{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:WMD5MUUEKOLLYZ6Z7KMAACYBCF","short_pith_number":"pith:WMD5MUUE","canonical_record":{"source":{"id":"2112.08614","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-16T04:37:10Z","cross_cats_sorted":[],"title_canon_sha256":"b9d61b39303c2448e046f261a76d7ba338b4b17ca03f5b5633348c189c17cef8","abstract_canon_sha256":"08e75873d2464d1ff9ed256c818f507c544d048c7ffebf9b689cfa4c87e6023f"},"schema_version":"1.0"},"canonical_sha256":"b307d652845396bc67d9fa98000b01116b9a004a1441e26eca48b648ba5e70ab","source":{"kind":"arxiv","id":"2112.08614","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.08614","created_at":"2026-07-05T04:20:31Z"},{"alias_kind":"arxiv_version","alias_value":"2112.08614v2","created_at":"2026-07-05T04:20:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.08614","created_at":"2026-07-05T04:20:31Z"},{"alias_kind":"pith_short_12","alias_value":"WMD5MUUEKOLL","created_at":"2026-07-05T04:20:31Z"},{"alias_kind":"pith_short_16","alias_value":"WMD5MUUEKOLLYZ6Z","created_at":"2026-07-05T04:20:31Z"},{"alias_kind":"pith_short_8","alias_value":"WMD5MUUE","created_at":"2026-07-05T04:20:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:WMD5MUUEKOLLYZ6Z7KMAACYBCF","target":"record","payload":{"canonical_record":{"source":{"id":"2112.08614","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-16T04:37:10Z","cross_cats_sorted":[],"title_canon_sha256":"b9d61b39303c2448e046f261a76d7ba338b4b17ca03f5b5633348c189c17cef8","abstract_canon_sha256":"08e75873d2464d1ff9ed256c818f507c544d048c7ffebf9b689cfa4c87e6023f"},"schema_version":"1.0"},"canonical_sha256":"b307d652845396bc67d9fa98000b01116b9a004a1441e26eca48b648ba5e70ab","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:20:31.798651Z","signature_b64":"l/Txdn1F5mgBbTBU6gUUNixIVtS+5xlcIrO71euseAcp10574jX6XrvQX5ff9vod3cAI+soj+M+IoaftYKvkAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b307d652845396bc67d9fa98000b01116b9a004a1441e26eca48b648ba5e70ab","last_reissued_at":"2026-07-05T04:20:31.798161Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:20:31.798161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.08614","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":"2026-07-05T04:20:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vGoYQsqBgoDPTUKWyKATUOuZ+ozglpm1iQ0LxIsCLM0pCMt0F4HaA7D2gqvxsblFNdPBO1Kcp/1FcMBbN97iBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:06:09.276552Z"},"content_sha256":"9910493f38c26be5c5f6c57c6324331852e11cc21c88cde20ad10502056f815e","schema_version":"1.0","event_id":"sha256:9910493f38c26be5c5f6c57c6324331852e11cc21c88cde20ad10502056f815e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:WMD5MUUEKOLLYZ6Z7KMAACYBCF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"KAT: A Knowledge Augmented Transformer for Vision-and-Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alex Hauptmann, Borui Wang, Jianfeng Gao, Liangke Gui, Qiuyuan Huang, Yonatan Bisk","submitted_at":"2021-12-16T04:37:10Z","abstract_excerpt":"The primary focus of recent work with largescale transformers has been on optimizing the amount of information packed into the model's parameters. In this work, we ask a different question: Can multimodal transformers leverage explicit knowledge in their reasoning? Existing, primarily unimodal, methods have explored approaches under the paradigm of knowledge retrieval followed by answer prediction, but leave open questions about the quality and relevance of the retrieved knowledge used, and how the reasoning processes over implicit and explicit knowledge should be integrated. To address these "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.08614","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/2112.08614/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":"2026-07-05T04:20:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RB+A2Est2VXSXUpxxlOZfkcJ3+hVOyIFO04ueI3YClE5nQv7kbTp9I96wCp0tRfE8yqyvyqSoly0xmd/o59TBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:06:09.276914Z"},"content_sha256":"20fe537d5558f98354fb70f8a3c28f762b92508058087c11445dc161000fc610","schema_version":"1.0","event_id":"sha256:20fe537d5558f98354fb70f8a3c28f762b92508058087c11445dc161000fc610"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WMD5MUUEKOLLYZ6Z7KMAACYBCF/bundle.json","state_url":"https://pith