{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5RCOYO46LLWRIJ4TOLKXD5D2RG","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":"1250d7e2d2cab1999cdcf47797169e218df75ac1ff5f668b975d46910fb23f4d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-21T18:57:21Z","title_canon_sha256":"c3dfd80c1cf0e1a037a367bb1bc6c32b5d556c3e7c183c00b8363286d0686586"},"schema_version":"1.0","source":{"id":"2308.11662","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.11662","created_at":"2026-07-05T06:44:51Z"},{"alias_kind":"arxiv_version","alias_value":"2308.11662v2","created_at":"2026-07-05T06:44:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.11662","created_at":"2026-07-05T06:44:51Z"},{"alias_kind":"pith_short_12","alias_value":"5RCOYO46LLWR","created_at":"2026-07-05T06:44:51Z"},{"alias_kind":"pith_short_16","alias_value":"5RCOYO46LLWRIJ4T","created_at":"2026-07-05T06:44:51Z"},{"alias_kind":"pith_short_8","alias_value":"5RCOYO46","created_at":"2026-07-05T06:44:51Z"}],"graph_snapshots":[{"event_id":"sha256:1267b4c3fe30366d3f1c4cacce47de77041ab98a9a053248084997af6527ec9c","target":"graph","created_at":"2026-07-05T06:44:51Z","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/2308.11662/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual question answering is a task of predicting the answer to a question about an image. Given that different people can provide different answers to a visual question, we aim to better understand why with answer groundings. We introduce the first dataset that visually grounds each unique answer to each visual question, which we call VQAAnswerTherapy. We then propose two novel problems of predicting whether a visual question has a single answer grounding and localizing all answer groundings. We benchmark modern algorithms for these novel problems to show where they succeed and struggle. The ","authors_text":"Chongyan Chen, Danna Gurari, Samreen Anjum","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-21T18:57:21Z","title":"VQA Therapy: Exploring Answer Differences by Visually Grounding Answers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.11662","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:e9ac2a4c073c98cd9f510273126962f272578e4c26bfe5735867fa940cad0af7","target":"record","created_at":"2026-07-05T06:44:51Z","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":"1250d7e2d2cab1999cdcf47797169e218df75ac1ff5f668b975d46910fb23f4d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-21T18:57:21Z","title_canon_sha256":"c3dfd80c1cf0e1a037a367bb1bc6c32b5d556c3e7c183c00b8363286d0686586"},"schema_version":"1.0","source":{"id":"2308.11662","kind":"arxiv","version":2}},"canonical_sha256":"ec44ec3b9e5aed14279372d571f47a89aba124f91eedf07e8dc96e4ceaa2aafb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec44ec3b9e5aed14279372d571f47a89aba124f91eedf07e8dc96e4ceaa2aafb","first_computed_at":"2026-07-05T06:44:51.291128Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:44:51.291128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dDZjLh+kTyKDGSZrAfb0TGw14HiTJ/GU8/Oc2zhb+sCvsLeTUecL8CsPmPoFFaDZ1IJTx3zSU54Wo8rLLKxKDw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:44:51.291537Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.11662","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e9ac2a4c073c98cd9f510273126962f272578e4c26bfe5735867fa940cad0af7","sha256:1267b4c3fe30366d3f1c4cacce47de77041ab98a9a053248084997af6527ec9c"],"state_sha256":"943cdafd9fd4b313af8da5a60743ddded6a6a634d9818639ec9246fa166a126b"}