{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:36JYG46PPUSVSESFG4LAZLQ4II","short_pith_number":"pith:36JYG46P","canonical_record":{"source":{"id":"1908.05054","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-14T10:03:12Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"12f5630026bd217c46e1eb1cae6cd3c1b584a5356a46ae87a4b764d40a604074","abstract_canon_sha256":"a8966c950167690f01897724030ba49599779f3c860281a1ae7ff4db5a2c857e"},"schema_version":"1.0"},"canonical_sha256":"df938373cf7d2559124537160cae1c4209408aac125702db136dbf5d53c50fb0","source":{"kind":"arxiv","id":"1908.05054","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.05054","created_at":"2026-07-05T00:16:36Z"},{"alias_kind":"arxiv_version","alias_value":"1908.05054v2","created_at":"2026-07-05T00:16:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.05054","created_at":"2026-07-05T00:16:36Z"},{"alias_kind":"pith_short_12","alias_value":"36JYG46PPUSV","created_at":"2026-07-05T00:16:36Z"},{"alias_kind":"pith_short_16","alias_value":"36JYG46PPUSVSESF","created_at":"2026-07-05T00:16:36Z"},{"alias_kind":"pith_short_8","alias_value":"36JYG46P","created_at":"2026-07-05T00:16:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:36JYG46PPUSVSESFG4LAZLQ4II","target":"record","payload":{"canonical_record":{"source":{"id":"1908.05054","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-14T10:03:12Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"12f5630026bd217c46e1eb1cae6cd3c1b584a5356a46ae87a4b764d40a604074","abstract_canon_sha256":"a8966c950167690f01897724030ba49599779f3c860281a1ae7ff4db5a2c857e"},"schema_version":"1.0"},"canonical_sha256":"df938373cf7d2559124537160cae1c4209408aac125702db136dbf5d53c50fb0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:16:36.159849Z","signature_b64":"+kmQhrJ3LYsmnTi8tpdNhdbBLN8H66GdaTS/zFkwwP5A+WMymIbkP7N3p/VL49r0SNHDdat1C9GjgXXohsIHDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df938373cf7d2559124537160cae1c4209408aac125702db136dbf5d53c50fb0","last_reissued_at":"2026-07-05T00:16:36.159371Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:16:36.159371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.05054","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":"2026-07-05T00:16:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xLMF80E372cKb/OpWBpLRhzAw1fbyofpUXAXyIbueh+D3Bywswv6osCRMDIxoqwME8jA5Pk/FwHpGfQComsgCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:38:54.554527Z"},"content_sha256":"7ee107a3ba02a21e01769144b9a9f9fbcfeab91a00d99e4d5251649bf0b19b1f","schema_version":"1.0","event_id":"sha256:7ee107a3ba02a21e01769144b9a9f9fbcfeab91a00d99e4d5251649bf0b19b1f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:36JYG46PPUSVSESFG4LAZLQ4II","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fusion of Detected Objects in Text for Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chris Alberti, David Reitter, Jeffrey Ling, Michael Collins","submitted_at":"2019-08-14T10:03:12Z","abstract_excerpt":"To advance models of multimodal context, we introduce a simple yet powerful neural architecture for data that combines vision and natural language. The \"Bounding Boxes in Text Transformer\" (B2T2) also leverages referential information binding words to portions of the image in a single unified architecture. B2T2 is highly effective on the Visual Commonsense Reasoning benchmark (https://visualcommonsense.com), achieving a new state-of-the-art with a 25% relative reduction in error rate compared to published baselines and obtaining the best performance to date on the public leaderboard (as of May"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.05054","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/1908.05054/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":"2026-07-05T00:16:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FUyR8RI1BtGuC0tS1wKpvybxf0v8kLb4heX8OFlDyLscDOsZRITuBEv4RnjdNfAjU3mdhqpOVbY8ojAsOnbxCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:38:54.554905Z"},"content_sha256":"cbf7cbf796d8681a407af71e3fd66bb8a2b43615434930ff2e37ece19224a319","schema_version":"1.0","event_id":"sha256:cbf7cbf796d8681a407af71e3fd66bb8a2b43615434930ff2e37ece19224a319"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/36JYG46PPUSVSESFG4LAZLQ4II/bundle.json","state_url":"https://pith.science/