{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5NWL7WUNSFZKPJSBZLGDLLCKQX","short_pith_number":"pith:5NWL7WUN","canonical_record":{"source":{"id":"2507.15889","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-20T02:10:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a5419dce1195d8fd7c16fe612604138be15ed226bb8751f421b4f52d9082462b","abstract_canon_sha256":"9500055b54ab01015257cf4f70981d19813e786ec163d22310372f8c902d0318"},"schema_version":"1.0"},"canonical_sha256":"eb6cbfda8d9172a7a641cacc35ac4a85f3562a739b4b68d39c8df240fd429de0","source":{"kind":"arxiv","id":"2507.15889","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.15889","created_at":"2026-07-05T11:40:58Z"},{"alias_kind":"arxiv_version","alias_value":"2507.15889v1","created_at":"2026-07-05T11:40:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15889","created_at":"2026-07-05T11:40:58Z"},{"alias_kind":"pith_short_12","alias_value":"5NWL7WUNSFZK","created_at":"2026-07-05T11:40:58Z"},{"alias_kind":"pith_short_16","alias_value":"5NWL7WUNSFZKPJSB","created_at":"2026-07-05T11:40:58Z"},{"alias_kind":"pith_short_8","alias_value":"5NWL7WUN","created_at":"2026-07-05T11:40:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5NWL7WUNSFZKPJSBZLGDLLCKQX","target":"record","payload":{"canonical_record":{"source":{"id":"2507.15889","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-20T02:10:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a5419dce1195d8fd7c16fe612604138be15ed226bb8751f421b4f52d9082462b","abstract_canon_sha256":"9500055b54ab01015257cf4f70981d19813e786ec163d22310372f8c902d0318"},"schema_version":"1.0"},"canonical_sha256":"eb6cbfda8d9172a7a641cacc35ac4a85f3562a739b4b68d39c8df240fd429de0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:58.673503Z","signature_b64":"tfmqFu/f8ZPErgLEAQJ9ABtkMz+C8bProUEJwlx30G06fw53rfPqD8IpmeQwK9KW9Y5FBexhR2nu0m9en8doDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb6cbfda8d9172a7a641cacc35ac4a85f3562a739b4b68d39c8df240fd429de0","last_reissued_at":"2026-07-05T11:40:58.672976Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:58.672976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.15889","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":"2026-07-05T11:40:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l5yD8WGwtxD+lK9h670u2TkVFUDgDpAKW5n0MvcOFG8VVLRXV9h2Eu6u+1WsjHN7okbVazKY6AUSYH3p0N1sCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:43:56.316256Z"},"content_sha256":"b2a56dc0fe53dfb0383aad30e29c5d004ad11a662600f6ed42ad1673998cf889","schema_version":"1.0","event_id":"sha256:b2a56dc0fe53dfb0383aad30e29c5d004ad11a662600f6ed42ad1673998cf889"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5NWL7WUNSFZKPJSBZLGDLLCKQX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dr. Boot: Bootstrapping Program Synthesis Language Models to Perform Repairing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Noah van der Vleuten","submitted_at":"2025-07-20T02:10:46Z","abstract_excerpt":"Language models for program synthesis are usually trained and evaluated on programming competition datasets (MBPP, APPS). However, these datasets are limited in size and quality, while these language models are extremely data hungry. Additionally, the language models have a misaligned program synthesis process compared to humans. While humans iteratively develop code with the help of a compiler, most program synthesis models currently produce code in one go. To solve these issues, we introduce a bootstrapping algorithm for program synthesis, that supports teaching models how to repair. We show"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.15889","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/2507.15889/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":"2026-07-05T11:40:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N1JwOC+Yy/+587hYDptgfpDejJ0w+Yvf6vsjYbocexLUyaS38RgZLeii1ytxNvXZXSiMo3vMaXyQZrj0bNBQAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:43:56.316867Z"},"content_sha256":"a2839e48908d5088449804bfaf7208ef37ac3f4d2934b900c27f3b12f4e037b4","schema_version":"1.0","event_id":"sha256:a2839e48908d5088449804bfaf7208ef37ac3f4d2934b900c27f3b12f4e037b4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5NWL7WUNSFZKPJSBZLGDLLCKQX/bundle.json","state_url":"https://pith