{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SNLLFWZHO6OEU2YHEZNIXQSRDA","short_pith_number":"pith:SNLLFWZH","canonical_record":{"source":{"id":"2605.10328","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-11T10:31:53Z","cross_cats_sorted":[],"title_canon_sha256":"8b28f1cf0c8f09ddde178cbc61f4e5207d45f781fd0e9a2d57dd9bd9da745e54","abstract_canon_sha256":"68406647a8d798eea679b65c0f1ba61071b8760fd32e256afd00f2c9b94a3545"},"schema_version":"1.0"},"canonical_sha256":"9356b2db27779c4a6b07265a8bc25118167eedd71a0c13f3c73f4510be488250","source":{"kind":"arxiv","id":"2605.10328","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.10328","created_at":"2026-06-03T01:05:51Z"},{"alias_kind":"arxiv_version","alias_value":"2605.10328v3","created_at":"2026-06-03T01:05:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.10328","created_at":"2026-06-03T01:05:51Z"},{"alias_kind":"pith_short_12","alias_value":"SNLLFWZHO6OE","created_at":"2026-06-03T01:05:51Z"},{"alias_kind":"pith_short_16","alias_value":"SNLLFWZHO6OEU2YH","created_at":"2026-06-03T01:05:51Z"},{"alias_kind":"pith_short_8","alias_value":"SNLLFWZH","created_at":"2026-06-03T01:05:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SNLLFWZHO6OEU2YHEZNIXQSRDA","target":"record","payload":{"canonical_record":{"source":{"id":"2605.10328","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-11T10:31:53Z","cross_cats_sorted":[],"title_canon_sha256":"8b28f1cf0c8f09ddde178cbc61f4e5207d45f781fd0e9a2d57dd9bd9da745e54","abstract_canon_sha256":"68406647a8d798eea679b65c0f1ba61071b8760fd32e256afd00f2c9b94a3545"},"schema_version":"1.0"},"canonical_sha256":"9356b2db27779c4a6b07265a8bc25118167eedd71a0c13f3c73f4510be488250","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:51.281406Z","signature_b64":"Bm6ie9NvjcxhRTjmli+1Dn5quqna2jzBcN2L4IR9ABm2LMCxP3IfgKIznLs4OdJyXia/LtR7LnZOlnSDQt0QBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9356b2db27779c4a6b07265a8bc25118167eedd71a0c13f3c73f4510be488250","last_reissued_at":"2026-06-03T01:05:51.280944Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:51.280944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.10328","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":"2026-06-03T01:05:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H6ZkaaQ4xsaJ3LgZLsjOsQ9hT+MwfBJ0uYhi6FEbAJKPmfY6r0YY6agJowpWH680+EmI3cMS/BQabbEGX9aJAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T03:34:52.876520Z"},"content_sha256":"9ac4bff28f514eea8cc151faad39caa765f2b08f06eb18d72af276ddb6bb92f6","schema_version":"1.0","event_id":"sha256:9ac4bff28f514eea8cc151faad39caa765f2b08f06eb18d72af276ddb6bb92f6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SNLLFWZHO6OEU2YHEZNIXQSRDA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ANCHOR: Abductive Network Construction with Hierarchical Orchestration for Reliable Probability Inference in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"ANCHOR builds dense hierarchical factor spaces from LLMs via iterative generation and clustering to support reliable Bayesian probability estimates.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guanran Luo, Jingqi Gao, Meihong Wang, Qingqiang Wu, Wentao Qiu, Zhongquan Jian","submitted_at":"2026-05-11T10:31:53Z","abstract_excerpt":"A central challenge in large-scale decision-making under incomplete information is estimating reliable probabilities. Recent approaches use Large Language Models (LLMs) to generate explanatory factors and coarse-grained probability estimates, which are then refined by a Na\\\"ive Bayes model over factor combinations. However, sparse factor spaces often yield ``unknown'' predictions, while expanding factors increases noise and spurious correlations, weakening conditional independence and degrading reliability. To address these limitations, we propose \\textsc{Anchor}, an aggregated Bayesian infere"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments show that ANCHOR markedly reduces ``unknown'' predictions and produces more reliable probability estimates than direct LLM baselines, achieving state-of-the-art performance while significantly reducing time and token overhead.