{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:YCPY2JL23A4OQI25DZMSMF6NTA","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":"64c9d9d067712d4cbc0611ebe92b95c5856bcf192f0ee8f843e217accdc04da7","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-02T13:06:53Z","title_canon_sha256":"6a5c4e1b492505ebc3ec19d52a302ab012dcc45c0ee8988a4dfd23777a8bae00"},"schema_version":"1.0","source":{"id":"2112.01194","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.01194","created_at":"2026-07-05T03:37:48Z"},{"alias_kind":"arxiv_version","alias_value":"2112.01194v2","created_at":"2026-07-05T03:37:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.01194","created_at":"2026-07-05T03:37:48Z"},{"alias_kind":"pith_short_12","alias_value":"YCPY2JL23A4O","created_at":"2026-07-05T03:37:48Z"},{"alias_kind":"pith_short_16","alias_value":"YCPY2JL23A4OQI25","created_at":"2026-07-05T03:37:48Z"},{"alias_kind":"pith_short_8","alias_value":"YCPY2JL2","created_at":"2026-07-05T03:37:48Z"}],"graph_snapshots":[{"event_id":"sha256:1ad53cba5aecd09b0baec799223a44c9906bfc2026fe515a782fe0f4a169a1d6","target":"graph","created_at":"2026-07-05T03:37:48Z","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/2112.01194/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video-Text pre-training aims at learning transferable representations from large-scale video-text pairs via aligning the semantics between visual and textual information. State-of-the-art approaches extract visual features from raw pixels in an end-to-end fashion. However, these methods operate at frame-level directly and thus overlook the spatio-temporal structure of objects in video, which yet has a strong synergy with nouns in textual descriptions. In this work, we propose a simple yet effective module for video-text representation learning, namely RegionLearner, which can take into account","authors_text":"Alex Jinpeng Wang, Guanyu Cai, Jinhui Tang, Mike Zheng Shou, Rui Yan, Xudong Lin, Yixiao Ge","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-02T13:06:53Z","title":"Video-Text Pre-training with Learned Regions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.01194","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:bafb05c86b246dcb290d75c3be8aef675dbf516fe31485c8bb2a5c06be43c528","target":"record","created_at":"2026-07-05T03:37:48Z","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":"64c9d9d067712d4cbc0611ebe92b95c5856bcf192f0ee8f843e217accdc04da7","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-02T13:06:53Z","title_canon_sha256":"6a5c4e1b492505ebc3ec19d52a302ab012dcc45c0ee8988a4dfd23777a8bae00"},"schema_version":"1.0","source":{"id":"2112.01194","kind":"arxiv","version":2}},"canonical_sha256":"c09f8d257ad838e8235d1e592617cd98136c3d5cb86d81324b06795d19c1610c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c09f8d257ad838e8235d1e592617cd98136c3d5cb86d81324b06795d19c1610c","first_computed_at":"2026-07-05T03:37:48.615048Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:37:48.615048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SuS92WrRcPyrO4X8lPIbC8rtzvMqptM5BWzu+CbuHWj0ROKsFcRjnK7Ts2iVEJim9mtXe91mq+lNfTlzwJXcAA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:37:48.615426Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.01194","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bafb05c86b246dcb290d75c3be8aef675dbf516fe31485c8bb2a5c06be43c528","sha256:1ad53cba5aecd09b0baec799223a44c9906bfc2026fe515a782fe0f4a169a1d6"],"state_sha256":"d8282fdfdf5f1961982d94c8642d300195b570112622c0ba47f98d1690a7ff66"}