.science/pith/WMD5MUUEKOLLYZ6Z7KMAACYBCF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WMD5MUUEKOLLYZ6Z7KMAACYBCF/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":"2026-07-06T19:06:09Z","links":{"resolver":"https://pith.science/pith/WMD5MUUEKOLLYZ6Z7KMAACYBCF","bundle":"https://pith.science/pith/WMD5MUUEKOLLYZ6Z7KMAACYBCF/bundle.json","state":"https://pith.science/pith/WMD5MUUEKOLLYZ6Z7KMAACYBCF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WMD5MUUEKOLLYZ6Z7KMAACYBCF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:WMD5MUUEKOLLYZ6Z7KMAACYBCF","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":"08e75873d2464d1ff9ed256c818f507c544d048c7ffebf9b689cfa4c87e6023f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-16T04:37:10Z","title_canon_sha256":"b9d61b39303c2448e046f261a76d7ba338b4b17ca03f5b5633348c189c17cef8"},"schema_version":"1.0","source":{"id":"2112.08614","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.08614","created_at":"2026-07-05T04:20:31Z"},{"alias_kind":"arxiv_version","alias_value":"2112.08614v2","created_at":"2026-07-05T04:20:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.08614","created_at":"2026-07-05T04:20:31Z"},{"alias_kind":"pith_short_12","alias_value":"WMD5MUUEKOLL","created_at":"2026-07-05T04:20:31Z"},{"alias_kind":"pith_short_16","alias_value":"WMD5MUUEKOLLYZ6Z","created_at":"2026-07-05T04:20:31Z"},{"alias_kind":"pith_short_8","alias_value":"WMD5MUUE","created_at":"2026-07-05T04:20:31Z"}],"graph_snapshots":[{"event_id":"sha256:20fe537d5558f98354fb70f8a3c28f762b92508058087c11445dc161000fc610","target":"graph","created_at":"2026-07-05T04:20:31Z","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/2112.08614/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The primary focus of recent work with largescale transformers has been on optimizing the amount of information packed into the model's parameters. In this work, we ask a different question: Can multimodal transformers leverage explicit knowledge in their reasoning? Existing, primarily unimodal, methods have explored approaches under the paradigm of knowledge retrieval followed by answer prediction, but leave open questions about the quality and relevance of the retrieved knowledge used, and how the reasoning processes over implicit and explicit knowledge should be integrated. To address these ","authors_text":"Alex Hauptmann, Borui Wang, Jianfeng Gao, Liangke Gui, Qiuyuan Huang, Yonatan Bisk","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-16T04:37:10Z","title":"KAT: A Knowledge Augmented Transformer for Vision-and-Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.08614","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":"sha256:9910493f38c26be5c5f6c57c6324331852e11cc21c88cde20ad10502056f815e","target":"record","created_at":"2026-07-05T04:20:31Z","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":"08e75873d2464d1ff9ed256c818f507c544d048c7ffebf9b689cfa4c87e6023f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-16T04:37:10Z","title_canon_sha256":"b9d61b39303c2448e046f261a76d7ba338b4b17ca03f5b5633348c189c17cef8"},"schema_version":"1.0","source":{"id":"2112.08614","kind":"arxiv","version":2}},"canonical_sha256":"b307d652845396bc67d9fa98000b01116b9a004a1441e26eca48b648ba5e70ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b307d652845396bc67d9fa98000b01116b9a004a1441e26eca48b648ba5e70ab","first_computed_at":"2026-07-05T04:20:31.798161Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:20:31.798161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l/Txdn1F5mgBbTBU6gUUNixIVtS+5xlcIrO71euseAcp10574jX6XrvQX5ff9vod3cAI+soj+M+IoaftYKvkAA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:20:31.798651Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.08614","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9910493f38c26be5c5f6c57c6324331852e11cc21c88cde20ad10502056f815e","sha256:20fe537d5558f98354fb70f8a3c28f762b92508058087c11445dc161000fc610"],"state_sha256":"624c87bc614f73c2a580f9dca9ade463394864fb3adcc3435a5fe1e093370a8b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BLEFiStNtoVtMRa944ZgIkKPQlXXyF2iF5GFbuCt4U8jgVTg1PB075WvcSXSwjGqTnfP3UnLLu1agOD3OJfeDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T19:06:09.281726Z","bundle_sha256":"72368f22327d52cdead8d89dffb14e7f335001fbcf2b54cad854aefecff6f681"}}