{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CQJTZ5IQ2ECJBL5ZV6JUWKK7SN","short_pith_number":"pith:CQJTZ5IQ","schema_version":"1.0","canonical_sha256":"14133cf510d10490afb9af934b295f935acc10f10c538017d57a7373e93e4ae5","source":{"kind":"arxiv","id":"2606.08831","version":1},"attestation_state":"computed","paper":{"title":"Inference-Time Conformal Reasoning with Valid Factuality Control for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Huan Zhang, Ting Wang, Yan Yan, Yuanjie Shi","submitted_at":"2026-06-07T20:52:10Z","abstract_excerpt":"Large language models (LLMs) increasingly perform multi-step reasoning, where intermediate claims form implicit directed acyclic graphs whose node correctness is structurally conditioned on their ancestors. This makes factuality uncertainty structural, rather than a trivial accumulation of node-wise errors, and necessitates inference-time uncertainty quantification over the reasoning structure. While conformal prediction (CP) offers flexible user-specified factuality control, existing work remains post-hoc and cannot intervene during generation. To fill the gap between CP's flexibility and its"},"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":"2606.08831","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-07T20:52:10Z","cross_cats_sorted":[],"title_canon_sha256":"9f89bb18db57369c54e28639f339289d8d3f4e62aa076db35f53c2fd41e474ae","abstract_canon_sha256":"f4172ed2364a495f16567daf0fc7352123e70168a6e0976f06a76b4239afc935"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:07:41.951469Z","signature_b64":"YXyyQrTMF7vIQUpLcDY4SY9o9hDItlutEo+9/CcocU8ynDDBMxrN/Dq7HsfT4JksGsq5yjprP/N2jdvLFAHKBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14133cf510d10490afb9af934b295f935acc10f10c538017d57a7373e93e4ae5","last_reissued_at":"2026-06-09T02:07:41.950571Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:07:41.950571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inference-Time Conformal Reasoning with Valid Factuality Control for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Huan Zhang, Ting Wang, Yan Yan, Yuanjie Shi","submitted_at":"2026-06-07T20:52:10Z","abstract_excerpt":"Large language models (LLMs) increasingly perform multi-step reasoning, where intermediate claims form implicit directed acyclic graphs whose node correctness is structurally conditioned on their ancestors. This makes factuality uncertainty structural, rather than a trivial accumulation of node-wise errors, and necessitates inference-time uncertainty quantification over the reasoning structure. While conformal prediction (CP) offers flexible user-specified factuality control, existing work remains post-hoc and cannot intervene during generation. To fill the gap between CP's flexibility and its"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08831","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/2606.08831/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":"2606.08831","created_at":"2026-06-09T02:07:41.950692+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.08831v1","created_at":"2026-06-09T02:07:41.950692+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08831","created_at":"2026-06-09T02:07:41.950692+00:00"},{"alias_kind":"pith_short_12","alias_value":"CQJTZ5IQ2ECJ","created_at":"2026-06-09T02:07:41.950692+00:00"},{"alias_kind":"pith_short_16","alias_value":"CQJTZ5IQ2ECJBL5Z","created_at":"2026-06-09T02:07:41.950692+00:00"},{"alias_kind":"pith_short_8","alias_value":"CQJTZ5IQ","created_at":"2026-06-09T02:07:41.950692+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/CQJTZ5IQ2ECJBL5ZV6JUWKK7SN","json":"https://pith.science/pith/CQJTZ5IQ2ECJBL5ZV6JUWKK7SN.json","graph_json":"https://pith.science/api/pith-number/CQJTZ5IQ2ECJBL5ZV6JUWKK7SN/graph.json","events_json":"https://pith.science/api/pith-number/CQJTZ5IQ2ECJBL5ZV6JUWKK7SN/events.json","paper":"https://pith.science/paper/CQJTZ5IQ"},"agent_actions":{"view_html":"https://pith.science/pith/CQJTZ5IQ2ECJBL5ZV6JUWKK7SN","download_json":"https://pith.science/pith/CQJTZ5IQ2ECJBL5ZV6JUWKK7SN.json","view_paper":"https://pith.science/paper/CQJTZ5IQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.08831&json=true","fetch_graph":"https://pith.science/api/pith-number/CQJTZ5IQ2ECJBL5ZV6JUWKK7SN/graph.json","fetch_events":"https://pith.science/api/pith-number/CQJTZ5IQ2ECJBL5ZV6JUWKK7SN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CQJTZ5IQ2ECJBL5ZV6JUWKK7SN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CQJTZ5IQ2ECJBL5ZV6JUWKK7SN/action/storage_attestation","attest_author":"https://pith.science/pith/CQJTZ5IQ2ECJBL5ZV6JUWKK7SN/action/author_attestation","sign_citation":"https://pith.science/pith/CQJTZ5IQ2ECJBL5ZV6JUWKK7SN/action/citation_signature","submit_replication":"https://pith.science/pith/CQJTZ5IQ2ECJBL5ZV6JUWKK7SN/action/replication_record"}},"created_at":"2026-06-09T02:07:41.950692+00:00","updated_at":"2026-06-09T02:07:41.950692+00:00"}