{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:RKDIN7TP5XZ4ROVED5HA3PHO5C","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":"157b99e4c8fd7baab864289c92502666c9ad2ed3d21bda5d6e9f2c1f32e2ec0a","cross_cats_sorted":["cs.CL","cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-04-13T19:18:10Z","title_canon_sha256":"62d6643e8e62c662afbae0a66fb29bb2b65965ce3f646c5893c5c87761719271"},"schema_version":"1.0","source":{"id":"2004.06165","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.06165","created_at":"2026-07-05T01:22:01Z"},{"alias_kind":"arxiv_version","alias_value":"2004.06165v5","created_at":"2026-07-05T01:22:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.06165","created_at":"2026-07-05T01:22:01Z"},{"alias_kind":"pith_short_12","alias_value":"RKDIN7TP5XZ4","created_at":"2026-07-05T01:22:01Z"},{"alias_kind":"pith_short_16","alias_value":"RKDIN7TP5XZ4ROVE","created_at":"2026-07-05T01:22:01Z"},{"alias_kind":"pith_short_8","alias_value":"RKDIN7TP","created_at":"2026-07-05T01:22:01Z"}],"graph_snapshots":[{"event_id":"sha256:3fcbcc223601c294aa8066f34de00c7b1905c9a88c6e98441385477ae5e96b64","target":"graph","created_at":"2026-07-05T01:22:01Z","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/2004.06165/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale pre-training methods of learning cross-modal representations on image-text pairs are becoming popular for vision-language tasks. While existing methods simply concatenate image region features and text features as input to the model to be pre-trained and use self-attention to learn image-text semantic alignments in a brute force manner, in this paper, we propose a new learning method Oscar (Object-Semantics Aligned Pre-training), which uses object tags detected in images as anchor points to significantly ease the learning of alignments. Our method is motivated by the observation th","authors_text":"Chunyuan Li, Furu Wei, Houdong Hu, Jianfeng Gao, Lei Zhang, Li Dong, Lijuan Wang, Pengchuan Zhang, Xiaowei Hu, Xiujun Li, Xi Yin, Yejin Choi","cross_cats":["cs.CL","cs.IR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-04-13T19:18:10Z","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.06165","kind":"arxiv","version":5},"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":"sha256:743c62af7ece050eddd7ce93a050e3a6bf963586f3b2ade0c71b2177bb9bfa2d","target":"record","created_at":"2026-07-05T01:22:01Z","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":"157b99e4c8fd7baab864289c92502666c9ad2ed3d21bda5d6e9f2c1f32e2ec0a","cross_cats_sorted":["cs.CL","cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-04-13T19:18:10Z","title_canon_sha256":"62d6643e8e62c662afbae0a66fb29bb2b65965ce3f646c5893c5c87761719271"},"schema_version":"1.0","source":{"id":"2004.06165","kind":"arxiv","version":5}},"canonical_sha256":"8a8686fe6fedf3c8baa41f4e0dbceee8a8dcecfbe2e0a531213e64fd7a1d4e83","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a8686fe6fedf3c8baa41f4e0dbceee8a8dcecfbe2e0a531213e64fd7a1d4e83","first_computed_at":"2026-07-05T01:22:01.392867Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:22:01.392867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b1gbYoBGoXdHGZn7tep1O2Q6uf/1d0jX2CcvubKWu+agGp2A3YgZjkbfaxevdqhRnbanb4WYQEGakQBLCeuJAw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:22:01.393373Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.06165","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:743c62af7ece050eddd7ce93a050e3a6bf963586f3b2ade0c71b2177bb9bfa2d","sha256:3fcbcc223601c294aa8066f34de00c7b1905c9a88c6e98441385477ae5e96b64"],"state_sha256":"7d6207de863c22215e6fa8a78c34899294d19f0ad78733e91e8e9d37dddcbc78"}