{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KLNR5TYDPFDYNLPZ3N4IQZ4U4S","short_pith_number":"pith:KLNR5TYD","schema_version":"1.0","canonical_sha256":"52db1ecf03794786adf9db78886794e4b570c5afe03bb9cadb1e774c0073e16b","source":{"kind":"arxiv","id":"2603.16091","version":3},"attestation_state":"computed","paper":{"title":"CounterRefine: Answer-Conditioned Counterevidence Retrieval for Inference-Time Knowledge Repair in Factual Question Answering","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"CounterRefine repairs factual answers at inference time by retrieving counterevidence to test and revise provisional responses.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Tianyi Huang, Ying Kai Deng","submitted_at":"2026-03-17T03:27:25Z","abstract_excerpt":"In factual question answering, many errors are not failures of access but failures of commitment: the system retrieves relevant evidence, yet still settles on the wrong answer. We present CounterRefine, a lightweight repair layer for short-form RAG that treats the first answer as a hypothesis to test. Given a draft, CounterRefine issues answer-conditioned expansion queries to retrieve candidate-specific evidence, then applies a constrained KEEP or REVISE refinement step whose proposed revisions are accepted only after deterministic validation. The design is intentionally narrow: it adds one ev"},"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":"2603.16091","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-17T03:27:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cfb90e4ee3ca9d53afefe8acda71ffa43af7d352fbb37ab3f3b5c150ca2daecb","abstract_canon_sha256":"82f5dcaa102d886402cef9f5bf379b150fd836d4f7e3291b30a1dcd89508eb5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:08.412784Z","signature_b64":"PKgyTjUsbmJOrOJtqWSFFqTC/RPfxDbT/gLcTe2UUK1o19RWw1lPBNNWb1jmlMUGc6ssOnqRSoSfEcwV6Wc8DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52db1ecf03794786adf9db78886794e4b570c5afe03bb9cadb1e774c0073e16b","last_reissued_at":"2026-05-20T00:03:08.411951Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:08.411951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CounterRefine: Answer-Conditioned Counterevidence Retrieval for Inference-Time Knowledge Repair in Factual Question Answering","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"CounterRefine repairs factual answers at inference time by retrieving counterevidence to test and revise provisional responses.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Tianyi Huang, Ying Kai Deng","submitted_at":"2026-03-17T03:27:25Z","abstract_excerpt":"In factual question answering, many errors are not failures of access but failures of commitment: the system retrieves relevant evidence, yet still settles on the wrong answer. We present CounterRefine, a lightweight repair layer for short-form RAG that treats the first answer as a hypothesis to test. Given a draft, CounterRefine issues answer-conditioned expansion queries to retrieve candidate-specific evidence, then applies a constrained KEEP or REVISE refinement step whose proposed revisions are accepted only after deterministic validation. The design is intentionally narrow: it adds one ev"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"On the full SimpleQA benchmark, CounterRefine improves a matched GPT-5 Baseline-RAG by 5.8 points and reaches a 73.1 percent correct rate, while exceeding the reported one-shot GPT-5.4 score by roughly 40 points.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the restricted refinement step with deterministic validation reliably distinguishes valid revisions from invalid ones across diverse factual questions without introducing new errors.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"CounterRefine improves factual QA by retrieving answer-conditioned counterevidence and deterministically refining draft answers, lifting a GPT-5 RAG baseline by 5.8 points to 73.1% on SimpleQA.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"CounterRefine repairs factual answers at inference time by retrieving counterevidence to test and revise provisional responses.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"1e19c41cf1dc3920a64b6e84b50a0baa39b93e0bd5633e6915f228cc2435f695"},"source":{"id":"2603.16091","kind":"arxiv","version":3},"verdict":{"id":"52c56e36-9719-4641-8649-f5d56d41495f","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T10:39:53.958425Z","strongest_claim":"On the full SimpleQA benchmark, CounterRefine improves a matched GPT-5 Baseline-RAG by 5.8 points and reaches a 73.1 percent correct rate, while exceeding the reported one-shot GPT-5.4 score by roughly 40 points.","one_line_summary":"CounterRefine improves factual QA by retrieving answer-conditioned counterevidence and deterministically refining draft answers, lifting a GPT-5 RAG baseline by 5.8 points to 73.1% on SimpleQA.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the restricted refinement step with deterministic validation reliably distinguishes valid revisions from invalid ones across diverse factual questions without introducing new errors.","pith_extraction_headline":"CounterRefine repairs factual answers at inference time by retrieving counterevidence to test and revise provisional responses."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.16091/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":"2603.16091","created_at":"2026-05-20T00:03:08.412080+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.16091v3","created_at":"2026-05-20T00:03:08.412080+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.16091","created_at":"2026-05-20T00:03:08.412080+00:00"},{"alias_kind":"pith_short_12","alias_value":"KLNR5TYDPFDY","created_at":"2026-05-20T00:03:08.412080+00:00"},{"alias_kind":"pith_short_16","alias_value":"KLNR5TYDPFDYNLPZ","created_at":"2026-05-20T00:03:08.412080+00:00"},{"alias_kind":"pith_short_8","alias_value":"KLNR5TYD","created_at":"2026-05-20T00:03:08.412080+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/KLNR5TYDPFDYNLPZ3N4IQZ4U4S","json":"https://pith.science/pith/KLNR5TYDPFDYNLPZ3N4IQZ4U4S.json","graph_json":"https://pith.science/api/pith-number/KLNR5TYDPFDYNLPZ3N4IQZ4U4S/graph.json","events_json":"https://pith.science/api/pith-number/KLNR5TYDPFDYNLPZ3N4IQZ4U4S/events.json","paper":"https://pith.science/paper/KLNR5TYD"},"agent_actions":{"view_html":"https://pith.science/pith/KLNR5TYDPFDYNLPZ3N4IQZ4U4S","download_json":"https://pith.science/pith/KLNR5TYDPFDYNLPZ3N4IQZ4U4S.json","view_paper":"https://pith.science/paper/KLNR5TYD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.16091&json=true","fetch_graph":"https://pith.science/api/pith-number/KLNR5TYDPFDYNLPZ3N4IQZ4U4S/graph.json","fetch_events":"https://pith.science/api/pith-number/KLNR5TYDPFDYNLPZ3N4IQZ4U4S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KLNR5TYDPFDYNLPZ3N4IQZ4U4S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KLNR5TYDPFDYNLPZ3N4IQZ4U4S/action/storage_attestation","attest_author":"https://pith.science/pith/KLNR5TYDPFDYNLPZ3N4IQZ4U4S/action/author_attestation","sign_citation":"https://pith.science/pith/KLNR5TYDPFDYNLPZ3N4IQZ4U4S/action/citation_signature","submit_replication":"https://pith.science/pith/KLNR5TYDPFDYNLPZ3N4IQZ4U4S/action/replication_record"}},"created_at":"2026-05-20T00:03:08.412080+00:00","updated_at":"2026-05-20T00:03:08.412080+00:00"}