{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FY43Z7BYRX25I3QJQDNVSBNKGO","short_pith_number":"pith:FY43Z7BY","schema_version":"1.0","canonical_sha256":"2e39bcfc388df5d46e0980db5905aa339db57ff9d37be45a0a225ee10bc3921e","source":{"kind":"arxiv","id":"2406.02631","version":1},"attestation_state":"computed","paper":{"title":"Contrastive Language Video Time Pre-training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hector A. Valdez, Hengyue Liu, Kyle Min, Subarna Tripathi","submitted_at":"2024-06-04T02:48:59Z","abstract_excerpt":"We introduce LAVITI, a novel approach to learning language, video, and temporal representations in long-form videos via contrastive learning. Different from pre-training on video-text pairs like EgoVLP, LAVITI aims to align language, video, and temporal features by extracting meaningful moments in untrimmed videos. Our model employs a set of learnable moment queries to decode clip-level visual, language, and temporal features. In addition to vision and language alignment, we introduce relative temporal embeddings (TE) to represent timestamps in videos, which enables contrastive learning of tim"},"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":"2406.02631","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-04T02:48:59Z","cross_cats_sorted":[],"title_canon_sha256":"57fee75163f61162e42d29e04bcc2558bdad85ee28c459196289e29f4166d9f1","abstract_canon_sha256":"1ab5f262a2574b830d3cf61a01c1a3f7a7a7c2c9a5212a7d5e45a380dcc6b1f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:28.274153Z","signature_b64":"0tgv/4yAzm2fgjtBKxCAmPdS6g8eyjJ+KIgrf1uDDfIXEQvhSkRX3ziflxzSxymWyR6IOl3C2SF+iBBOaE7IAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e39bcfc388df5d46e0980db5905aa339db57ff9d37be45a0a225ee10bc3921e","last_reissued_at":"2026-07-05T08:27:28.273736Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:28.273736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contrastive Language Video Time Pre-training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hector A. Valdez, Hengyue Liu, Kyle Min, Subarna Tripathi","submitted_at":"2024-06-04T02:48:59Z","abstract_excerpt":"We introduce LAVITI, a novel approach to learning language, video, and temporal representations in long-form videos via contrastive learning. Different from pre-training on video-text pairs like EgoVLP, LAVITI aims to align language, video, and temporal features by extracting meaningful moments in untrimmed videos. Our model employs a set of learnable moment queries to decode clip-level visual, language, and temporal features. In addition to vision and language alignment, we introduce relative temporal embeddings (TE) to represent timestamps in videos, which enables contrastive learning of tim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02631","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/2406.02631/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":"2406.02631","created_at":"2026-07-05T08:27:28.273792+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.02631v1","created_at":"2026-07-05T08:27:28.273792+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02631","created_at":"2026-07-05T08:27:28.273792+00:00"},{"alias_kind":"pith_short_12","alias_value":"FY43Z7BYRX25","created_at":"2026-07-05T08:27:28.273792+00:00"},{"alias_kind":"pith_short_16","alias_value":"FY43Z7BYRX25I3QJ","created_at":"2026-07-05T08:27:28.273792+00:00"},{"alias_kind":"pith_short_8","alias_value":"FY43Z7BY","created_at":"2026-07-05T08:27:28.273792+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.07160","citing_title":"Motion-aware Contrastive Learning for Temporal Panoptic Scene Graph Generation","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FY43Z7BYRX25I3QJQDNVSBNKGO","json":"https://pith.science/pith/FY43Z7BYRX25I3QJQDNVSBNKGO.json","graph_json":"https://pith.science/api/pith-number/FY43Z7BYRX25I3QJQDNVSBNKGO/graph.json","events_json":"https://pith.science/api/pith-number/FY43Z7BYRX25I3QJQDNVSBNKGO/events.json","paper":"https://pith.science/paper/FY43Z7BY"},"agent_actions":{"view_html":"https://pith.science/pith/FY43Z7BYRX25I3QJQDNVSBNKGO","download_json":"https://pith.science/pith/FY43Z7BYRX25I3QJQDNVSBNKGO.json","view_paper":"https://pith.science/paper/FY43Z7BY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.02631&json=true","fetch_graph":"https://pith.science/api/pith-number/FY43Z7BYRX25I3QJQDNVSBNKGO/graph.json","fetch_events":"https://pith.science/api/pith-number/FY43Z7BYRX25I3QJQDNVSBNKGO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FY43Z7BYRX25I3QJQDNVSBNKGO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FY43Z7BYRX25I3QJQDNVSBNKGO/action/storage_attestation","attest_author":"https://pith.science/pith/FY43Z7BYRX25I3QJQDNVSBNKGO/action/author_attestation","sign_citation":"https://pith.science/pith/FY43Z7BYRX25I3QJQDNVSBNKGO/action/citation_signature","submit_replication":"https://pith.science/pith/FY43Z7BYRX25I3QJQDNVSBNKGO/action/replication_record"}},"created_at":"2026-07-05T08:27:28.273792+00:00","updated_at":"2026-07-05T08:27:28.273792+00:00"}