{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IHDDE6SDMYZMICXFVHCZY4IUFL","short_pith_number":"pith:IHDDE6SD","schema_version":"1.0","canonical_sha256":"41c6327a436632c40ae5a9c59c71142ad33bfe575cd8d4fbaa8c7946e6f5b3a7","source":{"kind":"arxiv","id":"2606.06133","version":1},"attestation_state":"computed","paper":{"title":"TLA-Prover: Verifiable TLA+ Specification Synthesis via Preference-Optimized Low-Rank Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.LO"],"primary_cat":"cs.SE","authors_text":"Arslan Bisharat, Brian Ortiz, Eric Spencer, George K. Thiruvathukal, Khushboo Bhadauria, Konstantin Laufer, Mohammed Abuhamad, TaiNing Wang","submitted_at":"2026-06-04T13:17:06Z","abstract_excerpt":"TLA+ is a formal specification language for verifying distributed systems and safety-critical protocols. Large language models (LLMs) frequently produce TLA+ specifications that fail the TLC model checker for semantic reasons. Across 25 LLMs, the best public baseline is 26.6% syntactic parse and 8.6% semantic model-check. We present TLA-Prover, a 20-billion-parameter model for TLA+ specification synthesis. Training combines supervised fine-tuning (SFT) on verified examples with repair-based group-relative policy optimization (GRPO). In the GRPO stage, the model learns to fix its own rejected s"},"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":"2606.06133","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-04T13:17:06Z","cross_cats_sorted":["cs.AI","cs.LG","cs.LO"],"title_canon_sha256":"bb240ee2c5a28918febe1b9721592b7c16665c2d88e2001047f3e66fc0aa479a","abstract_canon_sha256":"58ec80fc27cbff7c623a80c6c04628d0270bb197e5fd900267bc933ae2bd458f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:34.629030Z","signature_b64":"3dv86SOrON7vRbNkiyliO0NoZWynJnQiKjYhoGej1iFzV/f+F5WKJQkbd4mtIOm1r5a8Ep30KeDyc559CFQuBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41c6327a436632c40ae5a9c59c71142ad33bfe575cd8d4fbaa8c7946e6f5b3a7","last_reissued_at":"2026-06-05T01:15:34.628501Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:34.628501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TLA-Prover: Verifiable TLA+ Specification Synthesis via Preference-Optimized Low-Rank Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.LO"],"primary_cat":"cs.SE","authors_text":"Arslan Bisharat, Brian Ortiz, Eric Spencer, George K. Thiruvathukal, Khushboo Bhadauria, Konstantin Laufer, Mohammed Abuhamad, TaiNing Wang","submitted_at":"2026-06-04T13:17:06Z","abstract_excerpt":"TLA+ is a formal specification language for verifying distributed systems and safety-critical protocols. Large language models (LLMs) frequently produce TLA+ specifications that fail the TLC model checker for semantic reasons. Across 25 LLMs, the best public baseline is 26.6% syntactic parse and 8.6% semantic model-check. We present TLA-Prover, a 20-billion-parameter model for TLA+ specification synthesis. Training combines supervised fine-tuning (SFT) on verified examples with repair-based group-relative policy optimization (GRPO). In the GRPO stage, the model learns to fix its own rejected s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06133","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/2606.06133/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":"2606.06133","created_at":"2026-06-05T01:15:34.628587+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.06133v1","created_at":"2026-06-05T01:15:34.628587+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06133","created_at":"2026-06-05T01:15:34.628587+00:00"},{"alias_kind":"pith_short_12","alias_value":"IHDDE6SDMYZM","created_at":"2026-06-05T01:15:34.628587+00:00"},{"alias_kind":"pith_short_16","alias_value":"IHDDE6SDMYZMICXF","created_at":"2026-06-05T01:15:34.628587+00:00"},{"alias_kind":"pith_short_8","alias_value":"IHDDE6SD","created_at":"2026-06-05T01:15:34.628587+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/IHDDE6SDMYZMICXFVHCZY4IUFL","json":"https://pith.science/pith/IHDDE6SDMYZMICXFVHCZY4IUFL.json","graph_json":"https://pith.science/api/pith-number/IHDDE6SDMYZMICXFVHCZY4IUFL/graph.json","events_json":"https://pith.science/api/pith-number/IHDDE6SDMYZMICXFVHCZY4IUFL/events.json","paper":"https://pith.science/paper/IHDDE6SD"},"agent_actions":{"view_html":"https://pith.science/pith/IHDDE6SDMYZMICXFVHCZY4IUFL","download_json":"https://pith.science/pith/IHDDE6SDMYZMICXFVHCZY4IUFL.json","view_paper":"https://pith.science/paper/IHDDE6SD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.06133&json=true","fetch_graph":"https://pith.science/api/pith-number/IHDDE6SDMYZMICXFVHCZY4IUFL/graph.json","fetch_events":"https://pith.science/api/pith-number/IHDDE6SDMYZMICXFVHCZY4IUFL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IHDDE6SDMYZMICXFVHCZY4IUFL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IHDDE6SDMYZMICXFVHCZY4IUFL/action/storage_attestation","attest_author":"https://pith.science/pith/IHDDE6SDMYZMICXFVHCZY4IUFL/action/author_attestation","sign_citation":"https://pith.science/pith/IHDDE6SDMYZMICXFVHCZY4IUFL/action/citation_signature","submit_replication":"https://pith.science/pith/IHDDE6SDMYZMICXFVHCZY4IUFL/action/replication_record"}},"created_at":"2026-06-05T01:15:34.628587+00:00","updated_at":"2026-06-05T01:15:34.628587+00:00"}