{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:7VTWOYTLGVV3443VG6OTXNPS3U","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"36f528ec872309f7cd293cf561c0dbe0322cb730c3d4f8ee851bbb2499ee70d9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-12T09:08:27Z","title_canon_sha256":"c89bd3f45068ec1377c24fb87660e811605ac7df2c76e893c966f0b8ec3aafe5"},"schema_version":"1.0","source":{"id":"2210.06031","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.06031","created_at":"2026-07-05T05:47:18Z"},{"alias_kind":"arxiv_version","alias_value":"2210.06031v2","created_at":"2026-07-05T05:47:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.06031","created_at":"2026-07-05T05:47:18Z"},{"alias_kind":"pith_short_12","alias_value":"7VTWOYTLGVV3","created_at":"2026-07-05T05:47:18Z"},{"alias_kind":"pith_short_16","alias_value":"7VTWOYTLGVV3443V","created_at":"2026-07-05T05:47:18Z"},{"alias_kind":"pith_short_8","alias_value":"7VTWOYTL","created_at":"2026-07-05T05:47:18Z"}],"graph_snapshots":[{"event_id":"sha256:1f8cadf450cb919e6f124968901e0bf290f3b8d3f469c68abef96b007edc5e45","target":"graph","created_at":"2026-07-05T05:47:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2210.06031/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bei Liu, Hongwei Xue, Huan Yang, Jianlong Fu, Ruihua Song, Yuchong Sun","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-12T09:08:27Z","title":"Long-Form Video-Language Pre-Training with Multimodal Temporal Contrastive Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.06031","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1d2b97c7f21801f40cd6dc01c43cdb9316b0932f8846437f171d11b85605bda4","target":"record","created_at":"2026-07-05T05:47:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"36f528ec872309f7cd293cf561c0dbe0322cb730c3d4f8ee851bbb2499ee70d9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-12T09:08:27Z","title_canon_sha256":"c89bd3f45068ec1377c24fb87660e811605ac7df2c76e893c966f0b8ec3aafe5"},"schema_version":"1.0","source":{"id":"2210.06031","kind":"arxiv","version":2}},"canonical_sha256":"fd6767626b356bbe7375379d3bb5f2dd2f17b6a6cb013b5791afa6936c41d827","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fd6767626b356bbe7375379d3bb5f2dd2f17b6a6cb013b5791afa6936c41d827","first_computed_at":"2026-07-05T05:47:18.239588Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:47:18.239588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MbmLcCovY1JtEgUD+10B/Xyi+GXfwyItVLQ/lNHXWNyOh0p0vB7XLTVLJhepFtY3IvXN3xJwctX4adgtVjHBBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:47:18.240081Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.06031","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d2b97c7f21801f40cd6dc01c43cdb9316b0932f8846437f171d11b85605bda4","sha256:1f8cadf450cb919e6f124968901e0bf290f3b8d3f469c68abef96b007edc5e45"],"state_sha256":"f5f5ab1016e01f656b4f07eabd35fdf5a6092863cc2b8cdc39678a840f20123b"}