{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:7VTWOYTLGVV3443VG6OTXNPS3U","short_pith_number":"pith:7VTWOYTL","schema_version":"1.0","canonical_sha256":"fd6767626b356bbe7375379d3bb5f2dd2f17b6a6cb013b5791afa6936c41d827","source":{"kind":"arxiv","id":"2210.06031","version":2},"attestation_state":"computed","paper":{"title":"Long-Form Video-Language Pre-Training with Multimodal Temporal Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bei Liu, Hongwei Xue, Huan Yang, Jianlong Fu, Ruihua Song, Yuchong Sun","submitted_at":"2022-10-12T09:08:27Z","abstract_excerpt":"Large-scale video-language pre-training has shown significant improvement in video-language understanding tasks. Previous studies of video-language pretraining mainly focus on short-form videos (i.e., within 30 seconds) and sentences, leaving long-form video-language pre-training rarely explored. Directly learning representation from long-form videos and language may benefit many long-form video-language understanding tasks. However, it is challenging due to the difficulty of modeling long-range relationships and the heavy computational burden caused by more frames. In this paper, we introduce"},"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":"2210.06031","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-12T09:08:27Z","cross_cats_sorted":[],"title_canon_sha256":"c89bd3f45068ec1377c24fb87660e811605ac7df2c76e893c966f0b8ec3aafe5","abstract_canon_sha256":"36f528ec872309f7cd293cf561c0dbe0322cb730c3d4f8ee851bbb2499ee70d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:47:18.240081Z","signature_b64":"MbmLcCovY1JtEgUD+10B/Xyi+GXfwyItVLQ/lNHXWNyOh0p0vB7XLTVLJhepFtY3IvXN3xJwctX4adgtVjHBBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd6767626b356bbe7375379d3bb5f2dd2f17b6a6cb013b5791afa6936c41d827","last_reissued_at":"2026-07-05T05:47:18.239588Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:47:18.239588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Long-Form Video-Language Pre-Training with Multimodal Temporal Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bei Liu, Hongwei Xue, Huan Yang, Jianlong Fu, Ruihua Song, Yuchong Sun","submitted_at":"2022-10-12T09:08:27Z","abstract_excerpt":"Large-scale video-language pre-training has shown significant improvement in video-language understanding tasks. Previous studies of video-language pretraining mainly focus on short-form videos (i.e., within 30 seconds) and sentences, leaving long-form video-language pre-training rarely explored. Directly learning representation from long-form videos and language may benefit many long-form video-language understanding tasks. However, it is challenging due to the difficulty of modeling long-range relationships and the heavy computational burden caused by more frames. In this paper, we introduce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.06031","kind":"arxiv","version":2},"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/2210.06031/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":"2210.06031","created_at":"2026-07-05T05:47:18.239644+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.06031v2","created_at":"2026-07-05T05:47:18.239644+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.06031","created_at":"2026-07-05T05:47:18.239644+00:00"},{"alias_kind":"pith_short_12","alias_value":"7VTWOYTLGVV3","created_at":"2026-07-05T05:47:18.239644+00:00"},{"alias_kind":"pith_short_16","alias_value":"7VTWOYTLGVV3443V","created_at":"2026-07-05T05:47:18.239644+00:00"},{"alias_kind":"pith_short_8","alias_value":"7VTWOYTL","created_at":"2026-07-05T05:47:18.239644+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.20136","citing_title":"IMPACT-CYCLE: A Contract-Based Multi-Agent System for Claim-Level Supervisory Correction of Long-Video Semantic Memory","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11283","citing_title":"Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey","ref_index":186,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7VTWOYTLGVV3443VG6OTXNPS3U","json":"https://pith.science/pith/7VTWOYTLGVV3443VG6OTXNPS3U.json","graph_json":"https://pith.science/api/pith-number/7VTWOYTLGVV3443VG6OTXNPS3U/graph.json","events_json":"https://pith.science/api/pith-number/7VTWOYTLGVV3443VG6OTXNPS3U/events.json","paper":"https://pith.science/paper/7VTWOYTL"},"agent_actions":{"view_html":"https://pith.science/pith/7VTWOYTLGVV3443VG6OTXNPS3U","download_json":"https://pith.science/pith/7VTWOYTLGVV3443VG6OTXNPS3U.json","view_paper":"https://pith.science/paper/7VTWOYTL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.06031&json=true","fetch_graph":"https://pith.science/api/pith-number/7VTWOYTLGVV3443VG6OTXNPS3U/graph.json","fetch_events":"https://pith.science/api/pith-number/7VTWOYTLGVV3443VG6OTXNPS3U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7VTWOYTLGVV3443VG6OTXNPS3U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7VTWOYTLGVV3443VG6OTXNPS3U/action/storage_attestation","attest_author":"https://pith.science/pith/7VTWOYTLGVV3443VG6OTXNPS3U/action/author_attestation","sign_citation":"https://pith.science/pith/7VTWOYTLGVV3443VG6OTXNPS3U/action/citation_signature","submit_replication":"https://pith.science/pith/7VTWOYTLGVV3443VG6OTXNPS3U/action/replication_record"}},"created_at":"2026-07-05T05:47:18.239644+00:00","updated_at":"2026-07-05T05:47:18.239644+00:00"}