{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:KUZVR6YPOAOWSFOBIGD5WCJ5KZ","short_pith_number":"pith:KUZVR6YP","canonical_record":{"source":{"id":"2004.13278","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2020-04-28T04:08:46Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"2008089efbe0a85ff86339df797eb71dcea52738f351fd76a7f77200760ad393","abstract_canon_sha256":"8c7865588d5e3701a8cc60064d09c72dea45018bc707c448e39b7a71be61acd5"},"schema_version":"1.0"},"canonical_sha256":"553358fb0f701d6915c14187db093d566580b665cd312875f509b8f0695629ea","source":{"kind":"arxiv","id":"2004.13278","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.13278","created_at":"2026-07-05T01:48:09Z"},{"alias_kind":"arxiv_version","alias_value":"2004.13278v3","created_at":"2026-07-05T01:48:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.13278","created_at":"2026-07-05T01:48:09Z"},{"alias_kind":"pith_short_12","alias_value":"KUZVR6YPOAOW","created_at":"2026-07-05T01:48:09Z"},{"alias_kind":"pith_short_16","alias_value":"KUZVR6YPOAOWSFOB","created_at":"2026-07-05T01:48:09Z"},{"alias_kind":"pith_short_8","alias_value":"KUZVR6YP","created_at":"2026-07-05T01:48:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:KUZVR6YPOAOWSFOBIGD5WCJ5KZ","target":"record","payload":{"canonical_record":{"source":{"id":"2004.13278","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2020-04-28T04:08:46Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"2008089efbe0a85ff86339df797eb71dcea52738f351fd76a7f77200760ad393","abstract_canon_sha256":"8c7865588d5e3701a8cc60064d09c72dea45018bc707c448e39b7a71be61acd5"},"schema_version":"1.0"},"canonical_sha256":"553358fb0f701d6915c14187db093d566580b665cd312875f509b8f0695629ea","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:48:09.161858Z","signature_b64":"CI0NZH2z9ymk98iDc1LU6xvuaItZvBv8hCTkFUMzVQ7gQ8pxUjvBN4+VwCZ/M0C9/DbueaynjmsSHgS90aq0DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"553358fb0f701d6915c14187db093d566580b665cd312875f509b8f0695629ea","last_reissued_at":"2026-07-05T01:48:09.161451Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:48:09.161451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.13278","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:48:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CzP2QKlIihJEbNg5Qy3WzZPDw8av7SxAE9KDprLA3LQrsoHW54UYvwbqdLPtlTepf4O9JbOMV4fdj1li2aqTBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T12:56:54.149713Z"},"content_sha256":"968aba67d203d988df81e3c40fa537ac100b56fbd6f4771ca6a918f55c25d9ae","schema_version":"1.0","event_id":"sha256:968aba67d203d988df81e3c40fa537ac100b56fbd6f4771ca6a918f55c25d9ae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:KUZVR6YPOAOWSFOBIGD5WCJ5KZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VD-BERT: A Unified Vision and Dialog Transformer with BERT","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Caiming Xiong, Irwin King, Michael R. Lyu, Shafiq Joty, Steven C.H. Hoi, Yue Wang","submitted_at":"2020-04-28T04:08:46Z","abstract_excerpt":"Visual dialog is a challenging vision-language task, where a dialog agent needs to answer a series of questions through reasoning on the image content and dialog history. Prior work has mostly focused on various attention mechanisms to model such intricate interactions. By contrast, in this work, we propose VD-BERT, a simple yet effective framework of unified vision-dialog Transformer that leverages the pretrained BERT language models for Visual Dialog tasks. The model is unified in that (1) it captures all the interactions between the image and the multi-turn dialog using a single-stream Tran"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.13278","kind":"arxiv","version":3},"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/2004.13278/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":"2026-07-05T01:48:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"npZA7tIb/+3ByWBVmLyFf8f8EkDwjNfXGUxaC83E3KJxpS5LrqrSfFLS627Ui1C4QSUXC6Bk+snVihmZlRY+Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T12:56:54.150091Z"},"content_sha256":"3114f87807b68d00a7127ade6cadc36e72a2f5a86924ddbbfb4ea024afbbf1f5","schema_version":"1.0","event_id":"sha256:3114f87807b68d00a7127ade6cadc36e72a2f5a86924ddbbfb4ea024afbbf1f5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KUZVR6YPOAOWSFOBIGD5WCJ5KZ/bundle.json","state_url":"https://pith.science