{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:UPXHNJ2BFLKXY474OHQ34YSDFT","short_pith_number":"pith:UPXHNJ2B","schema_version":"1.0","canonical_sha256":"a3ee76a7412ad57c73fc71e1be62432cf40381deea0c50ab74982943d5650d96","source":{"kind":"arxiv","id":"2012.11014","version":1},"attestation_state":"computed","paper":{"title":"KRISP: Integrating Implicit and Symbolic Knowledge for Open-Domain Knowledge-Based VQA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Abhinav Gupta, Devi Parikh, Kenneth Marino, Marcus Rohrbach, Xinlei Chen","submitted_at":"2020-12-20T20:13:02Z","abstract_excerpt":"One of the most challenging question types in VQA is when answering the question requires outside knowledge not present in the image. In this work we study open-domain knowledge, the setting when the knowledge required to answer a question is not given/annotated, neither at training nor test time. We tap into two types of knowledge representations and reasoning. First, implicit knowledge which can be learned effectively from unsupervised language pre-training and supervised training data with transformer-based models. Second, explicit, symbolic knowledge encoded in knowledge bases. Our approac"},"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":"2012.11014","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-12-20T20:13:02Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"598cda13f1373a8ac28c61a57504241896b21cb56ad4648b19500a88614b856a","abstract_canon_sha256":"0ff3493f0a460cfdd2c0df52a153e771fb377da5db9158299d93ed60793bd028"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:00:57.751296Z","signature_b64":"XuupNFFe+DeMHj3KNnab0hVlJ59t5UwqMC4+FEaXarI63xnin2CvSztu2iZr/D551zjhDpUFXes9hcAd3HvDCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3ee76a7412ad57c73fc71e1be62432cf40381deea0c50ab74982943d5650d96","last_reissued_at":"2026-07-05T02:00:57.750883Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:00:57.750883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KRISP: Integrating Implicit and Symbolic Knowledge for Open-Domain Knowledge-Based VQA","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Abhinav Gupta, Devi Parikh, Kenneth Marino, Marcus Rohrbach, Xinlei Chen","submitted_at":"2020-12-20T20:13:02Z","abstract_excerpt":"One of the most challenging question types in VQA is when answering the question requires outside knowledge not present in the image. In this work we study open-domain knowledge, the setting when the knowledge required to answer a question is not given/annotated, neither at training nor test time. We tap into two types of knowledge representations and reasoning. First, implicit knowledge which can be learned effectively from unsupervised language pre-training and supervised training data with transformer-based models. Second, explicit, symbolic knowledge encoded in knowledge bases. Our approac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.11014","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/2012.11014/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":"2012.11014","created_at":"2026-07-05T02:00:57.750938+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.11014v1","created_at":"2026-07-05T02:00:57.750938+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.11014","created_at":"2026-07-05T02:00:57.750938+00:00"},{"alias_kind":"pith_short_12","alias_value":"UPXHNJ2BFLKX","created_at":"2026-07-05T02:00:57.750938+00:00"},{"alias_kind":"pith_short_16","alias_value":"UPXHNJ2BFLKXY474","created_at":"2026-07-05T02:00:57.750938+00:00"},{"alias_kind":"pith_short_8","alias_value":"UPXHNJ2B","created_at":"2026-07-05T02:00:57.750938+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.20402","citing_title":"SoftReason: A Fully Differentiable Neuro-Soft-Symbolic Deductive Reasoning Architecture over High-Dimensional Perceptual Data","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UPXHNJ2BFLKXY474OHQ34YSDFT","json":"https://pith.science/pith/UPXHNJ2BFLKXY474OHQ34YSDFT.json","graph_json":"https://pith.science/api/pith-number/UPXHNJ2BFLKXY474OHQ34YSDFT/graph.json","events_json":"https://pith.science/api/pith-number/UPXHNJ2BFLKXY474OHQ34YSDFT/events.json","paper":"https://pith.science/paper/UPXHNJ2B"},"agent_actions":{"view_html":"https://pith.science/pith/UPXHNJ2BFLKXY474OHQ34YSDFT","download_json":"https://pith.science/pith/UPXHNJ2BFLKXY474OHQ34YSDFT.json","view_paper":"https://pith.science/paper/UPXHNJ2B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.11014&json=true","fetch_graph":"https://pith.science/api/pith-number/UPXHNJ2BFLKXY474OHQ34YSDFT/graph.json","fetch_events":"https://pith.science/api/pith-number/UPXHNJ2BFLKXY474OHQ34YSDFT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UPXHNJ2BFLKXY474OHQ34YSDFT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UPXHNJ2BFLKXY474OHQ34YSDFT/action/storage_attestation","attest_author":"https://pith.science/pith/UPXHNJ2BFLKXY474OHQ34YSDFT/action/author_attestation","sign_citation":"https://pith.science/pith/UPXHNJ2BFLKXY474OHQ34YSDFT/action/citation_signature","submit_replication":"https://pith.science/pith/UPXHNJ2BFLKXY474OHQ34YSDFT/action/replication_record"}},"created_at":"2026-07-05T02:00:57.750938+00:00","updated_at":"2026-07-05T02:00:57.750938+00:00"}