{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:NN7FI44JJD55FNBQYX625GNU63","short_pith_number":"pith:NN7FI44J","canonical_record":{"source":{"id":"2305.13697","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T05:11:34Z","cross_cats_sorted":[],"title_canon_sha256":"2dd16c6027283dd62a35083b506d8e2fe4a361cdc75e616c4054e7839ec3e900","abstract_canon_sha256":"8d448523530773be8870d768cc0ec6ea1bee7f213fae3a2962c1b5f2740f02f2"},"schema_version":"1.0"},"canonical_sha256":"6b7e54738948fbd2b430c5fdae99b4f6e1a0d3f5fdb3e69cdd7a8e15d2c966e3","source":{"kind":"arxiv","id":"2305.13697","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13697","created_at":"2026-07-05T06:12:56Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13697v1","created_at":"2026-07-05T06:12:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13697","created_at":"2026-07-05T06:12:56Z"},{"alias_kind":"pith_short_12","alias_value":"NN7FI44JJD55","created_at":"2026-07-05T06:12:56Z"},{"alias_kind":"pith_short_16","alias_value":"NN7FI44JJD55FNBQ","created_at":"2026-07-05T06:12:56Z"},{"alias_kind":"pith_short_8","alias_value":"NN7FI44J","created_at":"2026-07-05T06:12:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:NN7FI44JJD55FNBQYX625GNU63","target":"record","payload":{"canonical_record":{"source":{"id":"2305.13697","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T05:11:34Z","cross_cats_sorted":[],"title_canon_sha256":"2dd16c6027283dd62a35083b506d8e2fe4a361cdc75e616c4054e7839ec3e900","abstract_canon_sha256":"8d448523530773be8870d768cc0ec6ea1bee7f213fae3a2962c1b5f2740f02f2"},"schema_version":"1.0"},"canonical_sha256":"6b7e54738948fbd2b430c5fdae99b4f6e1a0d3f5fdb3e69cdd7a8e15d2c966e3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:56.228438Z","signature_b64":"q8AlJfzSczqQ19fFzHx1YvGQFUDUq768Y0KmqMsZqYIoseWZ5YxQZ9iylh6NbxAk5ZeaseIuWNpqtDEGSm5EAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b7e54738948fbd2b430c5fdae99b4f6e1a0d3f5fdb3e69cdd7a8e15d2c966e3","last_reissued_at":"2026-07-05T06:12:56.228092Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:56.228092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.13697","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:12:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"At8AXhg6wlvfyzS48EQoD/ZKUPRMbiU0+Uja9vdeGsjvKmDHHjFHD//6jPgxQSL8XXEYVRkxXC1MqmkSA0dfCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T00:35:14.433634Z"},"content_sha256":"8eea3c4637d90fa4b4d482b25d15131be08c865b2a270f500b8067a095d3beee","schema_version":"1.0","event_id":"sha256:8eea3c4637d90fa4b4d482b25d15131be08c865b2a270f500b8067a095d3beee"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:NN7FI44JJD55FNBQYX625GNU63","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"UNIMO-3: Multi-granularity Interaction for Vision-Language Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bing Qin, Can Gao, Hao L\\'iu, Hao Yang, Xinyan Xiao, Yanyan Zhao","submitted_at":"2023-05-23T05:11:34Z","abstract_excerpt":"Vision-and-language (VL) pre-training, which aims to learn a general representation of image-text pairs that can be transferred to various vision-and-language tasks. Compared with modeling uni-modal data, the main challenge of the VL model is: how to learn the cross-modal interaction from multimodal data, especially the fine-grained interaction. Existing works have shown that fully transformer-based models that adopt attention mechanisms to learn in-layer cross-model interaction can demonstrate impressive performance on various cross-modal downstream tasks. However, they ignored that the seman"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13697","kind":"arxiv","version":1},"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/2305.13697/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":"2026-07-05T06:12:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uN97BmJ6mrOWLwDnlWxPyE2EwLs9L4+Jn+N2AlepvaqeA5NgF1Ujtk+hll6iibfsG+ejfEZ4dmO2TEClMeenDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T00:35:14.435806Z"},"content_sha256":"c33e34f8640b54d1afbb2afd6de45b65e3c744f7ef0ae535692b3ecb3aac07dc","schema_version":"1.0","event_id":"sha256:c33e34f8640b54d1afbb2afd6de45b65e3c744f7ef0ae535692b3ecb3aac07dc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NN7FI44JJD55FNBQYX625GNU63/bundle.json","state_url":"https://pith.science