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that iterative LLM generation plus clustering will reliably produce a hierarchical factor space that captures latent dependencies without introducing new noise or spurious correlations that degrade the causal Bayesian network.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ANCHOR constructs dense hierarchical factor spaces via LLM generation and clustering, then augments Naive Bayes with a causal Bayesian network to reduce unknown predictions and improve reliability of LLM-based probability estimates.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"ANCHOR builds dense hierarchical factor spaces from LLMs via iterative generation and clustering to support reliable Bayesian probability estimates.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"8e03b7baf41cd5112189190ac2845f23ac61f007097d05a2ebafd811a0e2bf4d"},"source":{"id":"2605.10328","kind":"arxiv","version":3},"verdict":{"id":"aa6242d3-231a-4d6e-9e66-a922bbba999c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T07:34:17.238471Z","strongest_claim":"Experiments show that ANCHOR markedly reduces ``unknown'' predictions and produces more reliable probability estimates than direct LLM baselines, achieving state-of-the-art performance while significantly reducing time and token overhead.","one_line_summary":"ANCHOR constructs dense hierarchical factor spaces via LLM generation and clustering, then augments Naive Bayes with a causal Bayesian network to reduce unknown predictions and improve reliability of LLM-based probability estimates.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that iterative LLM generation plus clustering will reliably produce a hierarchical factor space that captures latent dependencies without introducing new noise or spurious correlations that degrade the causal Bayesian network.","pith_extraction_headline":"ANCHOR builds dense hierarchical factor spaces from LLMs via iterative generation and clustering to support reliable Bayesian probability estimates."},"integrity":{"clean":false,"summary":{"advisory":2,"critical":1,"by_detector":{"doi_compliance":{"total":3,"advisory":2,"critical":1,"informational":0}},"informational":0},"endpoint":"/pith/2605.10328/integrity.json","findings":[{"note":"Identifier '10.1016/j.ijcce.2024.11' is syntactically valid but the DOI registry (doi.org) returned 404, and Crossref / OpenAlex / internal corpus also have no record. The cited work could not be located through any authoritative source.","detector":"doi_compliance","severity":"critical","ref_index":10,"audited_at":"2026-05-19T09:28:01.502751Z","detected_doi":"10.1016/j.ijcce.2024.11","finding_type":"unresolvable_identifier","verdict_class":"cross_source","detected_arxiv_id":null},{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.18653/v1/2024.emnlp-main.499.URL) was visible in the surrounding text but could not be confirmed against doi.org as printed.","detector":"doi_compliance","severity":"advisory","ref_index":13,"audited_at":"2026-05-19T09:28:01.502751Z","detected_doi":"10.18653/v1/2024.emnlp-main.499.URL","finding_type":"recoverable_identifier","verdict_class":"incontrovertible","detected_arxiv_id":null},{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.5555/2567709.2567725.URL) was visible in the surrounding text but could not be confirmed against doi.org as