.science/pith/5NWL7WUNSFZKPJSBZLGDLLCKQX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5NWL7WUNSFZKPJSBZLGDLLCKQX/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":"2026-08-07T22:43:56Z","links":{"resolver":"https://pith.science/pith/5NWL7WUNSFZKPJSBZLGDLLCKQX","bundle":"https://pith.science/pith/5NWL7WUNSFZKPJSBZLGDLLCKQX/bundle.json","state":"https://pith.science/pith/5NWL7WUNSFZKPJSBZLGDLLCKQX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5NWL7WUNSFZKPJSBZLGDLLCKQX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5NWL7WUNSFZKPJSBZLGDLLCKQX","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":"9500055b54ab01015257cf4f70981d19813e786ec163d22310372f8c902d0318","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-20T02:10:46Z","title_canon_sha256":"a5419dce1195d8fd7c16fe612604138be15ed226bb8751f421b4f52d9082462b"},"schema_version":"1.0","source":{"id":"2507.15889","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.15889","created_at":"2026-07-05T11:40:58Z"},{"alias_kind":"arxiv_version","alias_value":"2507.15889v1","created_at":"2026-07-05T11:40:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15889","created_at":"2026-07-05T11:40:58Z"},{"alias_kind":"pith_short_12","alias_value":"5NWL7WUNSFZK","created_at":"2026-07-05T11:40:58Z"},{"alias_kind":"pith_short_16","alias_value":"5NWL7WUNSFZKPJSB","created_at":"2026-07-05T11:40:58Z"},{"alias_kind":"pith_short_8","alias_value":"5NWL7WUN","created_at":"2026-07-05T11:40:58Z"}],"graph_snapshots":[{"event_id":"sha256:a2839e48908d5088449804bfaf7208ef37ac3f4d2934b900c27f3b12f4e037b4","target":"graph","created_at":"2026-07-05T11:40:58Z","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/2507.15889/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models for program synthesis are usually trained and evaluated on programming competition datasets (MBPP, APPS). However, these datasets are limited in size and quality, while these language models are extremely data hungry. Additionally, the language models have a misaligned program synthesis process compared to humans. While humans iteratively develop code with the help of a compiler, most program synthesis models currently produce code in one go. To solve these issues, we introduce a bootstrapping algorithm for program synthesis, that supports teaching models how to repair. We show","authors_text":"Noah van der Vleuten","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-20T02:10:46Z","title":"Dr. Boot: Bootstrapping Program Synthesis Language Models to Perform Repairing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.15889","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:b2a56dc0fe53dfb0383aad30e29c5d004ad11a662600f6ed42ad1673998cf889","target":"record","created_at":"2026-07-05T11:40:58Z","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":"9500055b54ab01015257cf4f70981d19813e786ec163d22310372f8c902d0318","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-20T02:10:46Z","title_canon_sha256":"a5419dce1195d8fd7c16fe612604138be15ed226bb8751f421b4f52d9082462b"},"schema_version":"1.0","source":{"id":"2507.15889","kind":"arxiv","version":1}},"canonical_sha256":"eb6cbfda8d9172a7a641cacc35ac4a85f3562a739b4b68d39c8df240fd429de0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eb6cbfda8d9172a7a641cacc35ac4a85f3562a739b4b68d39c8df240fd429de0","first_computed_at":"2026-07-05T11:40:58.672976Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:40:58.672976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tfmqFu/f8ZPErgLEAQJ9ABtkMz+C8bProUEJwlx30G06fw53rfPqD8IpmeQwK9KW9Y5FBexhR2nu0m9en8doDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:40:58.673503Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.15889","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2a56dc0fe53dfb0383aad30e29c5d004ad11a662600f6ed42ad1673998cf889","sha256:a2839e48908d5088449804bfaf7208ef37ac3f4d2934b900c27f3b12f4e037b4"],"state_sha256":"9335cfc00f602f82791de0258c5b289bf9b43235aaac453b6e491d9c727bff30"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7+ehoUbAfD/MZI0WGQdfuZ8WIKgqKuTym8FdNyBGCI//6k+AFGYUYFl4RQY7C9q7PsE5Inwy4Q7I5IBinxBsAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T22:43:56.322778Z","bundle_sha256":"761beced0bac01d8ff08ad6c05b9a5fd903869ec139ae5d05503c7b994acc46b"}}