{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:Q6LLOSIMK3VKF5YJHYZ32Q4KNW","short_pith_number":"pith:Q6LLOSIM","canonical_record":{"source":{"id":"2506.06093","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-06T13:52:41Z","cross_cats_sorted":[],"title_canon_sha256":"04743adbb673bb29da319654bcc6d340af535d9e990f4ede6131aac2748ca131","abstract_canon_sha256":"147be6b853b5b1596c70437f269f6b9fa977c23ceffd56c1113e7281c0a78eaa"},"schema_version":"1.0"},"canonical_sha256":"8796b7490c56eaa2f7093e33bd438a6d82b6951b47f9b80b9059be3c2ed9482e","source":{"kind":"arxiv","id":"2506.06093","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.06093","created_at":"2026-07-05T11:17:25Z"},{"alias_kind":"arxiv_version","alias_value":"2506.06093v1","created_at":"2026-07-05T11:17:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06093","created_at":"2026-07-05T11:17:25Z"},{"alias_kind":"pith_short_12","alias_value":"Q6LLOSIMK3VK","created_at":"2026-07-05T11:17:25Z"},{"alias_kind":"pith_short_16","alias_value":"Q6LLOSIMK3VKF5YJ","created_at":"2026-07-05T11:17:25Z"},{"alias_kind":"pith_short_8","alias_value":"Q6LLOSIM","created_at":"2026-07-05T11:17:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:Q6LLOSIMK3VKF5YJHYZ32Q4KNW","target":"record","payload":{"canonical_record":{"source":{"id":"2506.06093","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-06T13:52:41Z","cross_cats_sorted":[],"title_canon_sha256":"04743adbb673bb29da319654bcc6d340af535d9e990f4ede6131aac2748ca131","abstract_canon_sha256":"147be6b853b5b1596c70437f269f6b9fa977c23ceffd56c1113e7281c0a78eaa"},"schema_version":"1.0"},"canonical_sha256":"8796b7490c56eaa2f7093e33bd438a6d82b6951b47f9b80b9059be3c2ed9482e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:25.497028Z","signature_b64":"jhOwi00ACb8dyLx2xB8TE5dubuZXRmf66g9IjTx05Y318bywUyzZnIRdpkwJFOXht1qxBjICmA+R1ovA9LgnBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8796b7490c56eaa2f7093e33bd438a6d82b6951b47f9b80b9059be3c2ed9482e","last_reissued_at":"2026-07-05T11:17:25.496479Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:25.496479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.06093","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:17:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7dLRhi4HcH//hxZcNeQkCGYroa8fs9Ty2LTRkF7wLb+pzo9EqruEQwtpp4ixhVxn1RNleVFpJRVQCNaUa5ejCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T17:36:47.085295Z"},"content_sha256":"a71387431625b7e2100b40f22ec3cba26136fff31e626ac0f55be3f4671c1386","schema_version":"1.0","event_id":"sha256:a71387431625b7e2100b40f22ec3cba26136fff31e626ac0f55be3f4671c1386"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:Q6LLOSIMK3VKF5YJHYZ32Q4KNW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcing Code Generation: Improving Text-to-SQL with Execution-Based Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Atharv Kulkarni, Vivek Srikumar","submitted_at":"2025-06-06T13:52:41Z","abstract_excerpt":"In this work, we study the problem of code generation with a large language model (LLM), with a focus on generating SQL queries from natural language questions. We ask: Instead of using supervised fine tuning with text-code pairs, can we tune a model by having it interact with a database engine? We frame this problem as a reinforcement learning problem where the model receives execution-based feedback from the environment in the form of scalar rewards. These rewards penalize execution failures and assign positive values when a query returns a correct answer. We use the rewards within the Group"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06093","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/2506.06093/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:17:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Dss7DOoCi4kIu1VyWeekg472UMvllVi7RyeI1EU5wp4e4PHGPRsxIsFeLykXnkCA3OaW4Ha9/WRixWIRuTXYAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T17:36:47.085813Z"},"content_sha256":"e49ed7fe62994493c3859a6c52d27f19ab710f06d5d40478b2d5b882f321b339","schema_version":"1.0","event_id":"sha256:e49ed7fe62994493c3859a6c52d27f19ab710f06d5d40478b2d5b882f321b339"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q6LLOSIMK3VKF5YJHYZ32Q4KNW/bundle.json","state_url":"https://pith.science