{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:55W5SISAB3RVHNCWM4GAQZNDOZ","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":"8620dc739424e42c18a38bf2800b5f4ac79cc46786a7a038c15d87324c74ca9c","cross_cats_sorted":["cs.CL","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-30T04:27:01Z","title_canon_sha256":"c580710621d603f59b81b0900b5385f14953d5480f7712c2e915c5ada5aa9813"},"schema_version":"1.0","source":{"id":"2212.14546","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.14546","created_at":"2026-07-05T05:29:11Z"},{"alias_kind":"arxiv_version","alias_value":"2212.14546v1","created_at":"2026-07-05T05:29:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.14546","created_at":"2026-07-05T05:29:11Z"},{"alias_kind":"pith_short_12","alias_value":"55W5SISAB3RV","created_at":"2026-07-05T05:29:11Z"},{"alias_kind":"pith_short_16","alias_value":"55W5SISAB3RVHNCW","created_at":"2026-07-05T05:29:11Z"},{"alias_kind":"pith_short_8","alias_value":"55W5SISA","created_at":"2026-07-05T05:29:11Z"}],"graph_snapshots":[{"event_id":"sha256:78db7f0b2cca0595c9aef692c2cc74a4decd922e9b4eadbfe8bee43bccdd5234","target":"graph","created_at":"2026-07-05T05:29:11Z","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/2212.14546/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video-language pre-training has advanced the performance of various downstream video-language tasks. However, most previous methods directly inherit or adapt typical image-language pre-training paradigms to video-language pre-training, thus not fully exploiting the unique characteristic of video, i.e., temporal. In this paper, we propose a Hierarchical Temporal-Aware video-language pre-training framework, HiTeA, with two novel pre-training tasks for modeling cross-modal alignment between moments and texts as well as the temporal relations of video-text pairs. Specifically, we propose a cross-m","authors_text":"Fei Huang, Guohai Xu, Haiyang Xu, Ji Zhang, Ming Yan, Qinghao Ye, Qi Qian","cross_cats":["cs.CL","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-30T04:27:01Z","title":"HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.14546","kind":"arxiv","version":1},"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":"sha256:59404684654b25e561fdc85c8e239b01dd648c33d37a70258585867ed13050be","target":"record","created_at":"2026-07-05T05:29:11Z","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":"8620dc739424e42c18a38bf2800b5f4ac79cc46786a7a038c15d87324c74ca9c","cross_cats_sorted":["cs.CL","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-30T04:27:01Z","title_canon_sha256":"c580710621d603f59b81b0900b5385f14953d5480f7712c2e915c5ada5aa9813"},"schema_version":"1.0","source":{"id":"2212.14546","kind":"arxiv","version":1}},"canonical_sha256":"ef6dd922400ee353b456670c0865a376797b6adc5fdfcf936aa8fcbb878e0b6f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef6dd922400ee353b456670c0865a376797b6adc5fdfcf936aa8fcbb878e0b6f","first_computed_at":"2026-07-05T05:29:11.499256Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:29:11.499256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"03k1OiSrewLOrlcXaopU0BLG8vnyfAzSbQk+HnsRWhfabkncpBkeE4RRtXq/7r2JJBUpMhxrMejMp47UoBqcDw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:29:11.499798Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.14546","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:59404684654b25e561fdc85c8e239b01dd648c33d37a70258585867ed13050be","sha256:78db7f0b2cca0595c9aef692c2cc74a4decd922e9b4eadbfe8bee43bccdd5234"],"state_sha256":"8b19bef987eaecfefb6b87b4368db8e93cc301fe64e6115bc72a9b43b5b54b36"}