printed.","detector":"doi_compliance","severity":"advisory","ref_index":14,"audited_at":"2026-05-19T09:28:01.502751Z","detected_doi":"10.5555/2567709.2567725.URL","finding_type":"recoverable_identifier","verdict_class":"incontrovertible","detected_arxiv_id":null}],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T06:02:01.176640Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T15:35:51.175919Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T11:31:18.885170Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T09:28:01.502751Z","status":"completed","version":"1.0.0","findings_count":3}],"snapshot_sha256":"17d6ea332693556a8790839455ad4f394c0a6c8172b45ed50adc2276dca59f66"},"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":"aa6242d3-231a-4d6e-9e66-a922bbba999c"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-03T01:05:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zQXzxXyU7yYN7bnJM5zLv/Ip6gXEkP8QN5yNs8cbUyKue1BnIZcchXPLRfTkAxydoOYebEK/b1P5DBML6QqcCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T03:34:52.877110Z"},"content_sha256":"a1a47473649bb268d838e1a0b7250d4c45907c1fa2cf5dd60bcf9a11c1df69b9","schema_version":"1.0","event_id":"sha256:a1a47473649bb268d838e1a0b7250d4c45907c1fa2cf5dd60bcf9a11c1df69b9"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:SNLLFWZHO6OEU2YHEZNIXQSRDA","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.5555/2567709.2567725.URL) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Curran Associates Inc. Zaidi, N. A., Cerquides, J., Carman, M. J., and Webb, G. I. Alleviating naive bayes attribute independence assumption by attribute weighting.J. Mach. Learn. Res., 14(1):1947–1988, 2013. doi: 10.5555/2567709. 2567725. ","arxiv_id":"2605.10328","detector":"doi_compliance","evidence":{"ref_index":14,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"Curran Associates Inc. Zaidi, N. A., Cerquides, J., Carman, M. J., and Webb, G. I. Alleviating naive bayes attribute independence assumption by attribute weighting.J. Mach. Learn. Res., 14(1):1947–1988, 2013. doi: 10.5555/2567709. 2567725. ","reconstructed_doi":"10.5555/2567709.2567725.URL"},"severity":"advisory","ref_index":14,"audited_at":"2026-05-19T09:28:01.502751Z","event_type":"pith.integrity.v1","detected_doi":"10.5555/2567709.2567725.URL","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"031e722b8eb5e6d6496ee0ec22670751028b2fd7f8f8a3e5c1f409ad904db480","paper_version":2,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":628,"payload_sha256":"3de4f7cd2757c7458c20b8c20a30b154c358e53348cac79513e3b6286f697aa3","signature_b64":"VzMwyMrZuIMQuk+RESYsIV1mD5iAR5fcfL+dh7sRnVOYKKYjYnkVvt/32ojtYDaZ9nUGHkxp+OH5Tba4xfk3Ag==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-19T09:31:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JFqneXve1+eWs6rT+OIlqEe2sgjfaeT394818hZxbx0yzITe/d4CjsLX/zAk04oLG0xHBVbqA+BlKbHikvmNBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T03:34:52.878031Z"},"content_sha256":"aa38d7b66105ce661d904ada0b7d1e714c76cb0fa7ce3c420c3757ce5099f7b6","schema_version":"1.0","event_id":"sha256:aa38d7b66105ce661d904ada0b7d1e714c76cb0fa7ce3c420c3757ce5099f7b6"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:SNLLFWZHO6OEU2YHEZNIXQSRDA","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.18653/v1/2024.emnlp-main.499.URL) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"URL https://aclanthology.org/2022. emnlp-main.134/. Tang, L., Laban, P., and Durrett, G. MiniCheck: Efficient fact-checking of LLMs on grounding documents. pp. 8818–8847, November 2024. doi: 10.18653/v1/2024. emnlp-main.499. URL https://acl","arxiv_id":"2605.10328","detector":"doi_compliance","evidence":{"ref_index":13,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"URL https://aclanthology.org/2022. emnlp-main.134/. Tang, L., Laban, P., and Durrett, G. MiniCheck: Efficient fact-checking of LLMs on grounding documents. pp. 8818–8847, November 2024. doi: 10.18653/v1/2024. emnlp-main.499. URL