{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:RKDIN7TP5XZ4ROVED5HA3PHO5C","short_pith_number":"pith:RKDIN7TP","canonical_record":{"source":{"id":"2004.06165","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-04-13T19:18:10Z","cross_cats_sorted":["cs.CL","cs.IR","cs.LG"],"title_canon_sha256":"62d6643e8e62c662afbae0a66fb29bb2b65965ce3f646c5893c5c87761719271","abstract_canon_sha256":"157b99e4c8fd7baab864289c92502666c9ad2ed3d21bda5d6e9f2c1f32e2ec0a"},"schema_version":"1.0"},"canonical_sha256":"8a8686fe6fedf3c8baa41f4e0dbceee8a8dcecfbe2e0a531213e64fd7a1d4e83","source":{"kind":"arxiv","id":"2004.06165","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:RKDIN7TP5XZ4ROVED5HA3PHO5C","target":"record","payload":{"canonical_record":{"source":{"id":"2004.06165","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-04-13T19:18:10Z","cross_cats_sorted":["cs.CL","cs.IR","cs.LG"],"title_canon_sha256":"62d6643e8e62c662afbae0a66fb29bb2b65965ce3f646c5893c5c87761719271","abstract_canon_sha256":"157b99e4c8fd7baab864289c92502666c9ad2ed3d21bda5d6e9f2c1f32e2ec0a"},"schema_version":"1.0"},"canonical_sha256":"8a8686fe6fedf3c8baa41f4e0dbceee8a8dcecfbe2e0a531213e64fd7a1d4e83","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:22:01.393373Z","signature_b64":"b1gbYoBGoXdHGZn7tep1O2Q6uf/1d0jX2CcvubKWu+agGp2A3YgZjkbfaxevdqhRnbanb4WYQEGakQBLCeuJAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a8686fe6fedf3c8baa41f4e0dbceee8a8dcecfbe2e0a531213e64fd7a1d4e83","last_reissued_at":"2026-07-05T01:22:01.392867Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:22:01.392867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.06165","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:22:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QDZ9bM2zyZJkvgmSONdgO4xdz/5I7LnztpYSb0qzQx4s1b6GEK+l/vK/E4cIvudaJcXmaAb4xjxTyE0GLyPvBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T16:25:33.602353Z"},"content_sha256":"743c62af7ece050eddd7ce93a050e3a6bf963586f3b2ade0c71b2177bb9bfa2d","schema_version":"1.0","event_id":"sha256:743c62af7ece050eddd7ce93a050e3a6bf963586f3b2ade0c71b2177bb9bfa2d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:RKDIN7TP5XZ4ROVED5HA3PHO5C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IR","cs.LG"],"primary_cat":"cs.CV","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","submitted_at":"2020-04-13T19:18:10Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.06165","kind":"arxiv","version":5},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2004.06165/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:22:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vkfPzNDmAnMLUFVD8+RYulhr4ipebEGfOkX5pjW8Pg6MGQevcmtsUlEZsJOnYaYTgDEvd4N3bVvaU/XL3PqADQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T16:25:33.602893Z"},"content_sha256":"3fcbcc223601c294aa8066f34de00c7b1905c9a88c6e98441385477ae5e96b64","schema_version":"1.0","event_id":"sha256:3fcbcc223601c294aa8066f34de00c7b1905c9a88c6e98441385477ae5e96b64"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RKDIN7TP5XZ4ROVED5HA3PHO5C/bundle.json","state_url":"https://pith.science/pith/RKDIN7TP5XZ4ROVED5HA3PHO5C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RKDIN7TP5XZ4ROVED5HA3PHO5C/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T16:25:33Z","links":{"resolver":"https://pith.science/pith/RKDIN7TP5XZ4ROVED5HA3PHO5C","bundle":"https://pith.science/pith/RKDIN7TP5XZ4ROVED5HA3PHO5C/bundle.json","state":"https://pith.science/pith/RKDIN7TP5XZ4ROVED5HA3PHO5C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RKDIN7TP5XZ4ROVED5HA3PHO5C/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N8tnFNR5W23E+b2s886r29kNyLSRDlAOpzvr9JN7n4DYEqMargAXObjUAH7gnLC4t4Tq84xXXQZDySB+G5YnBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T16:25:33.608318Z","bundle_sha256":"bec6e947b46c53df17fc0a3b089d554603ed79931f54942c7d5b7fcef59abbc1"}}