{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YJDDTPZFAZKX44Q72EG6T4FH6A","short_pith_number":"pith:YJDDTPZF","canonical_record":{"source":{"id":"2410.02749","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-03T17:57:22Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a2d56698163528d7a86d55efa967e73cf1a3565e965e9b1198b42ca9e58d8093","abstract_canon_sha256":"4be45810e558507019cb88b6dd6cc3ef39e4621226fcb96524d58fed1f28eed2"},"schema_version":"1.0"},"canonical_sha256":"c24639bf2506557e721fd10de9f0a7f00160ec1bd91952ea5456bd06f81d3a3a","source":{"kind":"arxiv","id":"2410.02749","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.02749","created_at":"2026-07-05T10:12:49Z"},{"alias_kind":"arxiv_version","alias_value":"2410.02749v3","created_at":"2026-07-05T10:12:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02749","created_at":"2026-07-05T10:12:49Z"},{"alias_kind":"pith_short_12","alias_value":"YJDDTPZFAZKX","created_at":"2026-07-05T10:12:49Z"},{"alias_kind":"pith_short_16","alias_value":"YJDDTPZFAZKX44Q7","created_at":"2026-07-05T10:12:49Z"},{"alias_kind":"pith_short_8","alias_value":"YJDDTPZF","created_at":"2026-07-05T10:12:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YJDDTPZFAZKX44Q72EG6T4FH6A","target":"record","payload":{"canonical_record":{"source":{"id":"2410.02749","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-03T17:57:22Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a2d56698163528d7a86d55efa967e73cf1a3565e965e9b1198b42ca9e58d8093","abstract_canon_sha256":"4be45810e558507019cb88b6dd6cc3ef39e4621226fcb96524d58fed1f28eed2"},"schema_version":"1.0"},"canonical_sha256":"c24639bf2506557e721fd10de9f0a7f00160ec1bd91952ea5456bd06f81d3a3a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:49.331294Z","signature_b64":"7+iQ2/xL4rTvTzGxXccckSA/6/QV2HYjm/M0IgQPL0JGsMJWdoop9BLnlDdwU995Ib2L+3wK3INLXLY5Ba6qBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c24639bf2506557e721fd10de9f0a7f00160ec1bd91952ea5456bd06f81d3a3a","last_reissued_at":"2026-07-05T10:12:49.330687Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:49.330687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.02749","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:12:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r2hQ7mBxOto2TaV9Eglge2LPO/fS486aGRW7KWMSRZo279Ee+Oh5LKniD56JbIV6sUiVYxkc4dwOzNm7yGjWAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:28:45.714748Z"},"content_sha256":"d226a42d0283196ffa8bc973f9b6e898db57b8ff4aa7e3cb72620b0c1df176aa","schema_version":"1.0","event_id":"sha256:d226a42d0283196ffa8bc973f9b6e898db57b8ff4aa7e3cb72620b0c1df176aa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YJDDTPZFAZKX44Q72EG6T4FH6A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Training Language Models on Synthetic Edit Sequences Improves Code Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Lerrel Pinto, Rob Fergus, Ulyana Piterbarg","submitted_at":"2024-10-03T17:57:22Z","abstract_excerpt":"Software engineers mainly write code by editing existing programs. In contrast, language models (LMs) autoregressively synthesize programs in a single pass. One explanation for this is the scarcity of sequential edit data. While high-quality instruction data for code synthesis is scarce, edit data for synthesis is even scarcer. To fill this gap, we develop a synthetic data generation algorithm called LintSeq. This algorithm refactors programs into sequences of synthetic edits by using a linter to procedurally sample across interdependent lines of source code. Synthetic edits sampled with LintS"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02749","kind":"arxiv","version":3},"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/2410.02749/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":"2026-07-05T10:12:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ibDkw1ga2Zn3aq3oxtyysWDRevwHsJCdy979oOOHDDo9X71DOIC3YrbC0Hr38fsSQ4TK5obpRDgRATBBv2W1Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:28:45.715284Z"},"content_sha256":"8d91883a3bfa0ff0bfa3224d360a74083e484aacd6ea90433a05e634fb5a7631","schema_version":"1.0","event_id":"sha256:8d91883a3bfa0ff0bfa3224d360a74083e484aacd6ea90433a05e634fb5a7631"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YJDDTPZFAZKX44Q72EG6T4FH6A/bundle.json","state_url":"https://pith.science/