https://acl","reconstructed_doi":"10.18653/v1/2024.emnlp-main.499.URL"},"severity":"advisory","ref_index":13,"audited_at":"2026-05-19T09:28:01.502751Z","event_type":"pith.integrity.v1","detected_doi":"10.18653/v1/2024.emnlp-main.499.URL","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"df874e57302d94507b0fe3081c583b463db7f2e286475a2e6d74685c93b6c0bc","paper_version":2,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":627,"payload_sha256":"06462212798cbc49e65d33648b39ee176d586e5db7f6a1cc617ccb5fcfb02779","signature_b64":"XAIqMvyQVHU6CpCzqHVd7vJFy11GdJ/3h4gPigBOnAHUjxTSMZNtK5SgYNX3JU05yJqwFJ3W3B9LNouv6LHcBA==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-19T09:31:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m2yoBiGBjBZIJ0FkvWfTyotYCX+qh7EePV88f+4EI0yzvEfhfH/idBPZj2G6xoTGHW0osBBYY47hi8gd+nGuCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T03:34:52.878339Z"},"content_sha256":"9af3c91654754945a6dd987d52db44216b928ead2e63d72f31b11b4b4270c3a2","schema_version":"1.0","event_id":"sha256:9af3c91654754945a6dd987d52db44216b928ead2e63d72f31b11b4b4270c3a2"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:SNLLFWZHO6OEU2YHEZNIXQSRDA","target":"integrity","payload":{"note":"Identifier '10.1016/j.ijcce.2024.11' is syntactically valid but the DOI registry (doi.org) returned 404, and Crossref / OpenAlex / internal corpus also have no record. The cited work could not be located through any authoritative source.","snippet":"doi: https://doi.org/10.1016/j.ijcce.2024.11","arxiv_id":"2605.10328","detector":"doi_compliance","evidence":{"doi":"10.1016/j.ijcce.2024.11","arxiv_id":null,"ref_index":10,"raw_excerpt":"doi: https://doi.org/10.1016/j.ijcce.2024.11","verdict_class":"cross_source","checked_sources":["crossref_by_doi","openalex_by_doi","doi_org_head"]},"severity":"critical","ref_index":10,"audited_at":"2026-05-19T09:28:01.502751Z","event_type":"pith.integrity.v1","detected_doi":"10.1016/j.ijcce.2024.11","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"unresolvable_identifier","evidence_hash":"17fbdbb52cc1c87bbe461675c6fd750c8334b1382e4291c14aaf9d44a090f850","paper_version":2,"verdict_class":"cross_source","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":626,"payload_sha256":"587a0335206708cae80920ac7a48687eca6ae91367487b2e3a45106224a3667b","signature_b64":"Pt7y3CsxJ4jFdp6k42w6DPiSBpoDU/lr4DKz/KhOVK6LQ4HRoXBK5bSedngCdJDCM9h9SOuXBL3u97V+P5fACQ==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-19T09:31:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u7hwX2tA4EfGuK6qFSYEru1G8SvOiwI9T64KDrLw56Rbl0tb53qpNqwuv+qqckv6g6iEPsNC8aWTq7ot0bUJDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T03:34:52.878625Z"},"content_sha256":"686b17fbbe7a71e630cd4dd045d4be051c633be62f4ef13d87c6a9a78d1d9aa2","schema_version":"1.0","event_id":"sha256:686b17fbbe7a71e630cd4dd045d4be051c633be62f4ef13d87c6a9a78d1d9aa2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SNLLFWZHO6OEU2YHEZNIXQSRDA/bundle.json","state_url":"https://pith.science/pith/SNLLFWZHO6OEU2YHEZNIXQSRDA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SNLLFWZHO6OEU2YHEZNIXQSRDA/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":"2026-06-03T03:34:52Z","links":{"resolver":"https://pith.science/pith/SNLLFWZHO6OEU2YHEZNIXQSRDA","bundle":"https://pith.science/pith/SNLLFWZHO6OEU2YHEZNIXQSRDA/bundle.json","state":"https://pith.science/pith/SNLLFWZHO6OEU2YHEZNIXQSRDA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SNLLFWZHO6OEU2YHEZNIXQSRDA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SNLLFWZHO6OEU2YHEZNIXQSRDA","merge_version":"pith-open-graph-merge-v1","event_count":5,"valid_event_count":5,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"68406647a8d798eea679b65c0f1ba61071b8760fd32e256afd00f2c9b94a3545","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-11T10:31:53Z","title_canon_sha256":"8b28f1cf0c8f09ddde178cbc61f4e5207d45f781fd0e9a2d57dd9bd9da745e54"},"schema_version":"1.0","source":{"id":"2605.10328","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.10328","created_at":"2026-06-03T01:05:51Z"},{"alias_kind":"arxiv_version","alias_value":"2605.10328v3","created_at":"2026-06-03T01:05:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.10328","created_at":"2026-06-03T01:05:51Z"},{"alias_kind":"pith_short_12","alias_value":"SNLLFWZHO6OE","created_at":"2026-06-03T01:05:51Z"},{"alias_kind":"pith_short_16","alias_value":"SNLLFWZHO6OEU2YH","created_at":"2026-06-03T01:05:51Z"},{"alias_kind":"pith_short_8","alias_value":"SNLLFWZH","created_at":"2026-06-03T01:05:51Z"}],"graph_snapshots":[{"event_id":"sha256:a1a47473649bb268d838e1a0b7250d4c45907c1fa2cf5dd60bcf9a11c1df69b9","target":"graph","created_at":"2026-06-03T01:05:51Z","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":"Experiments