{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:7ZCP2JSQTFE36UXSDWIDKDWV4Y","short_pith_number":"pith:7ZCP2JSQ","schema_version":"1.0","canonical_sha256":"fe44fd26509949bf52f21d90350ed5e6015256e281bd2f543654df76a58a510a","source":{"kind":"arxiv","id":"2012.11587","version":1},"attestation_state":"computed","paper":{"title":"Object-Centric Diagnosis of Visual Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chuang Gan, David D. Cox, Devi Parikh, Jiajun Wu, Jianwei Yang, Jiayuan Mao, Joshua B. Tenenbaum","submitted_at":"2020-12-21T18:59:28Z","abstract_excerpt":"When answering questions about an image, it not only needs knowing what -- understanding the fine-grained contents (e.g., objects, relationships) in the image, but also telling why -- reasoning over grounding visual cues to derive the answer for a question. Over the last few years, we have seen significant progress on visual question answering. Though impressive as the accuracy grows, it still lags behind to get knowing whether these models are undertaking grounding visual reasoning or just leveraging spurious correlations in the training data. Recently, a number of works have attempted to ans"},"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":"2012.11587","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-12-21T18:59:28Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"ec97ffb74109bac38383166754b6664c1dfb0b9c952c5921ba9fce574eef00bc","abstract_canon_sha256":"2e488388cc2fbc966e13f5a7ddba08907b5a58e2af2d4571460e7494d403696b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:01:02.924001Z","signature_b64":"bMUJElrGf/DBE4+uETnaojh3XVXRKFyFUcJnITSbpwzDFap/+wBJ4D7yHh/IGzF5BKuH7KV89ZjKLkYZgDNlAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe44fd26509949bf52f21d90350ed5e6015256e281bd2f543654df76a58a510a","last_reissued_at":"2026-07-05T02:01:02.923528Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:01:02.923528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Object-Centric Diagnosis of Visual Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chuang Gan, David D. Cox, Devi Parikh, Jiajun Wu, Jianwei Yang, Jiayuan Mao, Joshua B. Tenenbaum","submitted_at":"2020-12-21T18:59:28Z","abstract_excerpt":"When answering questions about an image, it not only needs knowing what -- understanding the fine-grained contents (e.g., objects, relationships) in the image, but also telling why -- reasoning over grounding visual cues to derive the answer for a question. Over the last few years, we have seen significant progress on visual question answering. Though impressive as the accuracy grows, it still lags behind to get knowing whether these models are undertaking grounding visual reasoning or just leveraging spurious correlations in the training data. Recently, a number of works have attempted to ans"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.11587","kind":"arxiv","version":1},"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/2012.11587/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":"2012.11587","created_at":"2026-07-05T02:01:02.923589+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.11587v1","created_at":"2026-07-05T02:01:02.923589+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.11587","created_at":"2026-07-05T02:01:02.923589+00:00"},{"alias_kind":"pith_short_12","alias_value":"7ZCP2JSQTFE3","created_at":"2026-07-05T02:01:02.923589+00:00"},{"alias_kind":"pith_short_16","alias_value":"7ZCP2JSQTFE36UXS","created_at":"2026-07-05T02:01:02.923589+00:00"},{"alias_kind":"pith_short_8","alias_value":"7ZCP2JSQ","created_at":"2026-07-05T02:01:02.923589+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7ZCP2JSQTFE36UXSDWIDKDWV4Y","json":"https://pith.science/pith/7ZCP2JSQTFE36UXSDWIDKDWV4Y.json","graph_json":"https://pith.science/api/pith-number/7ZCP2JSQTFE36UXSDWIDKDWV4Y/graph.json","events_json":"https://pith.science/api/pith-number/7ZCP2JSQTFE36UXSDWIDKDWV4Y/events.json","paper":"https://pith.science/paper/7ZCP2JSQ"},"agent_actions":{"view_html":"https://pith.science/pith/7ZCP2JSQTFE36UXSDWIDKDWV4Y","download_json":"https://pith.science/pith/7ZCP2JSQTFE36UXSDWIDKDWV4Y.json","view_paper":"https://pith.science/paper/7ZCP2JSQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.11587&json=true","fetch_graph":"https://pith.science/api/pith-number/7ZCP2JSQTFE36UXSDWIDKDWV4Y/graph.json","fetch_events":"https://pith.science/api/pith-number/7ZCP2JSQTFE36UXSDWIDKDWV4Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7ZCP2JSQTFE36UXSDWIDKDWV4Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7ZCP2JSQTFE36UXSDWIDKDWV4Y/action/storage_attestation","attest_author":"https://pith.science/pith/7ZCP2JSQTFE36UXSDWIDKDWV4Y/action/author_attestation","sign_citation":"https://pith.science/pith/7ZCP2JSQTFE36UXSDWIDKDWV4Y/action/citation_signature","submit_replication":"https://pith.science/pith/7ZCP2JSQTFE36UXSDWIDKDWV4Y/action/replication_record"}},"created_at":"2026-07-05T02:01:02.923589+00:00","updated_at":"2026-07-05T02:01:02.923589+00:00"}