{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:RBCRK2SWIW3G57K4ZN3BV4ZFNY","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":"e278a119c0c46be7ab02a40bce97b7e6d84b013e248866b7c8dbd1751309d968","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-27T11:43:45Z","title_canon_sha256":"514d8103576d9d5badda79650435e6475d8ed8db4a7193ca5fa59dc8f6a0d58e"},"schema_version":"1.0","source":{"id":"2011.13681","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.13681","created_at":"2026-07-05T03:58:01Z"},{"alias_kind":"arxiv_version","alias_value":"2011.13681v4","created_at":"2026-07-05T03:58:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.13681","created_at":"2026-07-05T03:58:01Z"},{"alias_kind":"pith_short_12","alias_value":"RBCRK2SWIW3G","created_at":"2026-07-05T03:58:01Z"},{"alias_kind":"pith_short_16","alias_value":"RBCRK2SWIW3G57K4","created_at":"2026-07-05T03:58:01Z"},{"alias_kind":"pith_short_8","alias_value":"RBCRK2SW","created_at":"2026-07-05T03:58:01Z"}],"graph_snapshots":[{"event_id":"sha256:2a22b1c2ae46599c5deb45a4024d4f7facc517afd332f9bac879e9b257b6af3a","target":"graph","created_at":"2026-07-05T03:58:01Z","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/2011.13681/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Arjun Mani, Nobline Yoo, Olga Russakovsky, Will Hinthorn","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-27T11:43:45Z","title":"Point and Ask: Incorporating Pointing into Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.13681","kind":"arxiv","version":4},"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":"sha256:6c6530fc10a0d81fb4922c5b8ff235a5639e72292dd348d8cedd0e97f115745d","target":"record","created_at":"2026-07-05T03:58:01Z","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":"e278a119c0c46be7ab02a40bce97b7e6d84b013e248866b7c8dbd1751309d968","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-27T11:43:45Z","title_canon_sha256":"514d8103576d9d5badda79650435e6475d8ed8db4a7193ca5fa59dc8f6a0d58e"},"schema_version":"1.0","source":{"id":"2011.13681","kind":"arxiv","version":4}},"canonical_sha256":"8845156a5645b66efd5ccb761af3256e20e1e9af6f7ea0781c145190968bec07","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8845156a5645b66efd5ccb761af3256e20e1e9af6f7ea0781c145190968bec07","first_computed_at":"2026-07-05T03:58:01.015116Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:58:01.015116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MmHPYQxk+CeuwXR+iTPlM3g2i2Ef460l4Fz1f3w2Ds/v1aHqbLr+AYA+EQIa65WqxhEHEWha0jfVjCN6hk+DCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:58:01.015563Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.13681","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c6530fc10a0d81fb4922c5b8ff235a5639e72292dd348d8cedd0e97f115745d","sha256:2a22b1c2ae46599c5deb45a4024d4f7facc517afd332f9bac879e9b257b6af3a"],"state_sha256":"9dc4a3d934e29c19a4e5c256ab4dca4b8d2f7b3db197f4c3d205c9b54230de57"}