pith/36JYG46PPUSVSESFG4LAZLQ4II/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/36JYG46PPUSVSESFG4LAZLQ4II/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":"2026-07-07T04:38:54Z","links":{"resolver":"https://pith.science/pith/36JYG46PPUSVSESFG4LAZLQ4II","bundle":"https://pith.science/pith/36JYG46PPUSVSESFG4LAZLQ4II/bundle.json","state":"https://pith.science/pith/36JYG46PPUSVSESFG4LAZLQ4II/state.json","well_known_bundle":"https://pith.science/.well-known/pith/36JYG46PPUSVSESFG4LAZLQ4II/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:36JYG46PPUSVSESFG4LAZLQ4II","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":"a8966c950167690f01897724030ba49599779f3c860281a1ae7ff4db5a2c857e","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-14T10:03:12Z","title_canon_sha256":"12f5630026bd217c46e1eb1cae6cd3c1b584a5356a46ae87a4b764d40a604074"},"schema_version":"1.0","source":{"id":"1908.05054","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.05054","created_at":"2026-07-05T00:16:36Z"},{"alias_kind":"arxiv_version","alias_value":"1908.05054v2","created_at":"2026-07-05T00:16:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.05054","created_at":"2026-07-05T00:16:36Z"},{"alias_kind":"pith_short_12","alias_value":"36JYG46PPUSV","created_at":"2026-07-05T00:16:36Z"},{"alias_kind":"pith_short_16","alias_value":"36JYG46PPUSVSESF","created_at":"2026-07-05T00:16:36Z"},{"alias_kind":"pith_short_8","alias_value":"36JYG46P","created_at":"2026-07-05T00:16:36Z"}],"graph_snapshots":[{"event_id":"sha256:cbf7cbf796d8681a407af71e3fd66bb8a2b43615434930ff2e37ece19224a319","target":"graph","created_at":"2026-07-05T00:16:36Z","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/1908.05054/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To advance models of multimodal context, we introduce a simple yet powerful neural architecture for data that combines vision and natural language. The \"Bounding Boxes in Text Transformer\" (B2T2) also leverages referential information binding words to portions of the image in a single unified architecture. B2T2 is highly effective on the Visual Commonsense Reasoning benchmark (https://visualcommonsense.com), achieving a new state-of-the-art with a 25% relative reduction in error rate compared to published baselines and obtaining the best performance to date on the public leaderboard (as of May","authors_text":"Chris Alberti, David Reitter, Jeffrey Ling, Michael Collins","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-14T10:03:12Z","title":"Fusion of Detected Objects in Text for Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.05054","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":"sha256:7ee107a3ba02a21e01769144b9a9f9fbcfeab91a00d99e4d5251649bf0b19b1f","target":"record","created_at":"2026-07-05T00:16:36Z","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":"a8966c950167690f01897724030ba49599779f3c860281a1ae7ff4db5a2c857e","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-14T10:03:12Z","title_canon_sha256":"12f5630026bd217c46e1eb1cae6cd3c1b584a5356a46ae87a4b764d40a604074"},"schema_version":"1.0","source":{"id":"1908.05054","kind":"arxiv","version":2}},"canonical_sha256":"df938373cf7d2559124537160cae1c4209408aac125702db136dbf5d53c50fb0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df938373cf7d2559124537160cae1c4209408aac125702db136dbf5d53c50fb0","first_computed_at":"2026-07-05T00:16:36.159371Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:16:36.159371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+kmQhrJ3LYsmnTi8tpdNhdbBLN8H66GdaTS/zFkwwP5A+WMymIbkP7N3p/VL49r0SNHDdat1C9GjgXXohsIHDA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:16:36.159849Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.05054","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ee107a3ba02a21e01769144b9a9f9fbcfeab91a00d99e4d5251649bf0b19b1f","sha256:cbf7cbf796d8681a407af71e3fd66bb8a2b43615434930ff2e37ece19224a319"],"state_sha256":"c7a79f3fbccba02fd63ffe0c2d33f35505d77f52e488d89c78ae1bfc87e5a303"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8g0iqKu57DlMwk6PqEl+p7GmLbjeIrqLvY96nN5U7RtwTu7vKWTmUNdMeWa/TjMyT/33A3lPG6YnRovpuO2fAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T04:38:54.557082Z","bundle_sha256":"eef2328514f96353f0e3b85299ed2f317e5c5704423538c231f86a5bc1518d94"}}