{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JH2QOK63JNLIVLJXAOHRVDDMEA","short_pith_number":"pith:JH2QOK63","canonical_record":{"source":{"id":"2504.15210","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-21T16:29:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"610ef47c413ea6b0fc2f48ba30b7accd9f63cb5662a30c41c200e6c3e14ee355","abstract_canon_sha256":"eca9c18fdc6f6384f1f63ce2ed8d736cd56a93fa6dd01f4e65520d72b45d8c7d"},"schema_version":"1.0"},"canonical_sha256":"49f5072bdb4b568aad37038f1a8c6c200229d4d829cf4f5c6fe057c8cc53391f","source":{"kind":"arxiv","id":"2504.15210","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.15210","created_at":"2026-07-05T10:58:26Z"},{"alias_kind":"arxiv_version","alias_value":"2504.15210v2","created_at":"2026-07-05T10:58:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15210","created_at":"2026-07-05T10:58:26Z"},{"alias_kind":"pith_short_12","alias_value":"JH2QOK63JNLI","created_at":"2026-07-05T10:58:26Z"},{"alias_kind":"pith_short_16","alias_value":"JH2QOK63JNLIVLJX","created_at":"2026-07-05T10:58:26Z"},{"alias_kind":"pith_short_8","alias_value":"JH2QOK63","created_at":"2026-07-05T10:58:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JH2QOK63JNLIVLJXAOHRVDDMEA","target":"record","payload":{"canonical_record":{"source":{"id":"2504.15210","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-21T16:29:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"610ef47c413ea6b0fc2f48ba30b7accd9f63cb5662a30c41c200e6c3e14ee355","abstract_canon_sha256":"eca9c18fdc6f6384f1f63ce2ed8d736cd56a93fa6dd01f4e65520d72b45d8c7d"},"schema_version":"1.0"},"canonical_sha256":"49f5072bdb4b568aad37038f1a8c6c200229d4d829cf4f5c6fe057c8cc53391f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:26.098918Z","signature_b64":"LSQxFrES0l2pusRQ5QcXeKZYMNa9+oGsPAlmjMvPFSQzCbT02OImNjrN9I7RciP3o1Lm0Mi/eXxizmlODcUHBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49f5072bdb4b568aad37038f1a8c6c200229d4d829cf4f5c6fe057c8cc53391f","last_reissued_at":"2026-07-05T10:58:26.098420Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:26.098420Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.15210","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:58:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n620J75vPixnPzsVQ7YLgUe4QMr8WiNm2DeWvlbm4eSn5PE+x2NpdhcyP/Beuo0D9g9kwkv17enHW8H2bSuDDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T20:37:22.598211Z"},"content_sha256":"de55ffd3ebc6a39b32b518147cc26efa397762ce8a0b83eda444b375a3426876","schema_version":"1.0","event_id":"sha256:de55ffd3ebc6a39b32b518147cc26efa397762ce8a0b83eda444b375a3426876"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JH2QOK63JNLIVLJXAOHRVDDMEA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Integrating Symbolic Execution into the Fine-Tuning of Code-Generating LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Abhinav Anand, Marina Sakharova, Mira Mezini","submitted_at":"2025-04-21T16:29:07Z","abstract_excerpt":"Code-generating Large Language Models (LLMs) have become essential tools in modern software development, enhancing productivity and accelerating development. This paper aims to investigate the fine-tuning of code-generating LLMs using Reinforcement Learning and Direct Preference Optimization, further improving their performance. To achieve this, we enhance the training data for the reward model with the help of symbolic execution techniques, ensuring more comprehensive and objective data. With symbolic execution, we create a custom dataset that better captures the nuances in code evaluation. O"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15210","kind":"arxiv","version":2},"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/2504.15210/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":"2026-07-05T10:58:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QuYxli9KGxuVXhUMtaaW5e/+IsqsIdmFA5N0Sqw/Ff1lpLywWqqymXdbUhPhnLjIO21yW6rz1CACqp4GvJ9pDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T20:37:22.599141Z"},"content_sha256":"3abd3a4a49c94f1411a7a03e8e9124915411dcf31559daf870d833076667fd65","schema_version":"1.0","event_id":"sha256:3abd3a4a49c94f1411a7a03e8e9124915411dcf31559daf870d833076667fd65"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JH2QOK63JNLIVLJXAOHRVDDMEA/bundle.json","state_url":"https://pith.science