{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:TQQHAHW2H7HIQBD235HINP75SH","short_pith_number":"pith:TQQHAHW2","canonical_record":{"source":{"id":"2301.10799","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-25T19:29:19Z","cross_cats_sorted":[],"title_canon_sha256":"47392aa4e51f4899b0bc21aab7471f704ae6fcc07d13052e0b388978f66753ca","abstract_canon_sha256":"013886f21e03cd3590b459350a6bc358d062dfc375483296ec286b3e253dbe78"},"schema_version":"1.0"},"canonical_sha256":"9c20701eda3fce88047adf4e86bffd91e5cafb7981ce36c33ece550ca35eed16","source":{"kind":"arxiv","id":"2301.10799","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.10799","created_at":"2026-07-05T05:40:52Z"},{"alias_kind":"arxiv_version","alias_value":"2301.10799v2","created_at":"2026-07-05T05:40:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.10799","created_at":"2026-07-05T05:40:52Z"},{"alias_kind":"pith_short_12","alias_value":"TQQHAHW2H7HI","created_at":"2026-07-05T05:40:52Z"},{"alias_kind":"pith_short_16","alias_value":"TQQHAHW2H7HIQBD2","created_at":"2026-07-05T05:40:52Z"},{"alias_kind":"pith_short_8","alias_value":"TQQHAHW2","created_at":"2026-07-05T05:40:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:TQQHAHW2H7HIQBD235HINP75SH","target":"record","payload":{"canonical_record":{"source":{"id":"2301.10799","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-25T19:29:19Z","cross_cats_sorted":[],"title_canon_sha256":"47392aa4e51f4899b0bc21aab7471f704ae6fcc07d13052e0b388978f66753ca","abstract_canon_sha256":"013886f21e03cd3590b459350a6bc358d062dfc375483296ec286b3e253dbe78"},"schema_version":"1.0"},"canonical_sha256":"9c20701eda3fce88047adf4e86bffd91e5cafb7981ce36c33ece550ca35eed16","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:40:52.914699Z","signature_b64":"KDDF9G2a9AgN0VpVo0scj+AatYAcq+JIRgwG5nzmld/sCtJfu8Qqi54MTGy5Lakby051ykUpajB3CgRmJo0uAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c20701eda3fce88047adf4e86bffd91e5cafb7981ce36c33ece550ca35eed16","last_reissued_at":"2026-07-05T05:40:52.914219Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:40:52.914219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.10799","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":"2026-07-05T05:40:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y7P91Nt+WVpLpV4fZDK6fFgLdpXWnKkXBBr1qVdB79v/dOQfx2NzcUfNt7DveAoWzP9u9lE22j0zyM+PCvCJAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T18:39:18.155694Z"},"content_sha256":"e5b549396fe1ff6d7e7f780cf5ba65d15b189136f5ed2f12ba878ad6712ae0a3","schema_version":"1.0","event_id":"sha256:e5b549396fe1ff6d7e7f780cf5ba65d15b189136f5ed2f12ba878ad6712ae0a3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:TQQHAHW2H7HIQBD235HINP75SH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards a Unified Model for Generating Answers and Explanations in Visual Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenxi Whitehouse, Pranava Madhyastha, Tillman Weyde","submitted_at":"2023-01-25T19:29:19Z","abstract_excerpt":"The field of visual question answering (VQA) has recently seen a surge in research focused on providing explanations for predicted answers. However, current systems mostly rely on separate models to predict answers and generate explanations, leading to less grounded and frequently inconsistent results. To address this, we propose a multitask learning approach towards a Unified Model for Answer and Explanation generation (UMAE). Our approach involves the addition of artificial prompt tokens to training data and fine-tuning a multimodal encoder-decoder model on a variety of VQA-related tasks. In"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.10799","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/2301.10799/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":"2026-07-05T05:40:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qAljbMtCGAvQGFLft0e0VNyRIEsKSVkemXf/QLco7ACmCwgGJm5sC6M4R66yPG+fCycorALBPS509VkhVQBfDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T18:39:18.156102Z"},"content_sha256":"bb5b5d3b33b5212b28b688602b5b55ae960387a18f355a1184c43077b118d7f8","schema_version":"1.0","event_id":"sha256:bb5b5d3b33b5212b28b688602b5b55ae960387a18f355a1184c43077b118d7f8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TQQHAHW2H7HIQBD235HINP75SH/bundle.json","state_url":"https://pith.science/pith/TQQHAHW2H7HIQBD235HINP75SH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TQQHAHW2H7HIQBD235HINP75SH/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":"2026-08-05T18:39:18Z","links":{"resolver":"https://pith.science/pith/TQQHAHW2H7HIQBD235HINP75SH","bundle":"https://pith.science/pith/TQQHAHW2H7HIQBD235HINP75SH/bundle.json","state":"https://pith.science/pith/TQQHAHW2H7HIQBD235HINP75SH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TQQHAHW2H7HIQBD235HINP75SH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TQQHAHW2H7HIQBD235HINP75SH","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":"013886f21e03cd3590b459350a6bc358d062dfc375483296ec286b3e253dbe78","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-25T19:29:19Z","title_canon_sha256":"47392aa4e51f4899b0bc21aab7471f704ae6fcc07d13052e0b388978f66753ca"},"schema_version":"1.0","source":{"id":"2301.10799","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.10799","created_at":"2026-07-05T05:40:52Z"},{"alias_kind":"arxiv_version","alias_value":"2301.10799v2","created_at":"2026-07-05T05:40:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.10799","created_at":"2026-07-05T05:40:52Z"},{"alias_kind":"pith_short_12","alias_value":"TQQHAHW2H7HI","created_at":"2026-07-05T05:40:52Z"},{"alias_kind":"pith_short_16","alias_value":"TQQHAHW2H7HIQBD2","created_at":"2026-07-05T05:40:52Z"},{"alias_kind":"pith_short_8","alias_value":"TQQHAHW2","created_at":"2026-07-05T05:40:52Z"}],"graph_snapshots":[{"event_id":"sha256:bb5b5d3b33b5212b28b688602b5b55ae960387a18f355a1184c43077b118d7f8","target":"graph","created_at":"2026-07-05T05:40:52Z","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/2301.10799/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The field of visual question answering (VQA) has recently seen a surge in research focused on providing explanations for predicted answers. However, current systems mostly rely on separate models to predict answers and generate explanations, leading to less grounded and frequently inconsistent results. To address this, we propose a multitask learning approach towards a Unified Model for Answer and Explanation generation (UMAE). Our approach involves the addition of artificial prompt tokens to training data and fine-tuning a multimodal encoder-decoder model on a variety of VQA-related tasks. In","authors_text":"Chenxi Whitehouse, Pranava Madhyastha, Tillman Weyde","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-25T19:29:19Z","title":"Towards a Unified Model for Generating Answers and Explanations in Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.10799","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:e5b549396fe1ff6d7e7f780cf5ba65d15b189136f5ed2f12ba878ad6712ae0a3","target":"record","created_at":"2026-07-05T05:40:52Z","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":"013886f21e03cd3590b459350a6bc358d062dfc375483296ec286b3e253dbe78","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-25T19:29:19Z","title_canon_sha256":"47392aa4e51f4899b0bc21aab7471f704ae6fcc07d13052e0b388978f66753ca"},"schema_version":"1.0","source":{"id":"2301.10799","kind":"arxiv","version":2}},"canonical_sha256":"9c20701eda3fce88047adf4e86bffd91e5cafb7981ce36c33ece550ca35eed16","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c20701eda3fce88047adf4e86bffd91e5cafb7981ce36c33ece550ca35eed16","first_computed_at":"2026-07-05T05:40:52.914219Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:40:52.914219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KDDF9G2a9AgN0VpVo0scj+AatYAcq+JIRgwG5nzmld/sCtJfu8Qqi54MTGy5Lakby051ykUpajB3CgRmJo0uAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:40:52.914699Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.10799","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e5b549396fe1ff6d7e7f780cf5ba65d15b189136f5ed2f12ba878ad6712ae0a3","sha256:bb5b5d3b33b5212b28b688602b5b55ae960387a18f355a1184c43077b118d7f8"],"state_sha256":"3ed915ca00c7ebc1eebbeac96f95e0ae98813583123f3ed3cc57f0f8eb80ac85"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pkAK/0bo13gQu4+WHs63y8agSaqscc1/gQIfE5hBJHA9hoseaK7l53w/2vB3lEqKKf7euRNlaU/H7LGUNZTuAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T18:39:18.160029Z","bundle_sha256":"97ce32a77e4927a90daaf6d3514076759ab12a8baf28867b07ec7ce96e6777a5"}}