show that ANCHOR markedly reduces ``unknown'' predictions and produces more reliable probability estimates than direct LLM baselines, achieving state-of-the-art performance while significantly reducing time and token overhead."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that iterative LLM generation plus clustering will reliably produce a hierarchical factor space that captures latent dependencies without introducing new noise or spurious correlations that degrade the causal Bayesian network."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"ANCHOR constructs dense hierarchical factor spaces via LLM generation and clustering, then augments Naive Bayes with a causal Bayesian network to reduce unknown predictions and improve reliability of LLM-based probability estimates."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"ANCHOR builds dense hierarchical factor spaces from LLMs via iterative generation and clustering to support reliable Bayesian probability estimates."}],"snapshot_sha256":"8e03b7baf41cd5112189190ac2845f23ac61f007097d05a2ebafd811a0e2bf4d"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":false,"detectors_run":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T06:02:01.176640Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T15:35:51.175919Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T11:31:18.885170Z","status":"completed","version":"1.0.0"},{"findings_count":3,"name":"doi_compliance","ran_at":"2026-05-19T09:28:01.502751Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.10328/integrity.json","findings":[{"audited_at":"2026-05-19T09:28:01.502751Z","detected_arxiv_id":null,"detected_doi":"10.1016/j.ijcce.2024.11","detector":"doi_compliance","finding_type":"unresolvable_identifier","note":"Identifier '10.1016/j.ijcce.2024.11' is syntactically valid but the DOI registry (doi.org) returned 404, and Crossref / OpenAlex / internal corpus also have no record. The cited work could not be located through any authoritative source.","ref_index":10,"severity":"critical","verdict_class":"cross_source"},{"audited_at":"2026-05-19T09:28:01.502751Z","detected_arxiv_id":null,"detected_doi":"10.18653/v1/2024.emnlp-main.499.URL","detector":"doi_compliance","finding_type":"recoverable_identifier","note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.18653/v1/2024.emnlp-main.499.URL) was visible in the surrounding text but could not be confirmed against doi.org as printed.","ref_index":13,"severity":"advisory","verdict_class":"incontrovertible"},{"audited_at":"2026-05-19T09:28:01.502751Z","detected_arxiv_id":null,"detected_doi":"10.5555/2567709.2567725.URL","detector":"doi_compliance","finding_type":"recoverable_identifier","note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.5555/2567709.2567725.URL) was visible in the surrounding text but could not be confirmed against doi.org as printed.","ref_index":14,"severity":"advisory","verdict_class":"incontrovertible"}],"snapshot_sha256":"17d6ea332693556a8790839455ad4f394c0a6c8172b45ed50adc2276dca59f66","summary":{"advisory":2,"by_detector":{"doi_compliance":{"advisory":2,"critical":1,"informational":0,"total":3}},"critical":1,"informational":0}},"paper":{"abstract_excerpt":"A central challenge in large-scale decision-making under incomplete information is estimating reliable probabilities. Recent approaches use Large Language Models (LLMs) to generate explanatory factors and coarse-grained probability estimates, which are then refined by a Na\\\"ive Bayes model over factor combinations. However, sparse factor spaces often yield ``unknown'' predictions, while expanding factors increases noise and spurious correlations, weakening conditional independence and degrading reliability. To address these limitations, we propose \\textsc{Anchor}, an aggregated Bayesian infere","authors_text":"Guanran Luo, Jingqi Gao, Meihong Wang, Qingqiang Wu, Wentao Qiu, Zhongquan Jian","cross_cats":[],"headline":"ANCHOR builds dense hierarchical factor spaces from LLMs via iterative generation and clustering to support reliable Bayesian probability estimates.