{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:JPFRLKZ6US6DIU6V2K6TOUWIE5","short_pith_number":"pith:JPFRLKZ6","schema_version":"1.0","canonical_sha256":"4bcb15ab3ea4bc3453d5d2bd3752c82752a892cce04f2d8eb444d8bc47e078d1","source":{"kind":"arxiv","id":"1810.03649","version":2},"attestation_state":"computed","paper":{"title":"Overcoming Language Priors in Visual Question Answering with Adversarial Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aishwarya Agrawal, Sainandan Ramakrishnan, Stefan Lee","submitted_at":"2018-10-08T18:29:05Z","abstract_excerpt":"Modern Visual Question Answering (VQA) models have been shown to rely heavily on superficial correlations between question and answer words learned during training such as overwhelmingly reporting the type of room as kitchen or the sport being played as tennis, irrespective of the image. Most alarmingly, this shortcoming is often not well reflected during evaluation because the same strong priors exist in test distributions; however, a VQA system that fails to ground questions in image content would likely perform poorly in real-world settings. In this work, we present a novel regularization s"},"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":"1810.03649","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-08T18:29:05Z","cross_cats_sorted":[],"title_canon_sha256":"521f2093a4577dc4935b771c9bcb5c47b37750b459092255081ea94fa793394c","abstract_canon_sha256":"925aaceb5a92fd8c7ac8997abc2fde3eac913565a4d7fad91c6f61327bdfa28f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:14.566749Z","signature_b64":"ehI9TpJPj1trEr1nWeP2bMP+3Bq93cOuWpIkLd7XcgiPfoWXhnyfB8K5E31OhE97JjT2+Sb5jXhDZrcJXtHCDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bcb15ab3ea4bc3453d5d2bd3752c82752a892cce04f2d8eb444d8bc47e078d1","last_reissued_at":"2026-05-18T00:01:14.566180Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:14.566180Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Overcoming Language Priors in Visual Question Answering with Adversarial Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aishwarya Agrawal, Sainandan Ramakrishnan, Stefan Lee","submitted_at":"2018-10-08T18:29:05Z","abstract_excerpt":"Modern Visual Question Answering (VQA) models have been shown to rely heavily on superficial correlations between question and answer words learned during training such as overwhelmingly reporting the type of room as kitchen or the sport being played as tennis, irrespective of the image. Most alarmingly, this shortcoming is often not well reflected during evaluation because the same strong priors exist in test distributions; however, a VQA system that fails to ground questions in image content would likely perform poorly in real-world settings. In this work, we present a novel regularization s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.03649","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":""},"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":"1810.03649","created_at":"2026-05-18T00:01:14.566258+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.03649v2","created_at":"2026-05-18T00:01:14.566258+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.03649","created_at":"2026-05-18T00:01:14.566258+00:00"},{"alias_kind":"pith_short_12","alias_value":"JPFRLKZ6US6D","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"JPFRLKZ6US6DIU6V","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"JPFRLKZ6","created_at":"2026-05-18T12:32:31.084164+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/JPFRLKZ6US6DIU6V2K6TOUWIE5","json":"https://pith.science/pith/JPFRLKZ6US6DIU6V2K6TOUWIE5.json","graph_json":"https://pith.science/api/pith-number/JPFRLKZ6US6DIU6V2K6TOUWIE5/graph.json","events_json":"https://pith.science/api/pith-number/JPFRLKZ6US6DIU6V2K6TOUWIE5/events.json","paper":"https://pith.science/paper/JPFRLKZ6"},"agent_actions":{"view_html":"https://pith.science/pith/JPFRLKZ6US6DIU6V2K6TOUWIE5","download_json":"https://pith.science/pith/JPFRLKZ6US6DIU6V2K6TOUWIE5.json","view_paper":"https://pith.science/paper/JPFRLKZ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.03649&json=true","fetch_graph":"https://pith.science/api/pith-number/JPFRLKZ6US6DIU6V2K6TOUWIE5/graph.json","fetch_events":"https://pith.science/api/pith-number/JPFRLKZ6US6DIU6V2K6TOUWIE5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JPFRLKZ6US6DIU6V2K6TOUWIE5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JPFRLKZ6US6DIU6V2K6TOUWIE5/action/storage_attestation","attest_author":"https://pith.science/pith/JPFRLKZ6US6DIU6V2K6TOUWIE5/action/author_attestation","sign_citation":"https://pith.science/pith/JPFRLKZ6US6DIU6V2K6TOUWIE5/action/citation_signature","submit_replication":"https://pith.science/pith/JPFRLKZ6US6DIU6V2K6TOUWIE5/action/replication_record"}},"created_at":"2026-05-18T00:01:14.566258+00:00","updated_at":"2026-05-18T00:01:14.566258+00:00"}