{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IZGHA42XP3IFN3DPL4YWVK2JF5","short_pith_number":"pith:IZGHA42X","schema_version":"1.0","canonical_sha256":"464c7073577ed056ec6f5f316aab492f7db7bf32d3e5a761679a08a826e69dea","source":{"kind":"arxiv","id":"2507.16331","version":4},"attestation_state":"computed","paper":{"title":"Re:Form -- Reducing Human Annotations in Scalable Formal Software Verification with RL in LLMs: A Preliminary Study on Dafny","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Binhang Yuan, Bowen Zhou, Chenghua Lin, Chuanhao Yan, Fengdi Che, Hang Zhao, Jie Fu, Jingzhe Shi, Xingwei Qu, Xin Li, Xuhan Huang, Xu Xu, Yaodong Yang, Yizhi Li, Yu Qiao","submitted_at":"2025-07-22T08:13:01Z","abstract_excerpt":"Existing informal language-based (e.g., human language) Large Language Models (LLMs) trained with Reinforcement Learning (RL) face a significant challenge: their verification processes, which provide crucial training signals, are neither reliable nor scalable. In fact, the prevalent large proprietary models could hardly generate verifiable programs. A promising yet largely uncharted alternative is formal language-based reasoning. Grounding LLMs in rigorous formal systems where generative models operate in formal language spaces (e.g., Dafny) enables the automatic and mathematically provable ve"},"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":"2507.16331","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-22T08:13:01Z","cross_cats_sorted":[],"title_canon_sha256":"57e1334a5d3dc05dd944e3894b016b43bb81f27c9698335d65da685242cce007","abstract_canon_sha256":"788fdca67adbc296622d4c726bbe5b98e7260fca5baa5905f07ad7cd740a5637"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T01:15:56.505741Z","signature_b64":"duoMTmxgPFsJz8osyey2Zc/D7T7vCXfkIPwpEN1mu3z+6RDu2S/RNkQG+7Rj4MDnD8EA4ewv9j4lHM1rg1UcBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"464c7073577ed056ec6f5f316aab492f7db7bf32d3e5a761679a08a826e69dea","last_reissued_at":"2026-07-07T01:15:56.504212Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T01:15:56.504212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Re:Form -- Reducing Human Annotations in Scalable Formal Software Verification with RL in LLMs: A Preliminary Study on Dafny","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Binhang Yuan, Bowen Zhou, Chenghua Lin, Chuanhao Yan, Fengdi Che, Hang Zhao, Jie Fu, Jingzhe Shi, Xingwei Qu, Xin Li, Xuhan Huang, Xu Xu, Yaodong Yang, Yizhi Li, Yu Qiao","submitted_at":"2025-07-22T08:13:01Z","abstract_excerpt":"Existing informal language-based (e.g., human language) Large Language Models (LLMs) trained with Reinforcement Learning (RL) face a significant challenge: their verification processes, which provide crucial training signals, are neither reliable nor scalable. In fact, the prevalent large proprietary models could hardly generate verifiable programs. A promising yet largely uncharted alternative is formal language-based reasoning. Grounding LLMs in rigorous formal systems where generative models operate in formal language spaces (e.g., Dafny) enables the automatic and mathematically provable ve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.16331","kind":"arxiv","version":4},"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/2507.16331/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":"2507.16331","created_at":"2026-07-07T01:15:56.504901+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.16331v4","created_at":"2026-07-07T01:15:56.504901+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.16331","created_at":"2026-07-07T01:15:56.504901+00:00"},{"alias_kind":"pith_short_12","alias_value":"IZGHA42XP3IF","created_at":"2026-07-07T01:15:56.504901+00:00"},{"alias_kind":"pith_short_16","alias_value":"IZGHA42XP3IFN3DP","created_at":"2026-07-07T01:15:56.504901+00:00"},{"alias_kind":"pith_short_8","alias_value":"IZGHA42X","created_at":"2026-07-07T01:15:56.504901+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":6,"sample":[{"citing_arxiv_id":"2605.30914","citing_title":"Automating Formal Verification with Reinforcement Learning and Recursive Inference","ref_index":104,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27859","citing_title":"Rethinking Agentic Reinforcement Learning In Large Language Models","ref_index":109,"is_internal_anchor":true},{"citing_arxiv_id":"2512.13399","citing_title":"Differentiable Evolutionary Reinforcement Learning","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27859","citing_title":"Rethinking Agentic Reinforcement Learning In Large Language Models","ref_index":109,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27859","citing_title":"Rethinking Agentic Reinforcement Learning In Large Language Models","ref_index":109,"is_internal_anchor":true},{"citing_arxiv_id":"2604.05820","citing_title":"SpecRL: Reinforcement Learning with Test-Based Completeness Rewards for Formal Specification Synthesis","ref_index":55,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IZGHA42XP3IFN3DPL4YWVK2JF5","json":"https://pith.science/pith/IZGHA42XP3IFN3DPL4YWVK2JF5.json","graph_json":"https://pith.science/api/pith-number/IZGHA42XP3IFN3DPL4YWVK2JF5/graph.json","events_json":"https://pith.science/api/pith-number/IZGHA42XP3IFN3DPL4YWVK2JF5/events.json","paper":"https://pith.science/paper/IZGHA42X"},"agent_actions":{"view_html":"https://pith.science/pith/IZGHA42XP3IFN3DPL4YWVK2JF5","download_json":"https://pith.science/pith/IZGHA42XP3IFN3DPL4YWVK2JF5.json","view_paper":"https://pith.science/paper/IZGHA42X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.16331&json=true","fetch_graph":"https://pith.science/api/pith-number/IZGHA42XP3IFN3DPL4YWVK2JF5/graph.json","fetch_events":"https://pith.science/api/pith-number/IZGHA42XP3IFN3DPL4YWVK2JF5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IZGHA42XP3IFN3DPL4YWVK2JF5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IZGHA42XP3IFN3DPL4YWVK2JF5/action/storage_attestation","attest_author":"https://pith.science/pith/IZGHA42XP3IFN3DPL4YWVK2JF5/action/author_attestation","sign_citation":"https://pith.science/pith/IZGHA42XP3IFN3DPL4YWVK2JF5/action/citation_signature","submit_replication":"https://pith.science/pith/IZGHA42XP3IFN3DPL4YWVK2JF5/action/replication_record"}},"created_at":"2026-07-07T01:15:56.504901+00:00","updated_at":"2026-07-07T01:15:56.504901+00:00"}