/pith/NN7FI44JJD55FNBQYX625GNU63/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NN7FI44JJD55FNBQYX625GNU63/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":"2026-08-05T00:35:14Z","links":{"resolver":"https://pith.science/pith/NN7FI44JJD55FNBQYX625GNU63","bundle":"https://pith.science/pith/NN7FI44JJD55FNBQYX625GNU63/bundle.json","state":"https://pith.science/pith/NN7FI44JJD55FNBQYX625GNU63/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NN7FI44JJD55FNBQYX625GNU63/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NN7FI44JJD55FNBQYX625GNU63","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":"8d448523530773be8870d768cc0ec6ea1bee7f213fae3a2962c1b5f2740f02f2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T05:11:34Z","title_canon_sha256":"2dd16c6027283dd62a35083b506d8e2fe4a361cdc75e616c4054e7839ec3e900"},"schema_version":"1.0","source":{"id":"2305.13697","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13697","created_at":"2026-07-05T06:12:56Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13697v1","created_at":"2026-07-05T06:12:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13697","created_at":"2026-07-05T06:12:56Z"},{"alias_kind":"pith_short_12","alias_value":"NN7FI44JJD55","created_at":"2026-07-05T06:12:56Z"},{"alias_kind":"pith_short_16","alias_value":"NN7FI44JJD55FNBQ","created_at":"2026-07-05T06:12:56Z"},{"alias_kind":"pith_short_8","alias_value":"NN7FI44J","created_at":"2026-07-05T06:12:56Z"}],"graph_snapshots":[{"event_id":"sha256:c33e34f8640b54d1afbb2afd6de45b65e3c744f7ef0ae535692b3ecb3aac07dc","target":"graph","created_at":"2026-07-05T06:12:56Z","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/2305.13697/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-and-language (VL) pre-training, which aims to learn a general representation of image-text pairs that can be transferred to various vision-and-language tasks. Compared with modeling uni-modal data, the main challenge of the VL model is: how to learn the cross-modal interaction from multimodal data, especially the fine-grained interaction. Existing works have shown that fully transformer-based models that adopt attention mechanisms to learn in-layer cross-model interaction can demonstrate impressive performance on various cross-modal downstream tasks. However, they ignored that the seman","authors_text":"Bing Qin, Can Gao, Hao L\\'iu, Hao Yang, Xinyan Xiao, Yanyan Zhao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T05:11:34Z","title":"UNIMO-3: Multi-granularity Interaction for Vision-Language Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13697","kind":"arxiv","version":1},"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":"sha256:8eea3c4637d90fa4b4d482b25d15131be08c865b2a270f500b8067a095d3beee","target":"record","created_at":"2026-07-05T06:12:56Z","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":"8d448523530773be8870d768cc0ec6ea1bee7f213fae3a2962c1b5f2740f02f2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T05:11:34Z","title_canon_sha256":"2dd16c6027283dd62a35083b506d8e2fe4a361cdc75e616c4054e7839ec3e900"},"schema_version":"1.0","source":{"id":"2305.13697","kind":"arxiv","version":1}},"canonical_sha256":"6b7e54738948fbd2b430c5fdae99b4f6e1a0d3f5fdb3e69cdd7a8e15d2c966e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b7e54738948fbd2b430c5fdae99b4f6e1a0d3f5fdb3e69cdd7a8e15d2c966e3","first_computed_at":"2026-07-05T06:12:56.228092Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:12:56.228092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q8AlJfzSczqQ19fFzHx1YvGQFUDUq768Y0KmqMsZqYIoseWZ5YxQZ9iylh6NbxAk5ZeaseIuWNpqtDEGSm5EAA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:12:56.228438Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.13697","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8eea3c4637d90fa4b4d482b25d15131be08c865b2a270f500b8067a095d3beee","sha256:c33e34f8640b54d1afbb2afd6de45b65e3c744f7ef0ae535692b3ecb3aac07dc"],"state_sha256":"75cd3c1669281469006a5632e7ac8f46232b0f98edb93468cdfd34984bf9878c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"crZZ1XxWn0hX2UxHQIu7J7fOdvRaycc6YMq7coTXOC7MeUmzd+HRWVjWpP7CT+X1cAFe7IbuQd/uHI9TdBlbCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T00:35:14.498007Z","bundle_sha256":"e3cc303b4407f9274b79e749d9247726dbf7739c5b3983950a3033efabc86260"}}