/pith/JH2QOK63JNLIVLJXAOHRVDDMEA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JH2QOK63JNLIVLJXAOHRVDDMEA/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":"2026-08-19T20:37:22Z","links":{"resolver":"https://pith.science/pith/JH2QOK63JNLIVLJXAOHRVDDMEA","bundle":"https://pith.science/pith/JH2QOK63JNLIVLJXAOHRVDDMEA/bundle.json","state":"https://pith.science/pith/JH2QOK63JNLIVLJXAOHRVDDMEA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JH2QOK63JNLIVLJXAOHRVDDMEA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JH2QOK63JNLIVLJXAOHRVDDMEA","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":"eca9c18fdc6f6384f1f63ce2ed8d736cd56a93fa6dd01f4e65520d72b45d8c7d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-21T16:29:07Z","title_canon_sha256":"610ef47c413ea6b0fc2f48ba30b7accd9f63cb5662a30c41c200e6c3e14ee355"},"schema_version":"1.0","source":{"id":"2504.15210","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.15210","created_at":"2026-07-05T10:58:26Z"},{"alias_kind":"arxiv_version","alias_value":"2504.15210v2","created_at":"2026-07-05T10:58:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15210","created_at":"2026-07-05T10:58:26Z"},{"alias_kind":"pith_short_12","alias_value":"JH2QOK63JNLI","created_at":"2026-07-05T10:58:26Z"},{"alias_kind":"pith_short_16","alias_value":"JH2QOK63JNLIVLJX","created_at":"2026-07-05T10:58:26Z"},{"alias_kind":"pith_short_8","alias_value":"JH2QOK63","created_at":"2026-07-05T10:58:26Z"}],"graph_snapshots":[{"event_id":"sha256:3abd3a4a49c94f1411a7a03e8e9124915411dcf31559daf870d833076667fd65","target":"graph","created_at":"2026-07-05T10:58:26Z","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/2504.15210/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Code-generating Large Language Models (LLMs) have become essential tools in modern software development, enhancing productivity and accelerating development. This paper aims to investigate the fine-tuning of code-generating LLMs using Reinforcement Learning and Direct Preference Optimization, further improving their performance. To achieve this, we enhance the training data for the reward model with the help of symbolic execution techniques, ensuring more comprehensive and objective data. With symbolic execution, we create a custom dataset that better captures the nuances in code evaluation. O","authors_text":"Abhinav Anand, Marina Sakharova, Mira Mezini","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-21T16:29:07Z","title":"Integrating Symbolic Execution into the Fine-Tuning of Code-Generating LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15210","kind":"arxiv","version":2},"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:de55ffd3ebc6a39b32b518147cc26efa397762ce8a0b83eda444b375a3426876","target":"record","created_at":"2026-07-05T10:58:26Z","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":"eca9c18fdc6f6384f1f63ce2ed8d736cd56a93fa6dd01f4e65520d72b45d8c7d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-21T16:29:07Z","title_canon_sha256":"610ef47c413ea6b0fc2f48ba30b7accd9f63cb5662a30c41c200e6c3e14ee355"},"schema_version":"1.0","source":{"id":"2504.15210","kind":"arxiv","version":2}},"canonical_sha256":"49f5072bdb4b568aad37038f1a8c6c200229d4d829cf4f5c6fe057c8cc53391f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"49f5072bdb4b568aad37038f1a8c6c200229d4d829cf4f5c6fe057c8cc53391f","first_computed_at":"2026-07-05T10:58:26.098420Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:58:26.098420Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LSQxFrES0l2pusRQ5QcXeKZYMNa9+oGsPAlmjMvPFSQzCbT02OImNjrN9I7RciP3o1Lm0Mi/eXxizmlODcUHBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:58:26.098918Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.15210","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de55ffd3ebc6a39b32b518147cc26efa397762ce8a0b83eda444b375a3426876","sha256:3abd3a4a49c94f1411a7a03e8e9124915411dcf31559daf870d833076667fd65"],"state_sha256":"39d8d02fbd5c1c26bc03f9606776e4448bd1d046179ea2d9c736c2d4af251b57"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZUEv8qEIxQbdLDNKZHuA4LfnXnWgfkt0JJ4XrkQxzT2s//XHGBABOTpcbJemgFsMJ8EtBpkSjB4IWhYvRCVYAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T20:37:22.605702Z","bundle_sha256":"50d57dd65e6ab62831ab72ff3939fd37fd4238a6c3065e714906d7d255dbfb9a"}}