{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:RBCRK2SWIW3G57K4ZN3BV4ZFNY","short_pith_number":"pith:RBCRK2SW","schema_version":"1.0","canonical_sha256":"8845156a5645b66efd5ccb761af3256e20e1e9af6f7ea0781c145190968bec07","source":{"kind":"arxiv","id":"2011.13681","version":4},"attestation_state":"computed","paper":{"title":"Point and Ask: Incorporating Pointing into Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arjun Mani, Nobline Yoo, Olga Russakovsky, Will Hinthorn","submitted_at":"2020-11-27T11:43:45Z","abstract_excerpt":"Visual Question Answering (VQA) has become one of the key benchmarks of visual recognition progress. Multiple VQA extensions have been explored to better simulate real-world settings: different question formulations, changing training and test distributions, conversational consistency in dialogues, and explanation-based answering. In this work, we further expand this space by considering visual questions that include a spatial point of reference. Pointing is a nearly universal gesture among humans, and real-world VQA is likely to involve a gesture towards the target region.\n  Concretely, we (1"},"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":"2011.13681","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-27T11:43:45Z","cross_cats_sorted":[],"title_canon_sha256":"514d8103576d9d5badda79650435e6475d8ed8db4a7193ca5fa59dc8f6a0d58e","abstract_canon_sha256":"e278a119c0c46be7ab02a40bce97b7e6d84b013e248866b7c8dbd1751309d968"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:58:01.015563Z","signature_b64":"MmHPYQxk+CeuwXR+iTPlM3g2i2Ef460l4Fz1f3w2Ds/v1aHqbLr+AYA+EQIa65WqxhEHEWha0jfVjCN6hk+DCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8845156a5645b66efd5ccb761af3256e20e1e9af6f7ea0781c145190968bec07","last_reissued_at":"2026-07-05T03:58:01.015116Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:58:01.015116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Point and Ask: Incorporating Pointing into Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arjun Mani, Nobline Yoo, Olga Russakovsky, Will Hinthorn","submitted_at":"2020-11-27T11:43:45Z","abstract_excerpt":"Visual Question Answering (VQA) has become one of the key benchmarks of visual recognition progress. Multiple VQA extensions have been explored to better simulate real-world settings: different question formulations, changing training and test distributions, conversational consistency in dialogues, and explanation-based answering. In this work, we further expand this space by considering visual questions that include a spatial point of reference. Pointing is a nearly universal gesture among humans, and real-world VQA is likely to involve a gesture towards the target region.\n  Concretely, we (1"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.13681","kind":"arxiv","version":4},"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/2011.13681/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":"2011.13681","created_at":"2026-07-05T03:58:01.015170+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.13681v4","created_at":"2026-07-05T03:58:01.015170+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.13681","created_at":"2026-07-05T03:58:01.015170+00:00"},{"alias_kind":"pith_short_12","alias_value":"RBCRK2SWIW3G","created_at":"2026-07-05T03:58:01.015170+00:00"},{"alias_kind":"pith_short_16","alias_value":"RBCRK2SWIW3G57K4","created_at":"2026-07-05T03:58:01.015170+00:00"},{"alias_kind":"pith_short_8","alias_value":"RBCRK2SW","created_at":"2026-07-05T03:58:01.015170+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2312.16886","citing_title":"MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2309.17421","citing_title":"The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)","ref_index":90,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RBCRK2SWIW3G57K4ZN3BV4ZFNY","json":"https://pith.science/pith/RBCRK2SWIW3G57K4ZN3BV4ZFNY.json","graph_json":"https://pith.science/api/pith-number/RBCRK2SWIW3G57K4ZN3BV4ZFNY/graph.json","events_json":"https://pith.science/api/pith-number/RBCRK2SWIW3G57K4ZN3BV4ZFNY/events.json","paper":"https://pith.science/paper/RBCRK2SW"},"agent_actions":{"view_html":"https://pith.science/pith/RBCRK2SWIW3G57K4ZN3BV4ZFNY","download_json":"https://pith.science/pith/RBCRK2SWIW3G57K4ZN3BV4ZFNY.json","view_paper":"https://pith.science/paper/RBCRK2SW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.13681&json=true","fetch_graph":"https://pith.science/api/pith-number/RBCRK2SWIW3G57K4ZN3BV4ZFNY/graph.json","fetch_events":"https://pith.science/api/pith-number/RBCRK2SWIW3G57K4ZN3BV4ZFNY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RBCRK2SWIW3G57K4ZN3BV4ZFNY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RBCRK2SWIW3G57K4ZN3BV4ZFNY/action/storage_attestation","attest_author":"https://pith.science/pith/RBCRK2SWIW3G57K4ZN3BV4ZFNY/action/author_attestation","sign_citation":"https://pith.science/pith/RBCRK2SWIW3G57K4ZN3BV4ZFNY/action/citation_signature","submit_replication":"https://pith.science/pith/RBCRK2SWIW3G57K4ZN3BV4ZFNY/action/replication_record"}},"created_at":"2026-07-05T03:58:01.015170+00:00","updated_at":"2026-07-05T03:58:01.015170+00:00"}