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-11T10:31:53Z","title":"ANCHOR: Abductive Network Construction with Hierarchical Orchestration for Reliable Probability Inference in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.10328","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-13T07:34:17.238471Z","id":"aa6242d3-231a-4d6e-9e66-a922bbba999c","model_set":{"reader":"grok-4.3"},"one_line_summary":"ANCHOR constructs dense hierarchical factor spaces via LLM generation and clustering, then augments Naive Bayes with a causal Bayesian network to reduce unknown predictions and improve reliability of LLM-based probability estimates.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"ANCHOR builds dense hierarchical factor spaces from LLMs via iterative generation and clustering to support reliable Bayesian probability estimates.","strongest_claim":"Experiments show that ANCHOR markedly reduces ``unknown'' predictions and produces more reliable probability estimates than direct LLM baselines, achieving state-of-the-art performance while significantly reducing time and token overhead.","weakest_assumption":"The assumption that iterative LLM generation plus clustering will reliably produce a hierarchical factor space that captures latent dependencies without introducing new noise or spurious correlations that degrade the causal Bayesian network."}},"verdict_id":"aa6242d3-231a-4d6e-9e66-a922bbba999c"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9ac4bff28f514eea8cc151faad39caa765f2b08f06eb18d72af276ddb6bb92f6","target":"record","created_at":"2026-06-03T01:05:51Z","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":"68406647a8d798eea679b65c0f1ba61071b8760fd32e256afd00f2c9b94a3545","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-11T10:31:53Z","title_canon_sha256":"8b28f1cf0c8f09ddde178cbc61f4e5207d45f781fd0e9a2d57dd9bd9da745e54"},"schema_version":"1.0","source":{"id":"2605.10328","kind":"arxiv","version":3}},"canonical_sha256":"9356b2db27779c4a6b07265a8bc25118167eedd71a0c13f3c73f4510be488250","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9356b2db27779c4a6b07265a8bc25118167eedd71a0c13f3c73f4510be488250","first_computed_at":"2026-06-03T01:05:51.280944Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:51.280944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Bm6ie9NvjcxhRTjmli+1Dn5quqna2jzBcN2L4IR9ABm2LMCxP3IfgKIznLs4OdJyXia/LtR7LnZOlnSDQt0QBQ==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:51.281406Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.10328","source_kind":"arxiv","source_version":3}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:686b17fbbe7a71e630cd4dd045d4be051c633be62f4ef13d87c6a9a78d1d9aa2","sha256:9af3c91654754945a6dd987d52db44216b928ead2e63d72f31b11b4b4270c3a2","sha256:aa38d7b66105ce661d904ada0b7d1e714c76cb0fa7ce3c420c3757ce5099f7b6"]}],"invalid_events":[],"applied_event_ids":["sha256:9ac4bff28f514eea8cc151faad39caa765f2b08f06eb18d72af276ddb6bb92f6","sha256:a1a47473649bb268d838e1a0b7250d4c45907c1fa2cf5dd60bcf9a11c1df69b9"],"state_sha256":"fdcc1594072a9d0d6c205b729f461e37a2e5b7707efc57d8fae6c7678b015883"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0HQXchx3DIN/2408HnHUA3wbPY/77M+4JDNoCRS6xHqD2XF6eDnLC7o/+342gvneIRKn3lEltlPCPETEX/QGDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T03:34:52.881519Z","bundle_sha256":"ca443f7a0e8b003c6220e80ae5c5a00982e05e98189efc55bba58ec36b364a39"}}