{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EMMDOIDNBPM4ADGUEB2TTBKWNU","short_pith_number":"pith:EMMDOIDN","schema_version":"1.0","canonical_sha256":"231837206d0bd9c00cd420753985566d0af06f571a12f8d468e4668f10aca8aa","source":{"kind":"arxiv","id":"2606.29150","version":1},"attestation_state":"computed","paper":{"title":"Flow Reasoning Models: Scaling Reasoning Through Iterative Self-Refinement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alec Helbling, Andrey Bryutkin, Hendrik Strobelt, Mauro Martino, Nima Dehmamy","submitted_at":"2026-06-28T02:10:36Z","abstract_excerpt":"Discrete flow models have recently shown promising performance on few-step text generation; however, when naively applied to structured reasoning tasks such as Sudoku and Zebra puzzles, they converge confidently to incorrect answers (solving only $\\sim$36% of Sudoku puzzles). We introduce Flow Reasoning Models (FRMs), a training and test-time-scaling framework for structured reasoning with flow models. We make the observation that, despite their poor solve rate, flow models can act as their own verifiers. A correct answer is a stable fixed point of the denoising dynamics, returning to itself w"},"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":"2606.29150","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-28T02:10:36Z","cross_cats_sorted":[],"title_canon_sha256":"4ce8a38fc7a12cb149cb47ceea3a59a90e7df4e76c1c7ae0dd06e56dcec4b480","abstract_canon_sha256":"71fde3ed82a8eb1da0a93fa1a3ab1d0323401f7d00552e539f066605d363748a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:54.731662Z","signature_b64":"qy3IXfjDgDyGpgriP5lm0Hyw3HuX8+MNR2287cBiu/S+e9+dZ9GISKhwVquxckx13vMZBXkRWopeOGpXUgvUAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"231837206d0bd9c00cd420753985566d0af06f571a12f8d468e4668f10aca8aa","last_reissued_at":"2026-06-30T01:17:54.731134Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:54.731134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Flow Reasoning Models: Scaling Reasoning Through Iterative Self-Refinement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alec Helbling, Andrey Bryutkin, Hendrik Strobelt, Mauro Martino, Nima Dehmamy","submitted_at":"2026-06-28T02:10:36Z","abstract_excerpt":"Discrete flow models have recently shown promising performance on few-step text generation; however, when naively applied to structured reasoning tasks such as Sudoku and Zebra puzzles, they converge confidently to incorrect answers (solving only $\\sim$36% of Sudoku puzzles). We introduce Flow Reasoning Models (FRMs), a training and test-time-scaling framework for structured reasoning with flow models. We make the observation that, despite their poor solve rate, flow models can act as their own verifiers. A correct answer is a stable fixed point of the denoising dynamics, returning to itself w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29150","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/2606.29150/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":"2606.29150","created_at":"2026-06-30T01:17:54.731209+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29150v1","created_at":"2026-06-30T01:17:54.731209+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29150","created_at":"2026-06-30T01:17:54.731209+00:00"},{"alias_kind":"pith_short_12","alias_value":"EMMDOIDNBPM4","created_at":"2026-06-30T01:17:54.731209+00:00"},{"alias_kind":"pith_short_16","alias_value":"EMMDOIDNBPM4ADGU","created_at":"2026-06-30T01:17:54.731209+00:00"},{"alias_kind":"pith_short_8","alias_value":"EMMDOIDN","created_at":"2026-06-30T01:17:54.731209+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/EMMDOIDNBPM4ADGUEB2TTBKWNU","json":"https://pith.science/pith/EMMDOIDNBPM4ADGUEB2TTBKWNU.json","graph_json":"https://pith.science/api/pith-number/EMMDOIDNBPM4ADGUEB2TTBKWNU/graph.json","events_json":"https://pith.science/api/pith-number/EMMDOIDNBPM4ADGUEB2TTBKWNU/events.json","paper":"https://pith.science/paper/EMMDOIDN"},"agent_actions":{"view_html":"https://pith.science/pith/EMMDOIDNBPM4ADGUEB2TTBKWNU","download_json":"https://pith.science/pith/EMMDOIDNBPM4ADGUEB2TTBKWNU.json","view_paper":"https://pith.science/paper/EMMDOIDN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29150&json=true","fetch_graph":"https://pith.science/api/pith-number/EMMDOIDNBPM4ADGUEB2TTBKWNU/graph.json","fetch_events":"https://pith.science/api/pith-number/EMMDOIDNBPM4ADGUEB2TTBKWNU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EMMDOIDNBPM4ADGUEB2TTBKWNU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EMMDOIDNBPM4ADGUEB2TTBKWNU/action/storage_attestation","attest_author":"https://pith.science/pith/EMMDOIDNBPM4ADGUEB2TTBKWNU/action/author_attestation","sign_citation":"https://pith.science/pith/EMMDOIDNBPM4ADGUEB2TTBKWNU/action/citation_signature","submit_replication":"https://pith.science/pith/EMMDOIDNBPM4ADGUEB2TTBKWNU/action/replication_record"}},"created_at":"2026-06-30T01:17:54.731209+00:00","updated_at":"2026-06-30T01:17:54.731209+00:00"}