/pith/KUZVR6YPOAOWSFOBIGD5WCJ5KZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KUZVR6YPOAOWSFOBIGD5WCJ5KZ/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":"2026-07-18T12:56:54Z","links":{"resolver":"https://pith.science/pith/KUZVR6YPOAOWSFOBIGD5WCJ5KZ","bundle":"https://pith.science/pith/KUZVR6YPOAOWSFOBIGD5WCJ5KZ/bundle.json","state":"https://pith.science/pith/KUZVR6YPOAOWSFOBIGD5WCJ5KZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KUZVR6YPOAOWSFOBIGD5WCJ5KZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:KUZVR6YPOAOWSFOBIGD5WCJ5KZ","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":"8c7865588d5e3701a8cc60064d09c72dea45018bc707c448e39b7a71be61acd5","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2020-04-28T04:08:46Z","title_canon_sha256":"2008089efbe0a85ff86339df797eb71dcea52738f351fd76a7f77200760ad393"},"schema_version":"1.0","source":{"id":"2004.13278","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.13278","created_at":"2026-07-05T01:48:09Z"},{"alias_kind":"arxiv_version","alias_value":"2004.13278v3","created_at":"2026-07-05T01:48:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.13278","created_at":"2026-07-05T01:48:09Z"},{"alias_kind":"pith_short_12","alias_value":"KUZVR6YPOAOW","created_at":"2026-07-05T01:48:09Z"},{"alias_kind":"pith_short_16","alias_value":"KUZVR6YPOAOWSFOB","created_at":"2026-07-05T01:48:09Z"},{"alias_kind":"pith_short_8","alias_value":"KUZVR6YP","created_at":"2026-07-05T01:48:09Z"}],"graph_snapshots":[{"event_id":"sha256:3114f87807b68d00a7127ade6cadc36e72a2f5a86924ddbbfb4ea024afbbf1f5","target":"graph","created_at":"2026-07-05T01:48:09Z","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/2004.13278/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual dialog is a challenging vision-language task, where a dialog agent needs to answer a series of questions through reasoning on the image content and dialog history. Prior work has mostly focused on various attention mechanisms to model such intricate interactions. By contrast, in this work, we propose VD-BERT, a simple yet effective framework of unified vision-dialog Transformer that leverages the pretrained BERT language models for Visual Dialog tasks. The model is unified in that (1) it captures all the interactions between the image and the multi-turn dialog using a single-stream Tran","authors_text":"Caiming Xiong, Irwin King, Michael R. Lyu, Shafiq Joty, Steven C.H. Hoi, Yue Wang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2020-04-28T04:08:46Z","title":"VD-BERT: A Unified Vision and Dialog Transformer with BERT"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.13278","kind":"arxiv","version":3},"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":"sha256:968aba67d203d988df81e3c40fa537ac100b56fbd6f4771ca6a918f55c25d9ae","target":"record","created_at":"2026-07-05T01:48:09Z","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":"8c7865588d5e3701a8cc60064d09c72dea45018bc707c448e39b7a71be61acd5","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2020-04-28T04:08:46Z","title_canon_sha256":"2008089efbe0a85ff86339df797eb71dcea52738f351fd76a7f77200760ad393"},"schema_version":"1.0","source":{"id":"2004.13278","kind":"arxiv","version":3}},"canonical_sha256":"553358fb0f701d6915c14187db093d566580b665cd312875f509b8f0695629ea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"553358fb0f701d6915c14187db093d566580b665cd312875f509b8f0695629ea","first_computed_at":"2026-07-05T01:48:09.161451Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:48:09.161451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CI0NZH2z9ymk98iDc1LU6xvuaItZvBv8hCTkFUMzVQ7gQ8pxUjvBN4+VwCZ/M0C9/DbueaynjmsSHgS90aq0DA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:48:09.161858Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.13278","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:968aba67d203d988df81e3c40fa537ac100b56fbd6f4771ca6a918f55c25d9ae","sha256:3114f87807b68d00a7127ade6cadc36e72a2f5a86924ddbbfb4ea024afbbf1f5"],"state_sha256":"f263e5ff1ae5775cf5cd88e5779aaa5fe0f280039abc30337115ffad48045d56"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XCyH7Z0CRn6xUwUyObdFyni2Tas1KmzrZ3LPy5eeZqYmFDLzI9cjJ+sc4kd3qZoxDyFhCZEvndgoZvy9ZAZUDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-18T12:56:54.153163Z","bundle_sha256":"c1aa914f70d76177860e3bb89111de2caf6b06e26fd435ea2ff3f2fe5082c0ad"}}