/action/author_attestation","sign_citation":"https://pith.science/pith/7YCT6GPLDBNFAPUYRWAIQTDHXO/action/citation_signature","submit_replication":"https://pith.science/pith/7YCT6GPLDBNFAPUYRWAIQTDHXO/action/replication_record"}},"created_at":"2026-07-05T05:23:41.593811+00:00","updated_at":"2026-07-05T05:23:41.593811+00:00"}