{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TEV332PWHHFAAJ6FCQY2DQBIH5","short_pith_number":"pith:TEV332PW","schema_version":"1.0","canonical_sha256":"992bbde9f639ca0027c51431a1c0283f5e39fe1a182d49b83f59daaac5401ca7","source":{"kind":"arxiv","id":"2501.02201","version":2},"attestation_state":"computed","paper":{"title":"Acknowledging Focus Ambiguity in Visual Questions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anush Venkatesh, Chongyan Chen, Danna Gurari, Yu-Yun Tseng, Zhuoheng Li","submitted_at":"2025-01-04T05:36:11Z","abstract_excerpt":"No published work on visual question answering (VQA) accounts for ambiguity regarding where the content described in the question is located in the image. To fill this gap, we introduce VQ-FocusAmbiguity, the first VQA dataset that visually grounds each plausible image region a question could refer to when arriving at valid answers. We next analyze and compare our dataset to existing datasets to reveal its unique properties. Finally, we benchmark modern models for two novel tasks related to acknowledging focus ambiguity: recognizing whether a visual question has focus ambiguity and locating al"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2501.02201","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-04T05:36:11Z","cross_cats_sorted":[],"title_canon_sha256":"3041d510a47232a23d784d65649e64105ae485c09d2596c3b5a6031738985ade","abstract_canon_sha256":"27490fc4352a223befa17dc0a3c110e30eccafd0b363edf733c880ffd0e8127a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:55.076377Z","signature_b64":"6NifdLV1prH1MxomHN9WWuku+u58YqTEnRX1+TEn6xGOL9Mb0iIc8gtOhmobsbAFyl5mPYc2d1nk1uqmPx79BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"992bbde9f639ca0027c51431a1c0283f5e39fe1a182d49b83f59daaac5401ca7","last_reissued_at":"2026-07-05T11:45:55.075813Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:55.075813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Acknowledging Focus Ambiguity in Visual Questions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anush Venkatesh, Chongyan Chen, Danna Gurari, Yu-Yun Tseng, Zhuoheng Li","submitted_at":"2025-01-04T05:36:11Z","abstract_excerpt":"No published work on visual question answering (VQA) accounts for ambiguity regarding where the content described in the question is located in the image. To fill this gap, we introduce VQ-FocusAmbiguity, the first VQA dataset that visually grounds each plausible image region a question could refer to when arriving at valid answers. We next analyze and compare our dataset to existing datasets to reveal its unique properties. Finally, we benchmark modern models for two novel tasks related to acknowledging focus ambiguity: recognizing whether a visual question has focus ambiguity and locating al"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.02201","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/2501.02201/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2501.02201","created_at":"2026-07-05T11:45:55.075875+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.02201v2","created_at":"2026-07-05T11:45:55.075875+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.02201","created_at":"2026-07-05T11:45:55.075875+00:00"},{"alias_kind":"pith_short_12","alias_value":"TEV332PWHHFA","created_at":"2026-07-05T11:45:55.075875+00:00"},{"alias_kind":"pith_short_16","alias_value":"TEV332PWHHFAAJ6F","created_at":"2026-07-05T11:45:55.075875+00:00"},{"alias_kind":"pith_short_8","alias_value":"TEV332PW","created_at":"2026-07-05T11:45:55.075875+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07817","citing_title":"GazeVLM: Active Vision via Internal Attention Control for Multimodal Reasoning","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TEV332PWHHFAAJ6FCQY2DQBIH5","json":"https://pith.science/pith/TEV332PWHHFAAJ6FCQY2DQBIH5.json","graph_json":"https://pith.science/api/pith-number/TEV332PWHHFAAJ6FCQY2DQBIH5/graph.json","events_json":"https://pith.science/api/pith-number/TEV332PWHHFAAJ6FCQY2DQBIH5/events.json","paper":"https://pith.science/paper/TEV332PW"},"agent_actions":{"view_html":"https://pith.science/pith/TEV332PWHHFAAJ6FCQY2DQBIH5","download_json":"https://pith.science/pith/TEV332PWHHFAAJ6FCQY2DQBIH5.json","view_paper":"https://pith.science/paper/TEV332PW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.02201&json=true","fetch_graph":"https://pith.science/api/pith-number/TEV332PWHHFAAJ6FCQY2DQBIH5/graph.json","fetch_events":"https://pith.science/api/pith-number/TEV332PWHHFAAJ6FCQY2DQBIH5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TEV332PWHHFAAJ6FCQY2DQBIH5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TEV332PWHHFAAJ6FCQY2DQBIH5/action/storage_attestation","attest_author":"https://pith.science/pith/TEV332PWHHFAAJ6FCQY2DQBIH5/action/author_attestation","sign_citation":"https://pith.science/pith/TEV332PWHHFAAJ6FCQY2DQBIH5/action/citation_signature","submit_replication":"https://pith.science/pith/TEV332PWHHFAAJ6FCQY2DQBIH5/action/replication_record"}},"created_at":"2026-07-05T11:45:55.075875+00:00","updated_at":"2026-07-05T11:45:55.075875+00:00"}