{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:HUA5C7S62DTQW5FC5UFMIORALT","short_pith_number":"pith:HUA5C7S6","canonical_record":{"source":{"id":"2104.03135","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-07T14:07:20Z","cross_cats_sorted":[],"title_canon_sha256":"4096012ca32def869975c10f002ff11ac586054005b5d456e6d716d83f89bdc1","abstract_canon_sha256":"ff837788e5cca911ccc32a23de4a65dfc4ad473e86a7fbdb63441588d4dc5973"},"schema_version":"1.0"},"canonical_sha256":"3d01d17e5ed0e70b74a2ed0ac43a205cc6582b4fe06568667bc38296f8686271","source":{"kind":"arxiv","id":"2104.03135","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.03135","created_at":"2026-07-05T02:30:16Z"},{"alias_kind":"arxiv_version","alias_value":"2104.03135v2","created_at":"2026-07-05T02:30:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.03135","created_at":"2026-07-05T02:30:16Z"},{"alias_kind":"pith_short_12","alias_value":"HUA5C7S62DTQ","created_at":"2026-07-05T02:30:16Z"},{"alias_kind":"pith_short_16","alias_value":"HUA5C7S62DTQW5FC","created_at":"2026-07-05T02:30:16Z"},{"alias_kind":"pith_short_8","alias_value":"HUA5C7S6","created_at":"2026-07-05T02:30:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:HUA5C7S62DTQW5FC5UFMIORALT","target":"record","payload":{"canonical_record":{"source":{"id":"2104.03135","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-07T14:07:20Z","cross_cats_sorted":[],"title_canon_sha256":"4096012ca32def869975c10f002ff11ac586054005b5d456e6d716d83f89bdc1","abstract_canon_sha256":"ff837788e5cca911ccc32a23de4a65dfc4ad473e86a7fbdb63441588d4dc5973"},"schema_version":"1.0"},"canonical_sha256":"3d01d17e5ed0e70b74a2ed0ac43a205cc6582b4fe06568667bc38296f8686271","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:30:16.156950Z","signature_b64":"N5PswqLLXC26OaDhKIznS7nrFlRE7P95dmII0Jeanb22doPu7cUd/98/AUG+Q/m6/Gptk/f3cjGoeApEtQXjBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d01d17e5ed0e70b74a2ed0ac43a205cc6582b4fe06568667bc38296f8686271","last_reissued_at":"2026-07-05T02:30:16.156505Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:30:16.156505Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.03135","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:30:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BGqlbGSNBJ0Bn87Rn6N57sr/Ro4mUAzCVlnQ3j44j628iL9ZHd84U2o9whYSJH+nzyXfNXkn7elze+RyrLW3Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T00:23:10.744574Z"},"content_sha256":"c9bac7060e50227769f5246f1b8c7fb0d01c80f43dfa4f8269382a25726f4d31","schema_version":"1.0","event_id":"sha256:c9bac7060e50227769f5246f1b8c7fb0d01c80f43dfa4f8269382a25726f4d31"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:HUA5C7S62DTQW5FC5UFMIORALT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bei Liu, Dongmei Fu, Jianlong Fu, Yupan Huang, Zhaoyang Zeng, Zhicheng Huang","submitted_at":"2021-04-07T14:07:20Z","abstract_excerpt":"We study joint learning of Convolutional Neural Network (CNN) and Transformer for vision-language pre-training (VLPT) which aims to learn cross-modal alignments from millions of image-text pairs. State-of-the-art approaches extract salient image regions and align regions with words step-by-step. As region-based visual features usually represent parts of an image, it is challenging for existing vision-language models to fully understand the semantics from paired natural languages. In this paper, we propose SOHO to \"See Out of tHe bOx\" that takes a whole image as input, and learns vision-languag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.03135","kind":"arxiv","version":2},"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/2104.03135/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":"2026-07-05T02:30:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dkC+wzOzADaG2oz63t+fC+jxyY6QA/nVHmNI7L7YCVwAKtl9rb+vXW4oU0Shuz6m3tHHANno8bftakJGn6avCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T00:23:10.744963Z"},"content_sha256":"3d9ed24c8a477fd0a24b2808f466fa3cbd2a51ff246d8c070b8de555c9c1a000","schema_version":"1.0","event_id":"sha256:3d9ed24c8a477fd0a24b2808f466fa3cbd2a51ff246d8c070b8de555c9c1a000"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HUA5C7S62DTQW5FC5UFMIORALT/bundle.json","state_url":"https://pith.science/pith/HUA5C7S62DTQW5FC5UFMIORALT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HUA5C7S62DTQW5FC5UFMIORALT/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":"2026-08-15T00:23:10Z","links":{"resolver":"https://pith.science/pith/HUA5C7S62DTQW5FC5UFMIORALT","bundle":"https://pith.science/pith/HUA5C7S62DTQW5FC5UFMIORALT/bundle.json","state":"https://pith.science/pith/HUA5C7S62DTQW5FC5UFMIORALT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HUA5C7S62DTQW5FC5UFMIORALT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:HUA5C7S62DTQW5FC5UFMIORALT","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":"ff837788e5cca911ccc32a23de4a65dfc4ad473e86a7fbdb63441588d4dc5973","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-07T14:07:20Z","title_canon_sha256":"4096012ca32def869975c10f002ff11ac586054005b5d456e6d716d83f89bdc1"},"schema_version":"1.0","source":{"id":"2104.03135","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.03135","created_at":"2026-07-05T02:30:16Z"},{"alias_kind":"arxiv_version","alias_value":"2104.03135v2","created_at":"2026-07-05T02:30:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.03135","created_at":"2026-07-05T02:30:16Z"},{"alias_kind":"pith_short_12","alias_value":"HUA5C7S62DTQ","created_at":"2026-07-05T02:30:16Z"},{"alias_kind":"pith_short_16","alias_value":"HUA5C7S62DTQW5FC","created_at":"2026-07-05T02:30:16Z"},{"alias_kind":"pith_short_8","alias_value":"HUA5C7S6","created_at":"2026-07-05T02:30:16Z"}],"graph_snapshots":[{"event_id":"sha256:3d9ed24c8a477fd0a24b2808f466fa3cbd2a51ff246d8c070b8de555c9c1a000","target":"graph","created_at":"2026-07-05T02:30:16Z","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/2104.03135/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study joint learning of Convolutional Neural Network (CNN) and Transformer for vision-language pre-training (VLPT) which aims to learn cross-modal alignments from millions of image-text pairs. State-of-the-art approaches extract salient image regions and align regions with words step-by-step. As region-based visual features usually represent parts of an image, it is challenging for existing vision-language models to fully understand the semantics from paired natural languages. In this paper, we propose SOHO to \"See Out of tHe bOx\" that takes a whole image as input, and learns vision-languag","authors_text":"Bei Liu, Dongmei Fu, Jianlong Fu, Yupan Huang, Zhaoyang Zeng, Zhicheng Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-07T14:07:20Z","title":"Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.03135","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:c9bac7060e50227769f5246f1b8c7fb0d01c80f43dfa4f8269382a25726f4d31","target":"record","created_at":"2026-07-05T02:30:16Z","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":"ff837788e5cca911ccc32a23de4a65dfc4ad473e86a7fbdb63441588d4dc5973","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-07T14:07:20Z","title_canon_sha256":"4096012ca32def869975c10f002ff11ac586054005b5d456e6d716d83f89bdc1"},"schema_version":"1.0","source":{"id":"2104.03135","kind":"arxiv","version":2}},"canonical_sha256":"3d01d17e5ed0e70b74a2ed0ac43a205cc6582b4fe06568667bc38296f8686271","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3d01d17e5ed0e70b74a2ed0ac43a205cc6582b4fe06568667bc38296f8686271","first_computed_at":"2026-07-05T02:30:16.156505Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:30:16.156505Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N5PswqLLXC26OaDhKIznS7nrFlRE7P95dmII0Jeanb22doPu7cUd/98/AUG+Q/m6/Gptk/f3cjGoeApEtQXjBA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:30:16.156950Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.03135","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c9bac7060e50227769f5246f1b8c7fb0d01c80f43dfa4f8269382a25726f4d31","sha256:3d9ed24c8a477fd0a24b2808f466fa3cbd2a51ff246d8c070b8de555c9c1a000"],"state_sha256":"112c18d2e76665d5d141b1a1baa5a0e49f86f5a4201e6dbfde9680d00d6c0181"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"11aBGmgrOJ2x1FmyotSp1AeRejE/DmhRpAVhHfQ/Ae7Gf7g1q2I8ZjgZnVCzNkgMCThELQuBvDXFdQt/eB/GDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T00:23:10.748287Z","bundle_sha256":"200d8f3a0a4d4d3b4ac3e0c261446c45da22fd60e1130e417ddb58cd51838d23"}}