{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:IOB7TPSDO4WUJUGCL5OYSQUTGZ","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":"1a9be088fa340c48e0062fc7e2bdcbcaf162b54e5076601c14961302311e47e1","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-04-04T22:15:35Z","title_canon_sha256":"67151a891c19e8cf7a3528fc9e622f2e0e8260ae8db368f56a949c3855b9d700"},"schema_version":"1.0","source":{"id":"2004.02032","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.02032","created_at":"2026-07-05T00:52:55Z"},{"alias_kind":"arxiv_version","alias_value":"2004.02032v1","created_at":"2026-07-05T00:52:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.02032","created_at":"2026-07-05T00:52:55Z"},{"alias_kind":"pith_short_12","alias_value":"IOB7TPSDO4WU","created_at":"2026-07-05T00:52:55Z"},{"alias_kind":"pith_short_16","alias_value":"IOB7TPSDO4WUJUGC","created_at":"2026-07-05T00:52:55Z"},{"alias_kind":"pith_short_8","alias_value":"IOB7TPSD","created_at":"2026-07-05T00:52:55Z"}],"graph_snapshots":[{"event_id":"sha256:52551d164f544ab2dc25601d8461aa37a5fb0c0828428caf9f33357561abdf90","target":"graph","created_at":"2026-07-05T00:52:55Z","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/2004.02032/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite recent advances in Visual QuestionAnswering (VQA), it remains a challenge todetermine how much success can be attributedto sound reasoning and comprehension ability.We seek to investigate this question by propos-ing a new task ofrationale generation. Es-sentially, we task a VQA model with generat-ing rationales for the answers it predicts. Weuse data from the Visual Commonsense Rea-soning (VCR) task, as it contains ground-truthrationales along with visual questions and an-swers. We first investigate commonsense un-derstanding in one of the leading VCR mod-els, ViLBERT, by generating ra","authors_text":"Garrison W. Cottrell, Hammad A. Ayyubi, Julian J. McAuley, Md. Mehrab Tanjim","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-04-04T22:15:35Z","title":"Generating Rationales in Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.02032","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":"sha256:8f188845717835cc71a1b29a1c20078af5307b060477430e94e9ddb959db6f48","target":"record","created_at":"2026-07-05T00:52:55Z","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":"1a9be088fa340c48e0062fc7e2bdcbcaf162b54e5076601c14961302311e47e1","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-04-04T22:15:35Z","title_canon_sha256":"67151a891c19e8cf7a3528fc9e622f2e0e8260ae8db368f56a949c3855b9d700"},"schema_version":"1.0","source":{"id":"2004.02032","kind":"arxiv","version":1}},"canonical_sha256":"4383f9be43772d44d0c25f5d894293364d6d4f876224dfbb6ce5dc1390dc6e9d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4383f9be43772d44d0c25f5d894293364d6d4f876224dfbb6ce5dc1390dc6e9d","first_computed_at":"2026-07-05T00:52:55.360612Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:52:55.360612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XDOq4hUUqnC9QFpF2Z8ZVl0gsOqJBfv9FAKaTijVUXBvAHws2x9wLgmEC1ZOk42mK4UmCbU6m499hccG77YbBA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:52:55.360970Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.02032","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f188845717835cc71a1b29a1c20078af5307b060477430e94e9ddb959db6f48","sha256:52551d164f544ab2dc25601d8461aa37a5fb0c0828428caf9f33357561abdf90"],"state_sha256":"0f3d1d3b1c35ff040377831b43aa0c505eb54c4d2e5ce7e0c37a86446cefea1f"}