{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KHFV77GENXO6L7FS3NZXM6XQG2","short_pith_number":"pith:KHFV77GE","schema_version":"1.0","canonical_sha256":"51cb5ffcc46ddde5fcb2db73767af036955477460869cbdb439d98f03da4ffdc","source":{"kind":"arxiv","id":"2203.05081","version":1},"attestation_state":"computed","paper":{"title":"NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Fawaz Sammani, Nikos Deligiannis, Tanmoy Mukherjee","submitted_at":"2022-03-09T22:57:15Z","abstract_excerpt":"Natural language explanation (NLE) models aim at explaining the decision-making process of a black box system via generating natural language sentences which are human-friendly, high-level and fine-grained. Current NLE models explain the decision-making process of a vision or vision-language model (a.k.a., task model), e.g., a VQA model, via a language model (a.k.a., explanation model), e.g., GPT. Other than the additional memory resources and inference time required by the task model, the task and explanation models are completely independent, which disassociates the explanation from the reas"},"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":"2203.05081","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-09T22:57:15Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c680724a1635cd848d11fc0322eca11e31918d910ca38194323d87a131c0e933","abstract_canon_sha256":"2e350d4bb433f216913bef99ea91cc48c0066d2f3ec83a836363832e4d35e622"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:03:29.577117Z","signature_b64":"IEZ331cSYAoTAGcKpkPmFFQsFfeSsmlzXfi5UB6d7BMPHH8PIrvH1HfyB5beb67bABqkfGyyTd7pVAhGzW5IAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51cb5ffcc46ddde5fcb2db73767af036955477460869cbdb439d98f03da4ffdc","last_reissued_at":"2026-07-05T04:03:29.576648Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:03:29.576648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Fawaz Sammani, Nikos Deligiannis, Tanmoy Mukherjee","submitted_at":"2022-03-09T22:57:15Z","abstract_excerpt":"Natural language explanation (NLE) models aim at explaining the decision-making process of a black box system via generating natural language sentences which are human-friendly, high-level and fine-grained. Current NLE models explain the decision-making process of a vision or vision-language model (a.k.a., task model), e.g., a VQA model, via a language model (a.k.a., explanation model), e.g., GPT. Other than the additional memory resources and inference time required by the task model, the task and explanation models are completely independent, which disassociates the explanation from the reas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.05081","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/2203.05081/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":"2203.05081","created_at":"2026-07-05T04:03:29.576699+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.05081v1","created_at":"2026-07-05T04:03:29.576699+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.05081","created_at":"2026-07-05T04:03:29.576699+00:00"},{"alias_kind":"pith_short_12","alias_value":"KHFV77GENXO6","created_at":"2026-07-05T04:03:29.576699+00:00"},{"alias_kind":"pith_short_16","alias_value":"KHFV77GENXO6L7FS","created_at":"2026-07-05T04:03:29.576699+00:00"},{"alias_kind":"pith_short_8","alias_value":"KHFV77GE","created_at":"2026-07-05T04:03:29.576699+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/KHFV77GENXO6L7FS3NZXM6XQG2","json":"https://pith.science/pith/KHFV77GENXO6L7FS3NZXM6XQG2.json","graph_json":"https://pith.science/api/pith-number/KHFV77GENXO6L7FS3NZXM6XQG2/graph.json","events_json":"https://pith.science/api/pith-number/KHFV77GENXO6L7FS3NZXM6XQG2/events.json","paper":"https://pith.science/paper/KHFV77GE"},"agent_actions":{"view_html":"https://pith.science/pith/KHFV77GENXO6L7FS3NZXM6XQG2","download_json":"https://pith.science/pith/KHFV77GENXO6L7FS3NZXM6XQG2.json","view_paper":"https://pith.science/paper/KHFV77GE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.05081&json=true","fetch_graph":"https://pith.science/api/pith-number/KHFV77GENXO6L7FS3NZXM6XQG2/graph.json","fetch_events":"https://pith.science/api/pith-number/KHFV77GENXO6L7FS3NZXM6XQG2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KHFV77GENXO6L7FS3NZXM6XQG2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KHFV77GENXO6L7FS3NZXM6XQG2/action/storage_attestation","attest_author":"https://pith.science/pith/KHFV77GENXO6L7FS3NZXM6XQG2/action/author_attestation","sign_citation":"https://pith.science/pith/KHFV77GENXO6L7FS3NZXM6XQG2/action/citation_signature","submit_replication":"https://pith.science/pith/KHFV77GENXO6L7FS3NZXM6XQG2/action/replication_record"}},"created_at":"2026-07-05T04:03:29.576699+00:00","updated_at":"2026-07-05T04:03:29.576699+00:00"}