/pith/Q6LLOSIMK3VKF5YJHYZ32Q4KNW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q6LLOSIMK3VKF5YJHYZ32Q4KNW/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":"2026-08-19T17:36:47Z","links":{"resolver":"https://pith.science/pith/Q6LLOSIMK3VKF5YJHYZ32Q4KNW","bundle":"https://pith.science/pith/Q6LLOSIMK3VKF5YJHYZ32Q4KNW/bundle.json","state":"https://pith.science/pith/Q6LLOSIMK3VKF5YJHYZ32Q4KNW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q6LLOSIMK3VKF5YJHYZ32Q4KNW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Q6LLOSIMK3VKF5YJHYZ32Q4KNW","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"147be6b853b5b1596c70437f269f6b9fa977c23ceffd56c1113e7281c0a78eaa","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-06T13:52:41Z","title_canon_sha256":"04743adbb673bb29da319654bcc6d340af535d9e990f4ede6131aac2748ca131"},"schema_version":"1.0","source":{"id":"2506.06093","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.06093","created_at":"2026-07-05T11:17:25Z"},{"alias_kind":"arxiv_version","alias_value":"2506.06093v1","created_at":"2026-07-05T11:17:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06093","created_at":"2026-07-05T11:17:25Z"},{"alias_kind":"pith_short_12","alias_value":"Q6LLOSIMK3VK","created_at":"2026-07-05T11:17:25Z"},{"alias_kind":"pith_short_16","alias_value":"Q6LLOSIMK3VKF5YJ","created_at":"2026-07-05T11:17:25Z"},{"alias_kind":"pith_short_8","alias_value":"Q6LLOSIM","created_at":"2026-07-05T11:17:25Z"}],"graph_snapshots":[{"event_id":"sha256:e49ed7fe62994493c3859a6c52d27f19ab710f06d5d40478b2d5b882f321b339","target":"graph","created_at":"2026-07-05T11:17:25Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.06093/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we study the problem of code generation with a large language model (LLM), with a focus on generating SQL queries from natural language questions. We ask: Instead of using supervised fine tuning with text-code pairs, can we tune a model by having it interact with a database engine? We frame this problem as a reinforcement learning problem where the model receives execution-based feedback from the environment in the form of scalar rewards. These rewards penalize execution failures and assign positive values when a query returns a correct answer. We use the rewards within the Group","authors_text":"Atharv Kulkarni, Vivek Srikumar","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-06T13:52:41Z","title":"Reinforcing Code Generation: Improving Text-to-SQL with Execution-Based Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06093","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a71387431625b7e2100b40f22ec3cba26136fff31e626ac0f55be3f4671c1386","target":"record","created_at":"2026-07-05T11:17:25Z","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":"147be6b853b5b1596c70437f269f6b9fa977c23ceffd56c1113e7281c0a78eaa","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-06T13:52:41Z","title_canon_sha256":"04743adbb673bb29da319654bcc6d340af535d9e990f4ede6131aac2748ca131"},"schema_version":"1.0","source":{"id":"2506.06093","kind":"arxiv","version":1}},"canonical_sha256":"8796b7490c56eaa2f7093e33bd438a6d82b6951b47f9b80b9059be3c2ed9482e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8796b7490c56eaa2f7093e33bd438a6d82b6951b47f9b80b9059be3c2ed9482e","first_computed_at":"2026-07-05T11:17:25.496479Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:25.496479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jhOwi00ACb8dyLx2xB8TE5dubuZXRmf66g9IjTx05Y318bywUyzZnIRdpkwJFOXht1qxBjICmA+R1ovA9LgnBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:25.497028Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.06093","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a71387431625b7e2100b40f22ec3cba26136fff31e626ac0f55be3f4671c1386","sha256:e49ed7fe62994493c3859a6c52d27f19ab710f06d5d40478b2d5b882f321b339"],"state_sha256":"a6e06241d23e863d138e13767666af96f84806951dcf185c4a363e657c1f90a8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QeIH0JRSK/7Izh8AC5amO0tDWZE1Fp/fzSBZPFNx+IC/z69ilwtMZI/x+WyFEPyTLtwb1RExgAfy75whf04XBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T17:36:47.090907Z","bundle_sha256":"87e92b207be4ec526245f9461d89e8d28db74cc37550d40677f3a56b0221607b"}}