pith/YJDDTPZFAZKX44Q72EG6T4FH6A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YJDDTPZFAZKX44Q72EG6T4FH6A/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":"2026-08-03T16:28:45Z","links":{"resolver":"https://pith.science/pith/YJDDTPZFAZKX44Q72EG6T4FH6A","bundle":"https://pith.science/pith/YJDDTPZFAZKX44Q72EG6T4FH6A/bundle.json","state":"https://pith.science/pith/YJDDTPZFAZKX44Q72EG6T4FH6A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YJDDTPZFAZKX44Q72EG6T4FH6A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YJDDTPZFAZKX44Q72EG6T4FH6A","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":"4be45810e558507019cb88b6dd6cc3ef39e4621226fcb96524d58fed1f28eed2","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-03T17:57:22Z","title_canon_sha256":"a2d56698163528d7a86d55efa967e73cf1a3565e965e9b1198b42ca9e58d8093"},"schema_version":"1.0","source":{"id":"2410.02749","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.02749","created_at":"2026-07-05T10:12:49Z"},{"alias_kind":"arxiv_version","alias_value":"2410.02749v3","created_at":"2026-07-05T10:12:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02749","created_at":"2026-07-05T10:12:49Z"},{"alias_kind":"pith_short_12","alias_value":"YJDDTPZFAZKX","created_at":"2026-07-05T10:12:49Z"},{"alias_kind":"pith_short_16","alias_value":"YJDDTPZFAZKX44Q7","created_at":"2026-07-05T10:12:49Z"},{"alias_kind":"pith_short_8","alias_value":"YJDDTPZF","created_at":"2026-07-05T10:12:49Z"}],"graph_snapshots":[{"event_id":"sha256:8d91883a3bfa0ff0bfa3224d360a74083e484aacd6ea90433a05e634fb5a7631","target":"graph","created_at":"2026-07-05T10:12:49Z","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/2410.02749/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Software engineers mainly write code by editing existing programs. In contrast, language models (LMs) autoregressively synthesize programs in a single pass. One explanation for this is the scarcity of sequential edit data. While high-quality instruction data for code synthesis is scarce, edit data for synthesis is even scarcer. To fill this gap, we develop a synthetic data generation algorithm called LintSeq. This algorithm refactors programs into sequences of synthetic edits by using a linter to procedurally sample across interdependent lines of source code. Synthetic edits sampled with LintS","authors_text":"Lerrel Pinto, Rob Fergus, Ulyana Piterbarg","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-03T17:57:22Z","title":"Training Language Models on Synthetic Edit Sequences Improves Code Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02749","kind":"arxiv","version":3},"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:d226a42d0283196ffa8bc973f9b6e898db57b8ff4aa7e3cb72620b0c1df176aa","target":"record","created_at":"2026-07-05T10:12:49Z","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":"4be45810e558507019cb88b6dd6cc3ef39e4621226fcb96524d58fed1f28eed2","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-03T17:57:22Z","title_canon_sha256":"a2d56698163528d7a86d55efa967e73cf1a3565e965e9b1198b42ca9e58d8093"},"schema_version":"1.0","source":{"id":"2410.02749","kind":"arxiv","version":3}},"canonical_sha256":"c24639bf2506557e721fd10de9f0a7f00160ec1bd91952ea5456bd06f81d3a3a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c24639bf2506557e721fd10de9f0a7f00160ec1bd91952ea5456bd06f81d3a3a","first_computed_at":"2026-07-05T10:12:49.330687Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:12:49.330687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7+iQ2/xL4rTvTzGxXccckSA/6/QV2HYjm/M0IgQPL0JGsMJWdoop9BLnlDdwU995Ib2L+3wK3INLXLY5Ba6qBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:12:49.331294Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.02749","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d226a42d0283196ffa8bc973f9b6e898db57b8ff4aa7e3cb72620b0c1df176aa","sha256:8d91883a3bfa0ff0bfa3224d360a74083e484aacd6ea90433a05e634fb5a7631"],"state_sha256":"05e6a3b39b36bae21ec12232914a5a4234c1d6570b4659197abcb44fab043771"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sgrMUDcGKn1WCLajVaqEHFqxcmwrJEN0wwYe4W09MFgnbUjm3PH2W9hiwMAfyIazoDCZ7yhPkPZwSRIju6jeCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T16:28:45.720577Z","bundle_sha256":"d8c2ca60296210502cba7b72c865563e54f8da30609ddc91f713ea9fd2e0cbdf"}}