{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:T6WK32VVE22GYDQEFBUF462WSL","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":"72e2938ca40aab4f3a09b86bfc18b36fd67c3a61fd532197d86e3b354abbb852","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-01T06:42:16Z","title_canon_sha256":"368b99d92363d552f52b3b944870d1799c118f5caf4f7d3816fd5d77775fe8e5"},"schema_version":"1.0","source":{"id":"2104.00285","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.00285","created_at":"2026-07-05T02:31:23Z"},{"alias_kind":"arxiv_version","alias_value":"2104.00285v2","created_at":"2026-07-05T02:31:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.00285","created_at":"2026-07-05T02:31:23Z"},{"alias_kind":"pith_short_12","alias_value":"T6WK32VVE22G","created_at":"2026-07-05T02:31:23Z"},{"alias_kind":"pith_short_16","alias_value":"T6WK32VVE22GYDQE","created_at":"2026-07-05T02:31:23Z"},{"alias_kind":"pith_short_8","alias_value":"T6WK32VV","created_at":"2026-07-05T02:31:23Z"}],"graph_snapshots":[{"event_id":"sha256:f66090f62a4a9fe70d170bb735a60f0dbefa0ac2df85f86e1681a154ec7f5dff","target":"graph","created_at":"2026-07-05T02:31:23Z","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/2104.00285/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work concerns video-language pre-training and representation learning. In this now ubiquitous training scheme, a model first performs pre-training on paired videos and text (e.g., video clips and accompanied subtitles) from a large uncurated source corpus, before transferring to specific downstream tasks. This two-stage training process inevitably raises questions about the generalization ability of the pre-trained model, which is particularly pronounced when a salient domain gap exists between source and target data (e.g., instructional cooking videos vs. movies). In this paper, we first","authors_text":"Jingjing Liu, Lei Zhang, Luowei Zhou, Yu Cheng, Zhe Gan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-01T06:42:16Z","title":"CUPID: Adaptive Curation of Pre-training Data for Video-and-Language Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.00285","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":"sha256:594c17ab08621a72d1908291632f42971c8cbe1e3e3a9c1329e063e4fc141399","target":"record","created_at":"2026-07-05T02:31:23Z","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":"72e2938ca40aab4f3a09b86bfc18b36fd67c3a61fd532197d86e3b354abbb852","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-01T06:42:16Z","title_canon_sha256":"368b99d92363d552f52b3b944870d1799c118f5caf4f7d3816fd5d77775fe8e5"},"schema_version":"1.0","source":{"id":"2104.00285","kind":"arxiv","version":2}},"canonical_sha256":"9facadeab526b46c0e0428685e7b5692d6d80afa7627bd69602da48e3ab39654","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9facadeab526b46c0e0428685e7b5692d6d80afa7627bd69602da48e3ab39654","first_computed_at":"2026-07-05T02:31:23.569878Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:31:23.569878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MBgWAax8ZHaxX4LrjimitYsvzYmEfNTuToZpx1JCwfaezA7dUXqd+wVqgzbQMro/AGXfgKY/X9mtAzN0r5RYAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:31:23.570346Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.00285","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:594c17ab08621a72d1908291632f42971c8cbe1e3e3a9c1329e063e4fc141399","sha256:f66090f62a4a9fe70d170bb735a60f0dbefa0ac2df85f86e1681a154ec7f5dff"],"state_sha256":"465a8d53f4e11cb357aad3906b886f05922ef2cefcd1c06d4370ef68c7977d1d"}