{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:KLNR5TYDPFDYNLPZ3N4IQZ4U4S","short_pith_number":"pith:KLNR5TYD","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"},"canonical_sha256":"52db1ecf03794786adf9db78886794e4b570c5afe03bb9cadb1e774c0073e16b","source":{"kind":"arxiv","id":"2603.16091","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.16091","created_at":"2026-05-20T00:03:08Z"},{"alias_kind":"arxiv_version","alias_value":"2603.16091v3","created_at":"2026-05-20T00:03:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.16091","created_at":"2026-05-20T00:03:08Z"},{"alias_kind":"pith_short_12","alias_value":"KLNR5TYDPFDY","created_at":"2026-05-20T00:03:08Z"},{"alias_kind":"pith_short_16","alias_value":"KLNR5TYDPFDYNLPZ","created_at":"2026-05-20T00:03:08Z"},{"alias_kind":"pith_short_8","alias_value":"KLNR5TYD","created_at":"2026-05-20T00:03:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:KLNR5TYDPFDYNLPZ3N4IQZ4U4S","target":"record","payload":{"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"},"canonical_sha256":"52db1ecf03794786adf9db78886794e4b570c5afe03bb9cadb1e774c0073e16b","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"},"source_kind":"arxiv","source_id":"2603.16091","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:03:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LUjdtuHBDP9fAitgZMfDdnLpi3jAjBwlQYAScSqBKK3BICDctqQhLFM1Da5UjG5t4DggtihWv0d7FAQoxln9Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T16:39:34.747750Z"},"content_sha256":"6fc484e3c5d4115ab90e278fa1f1190c0ad9c767a14f9d60af380be807d990e2","schema_version":"1.0","event_id":"sha256:6fc484e3c5d4115ab90e278fa1f1190c0ad9c767a14f9d60af380be807d990e2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:KLNR5TYDPFDYNLPZ3N4IQZ4U4S","target":"graph","payload":{"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"},"verdict_id":"52c56e36-9719-4641-8649-f5d56d41495f"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:03:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6py0YzuSskPqSgRTlmr69cR9UTKzcbtnwkANhrPHezu4XI/4+8kIeZLCHoANSyZxw3x0g+v2EQMzH6rxb8FcBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T16:39:34.748702Z"},"content_sha256":"585009bd3128701ca3985525e0e382a1b42f43a4c99a0b94e3dbbd4be6ed515b","schema_version":"1.0","event_id":"sha256:585009bd3128701ca3985525e0e382a1b42f43a4c99a0b94e3dbbd4be6ed515b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KLNR5TYDPFDYNLPZ3N4IQZ4U4S/bundle.json","state_url":"https://pith.science/pith/KLNR5TYDPFDYNLPZ3N4IQZ4U4S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KLNR5TYDPFDYNLPZ3N4IQZ4U4S/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-08T16:39:34Z","links":{"resolver":"https://pith.science/pith/KLNR5TYDPFDYNLPZ3N4IQZ4U4S","bundle":"https://pith.science/pith/KLNR5TYDPFDYNLPZ3N4IQZ4U4S/bundle.json","state":"https://pith.science/pith/KLNR5TYDPFDYNLPZ3N4IQZ4U4S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KLNR5TYDPFDYNLPZ3N4IQZ4U4S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KLNR5TYDPFDYNLPZ3N4IQZ4U4S","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"82f5dcaa102d886402cef9f5bf379b150fd836d4f7e3291b30a1dcd89508eb5e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-17T03:27:25Z","title_canon_sha256":"cfb90e4ee3ca9d53afefe8acda71ffa43af7d352fbb37ab3f3b5c150ca2daecb"},"schema_version":"1.0","source":{"id":"2603.16091","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.16091","created_at":"2026-05-20T00:03:08Z"},{"alias_kind":"arxiv_version","alias_value":"2603.16091v3","created_at":"2026-05-20T00:03:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.16091","created_at":"2026-05-20T00:03:08Z"},{"alias_kind":"pith_short_12","alias_value":"KLNR5TYDPFDY","created_at":"2026-05-20T00:03:08Z"},{"alias_kind":"pith_short_16","alias_value":"KLNR5TYDPFDYNLPZ","created_at":"2026-05-20T00:03:08Z"},{"alias_kind":"pith_short_8","alias_value":"KLNR5TYD","created_at":"2026-05-20T00:03:08Z"}],"graph_snapshots":[{"event_id":"sha256:585009bd3128701ca3985525e0e382a1b42f43a4c99a0b94e3dbbd4be6ed515b","target":"graph","created_at":"2026-05-20T00:03:08Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the restricted refinement step with deterministic validation reliably distinguishes valid revisions from invalid ones across diverse factual questions without introducing new errors."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"CounterRefine repairs factual answers at inference time by retrieving counterevidence to test and revise provisional responses."}],"snapshot_sha256":"1e19c41cf1dc3920a64b6e84b50a0baa39b93e0bd5633e6915f228cc2435f695"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2603.16091/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Tianyi Huang, Ying Kai Deng","cross_cats":["cs.AI"],"headline":"CounterRefine repairs factual answers at inference time by retrieving counterevidence to test and revise provisional responses.","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-17T03:27:25Z","title":"CounterRefine: Answer-Conditioned Counterevidence Retrieval for Inference-Time Knowledge Repair in Factual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.16091","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-15T10:39:53.958425Z","id":"52c56e36-9719-4641-8649-f5d56d41495f","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"CounterRefine repairs factual answers at inference time by retrieving counterevidence to test and revise provisional responses.","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.","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."}},"verdict_id":"52c56e36-9719-4641-8649-f5d56d41495f"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6fc484e3c5d4115ab90e278fa1f1190c0ad9c767a14f9d60af380be807d990e2","target":"record","created_at":"2026-05-20T00:03:08Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"82f5dcaa102d886402cef9f5bf379b150fd836d4f7e3291b30a1dcd89508eb5e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-17T03:27:25Z","title_canon_sha256":"cfb90e4ee3ca9d53afefe8acda71ffa43af7d352fbb37ab3f3b5c150ca2daecb"},"schema_version":"1.0","source":{"id":"2603.16091","kind":"arxiv","version":3}},"canonical_sha256":"52db1ecf03794786adf9db78886794e4b570c5afe03bb9cadb1e774c0073e16b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"52db1ecf03794786adf9db78886794e4b570c5afe03bb9cadb1e774c0073e16b","first_computed_at":"2026-05-20T00:03:08.411951Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:08.411951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PKgyTjUsbmJOrOJtqWSFFqTC/RPfxDbT/gLcTe2UUK1o19RWw1lPBNNWb1jmlMUGc6ssOnqRSoSfEcwV6Wc8DA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:08.412784Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.16091","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6fc484e3c5d4115ab90e278fa1f1190c0ad9c767a14f9d60af380be807d990e2","sha256:585009bd3128701ca3985525e0e382a1b42f43a4c99a0b94e3dbbd4be6ed515b"],"state_sha256":"fdd5a9fb43b37ef4c0a34deb954dbef1911890bfa7892e4fe5068618a3d959bc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qt7VllCMfHbyAlGg2uTvGJqjvEKCZHJ+XN11U2qCZRIcrtpqj6niJHU5KKJ5plPAAWcNFnJI3tE0FItg41r6DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T16:39:34.753357Z","bundle_sha256":"f104a3a07e1331ec54e8d0ad2a64500ee1afe20fbe45748440fd4f7b971fc135"}}