{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VTPOX5ZNBHOMPBPMFNEZTCWWLI","short_pith_number":"pith:VTPOX5ZN","canonical_record":{"source":{"id":"2602.07457","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-02-07T09:22:25Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"06d9566f9bc3ba6b53b176066e61e436ea47ce6ac2e50c8f66631d88de2f663e","abstract_canon_sha256":"9730115e7db0b34873c3fc817e30d507f9b80d901e48a46e69d2c83f3dc21f64"},"schema_version":"1.0"},"canonical_sha256":"acdeebf72d09dcc785ec2b49998ad65a2691f2b9a7b9c64c949afb8ac61b3475","source":{"kind":"arxiv","id":"2602.07457","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.07457","created_at":"2026-06-01T01:02:32Z"},{"alias_kind":"arxiv_version","alias_value":"2602.07457v2","created_at":"2026-06-01T01:02:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.07457","created_at":"2026-06-01T01:02:32Z"},{"alias_kind":"pith_short_12","alias_value":"VTPOX5ZNBHOM","created_at":"2026-06-01T01:02:32Z"},{"alias_kind":"pith_short_16","alias_value":"VTPOX5ZNBHOMPBPM","created_at":"2026-06-01T01:02:32Z"},{"alias_kind":"pith_short_8","alias_value":"VTPOX5ZN","created_at":"2026-06-01T01:02:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VTPOX5ZNBHOMPBPMFNEZTCWWLI","target":"record","payload":{"canonical_record":{"source":{"id":"2602.07457","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-02-07T09:22:25Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"06d9566f9bc3ba6b53b176066e61e436ea47ce6ac2e50c8f66631d88de2f663e","abstract_canon_sha256":"9730115e7db0b34873c3fc817e30d507f9b80d901e48a46e69d2c83f3dc21f64"},"schema_version":"1.0"},"canonical_sha256":"acdeebf72d09dcc785ec2b49998ad65a2691f2b9a7b9c64c949afb8ac61b3475","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:02:32.573523Z","signature_b64":"ibMDK9Zg9bpvCH1ZOGlfSyZdI0TCU0OP8U96rIQ9g3ll1A5fzgGXeXgBmXdty5MHewvrPtqSnJw1LNcxAfekCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acdeebf72d09dcc785ec2b49998ad65a2691f2b9a7b9c64c949afb8ac61b3475","last_reissued_at":"2026-06-01T01:02:32.572630Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:02:32.572630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.07457","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":"2026-06-01T01:02:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y+NzyllliMEuOpNDArBrbVFrRc8H4klrHKYf0DXpMxpv5AGkMfnwc39nEp2ZrOesxVfS6Hm4OHhaEQVuQizhCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T18:39:57.283898Z"},"content_sha256":"6d90be74808cc1a35be37613fdec91e66d3ae54204359ddb8aee14795fba84e3","schema_version":"1.0","event_id":"sha256:6d90be74808cc1a35be37613fdec91e66d3ae54204359ddb8aee14795fba84e3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VTPOX5ZNBHOMPBPMFNEZTCWWLI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pull Requests as a Training Signal for Repo-Level Code Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Lei Ji, Lin Gui, Murong Ma, Peng Cheng, Qinglin Zhu, Runcong Zhao, Shuai Lu, Tianyu Chen, Xiangxiang Dai, Yeyun Gong, Yulan He","submitted_at":"2026-02-07T09:22:25Z","abstract_excerpt":"Repository-level code editing requires models to understand complex dependencies and execute precise multi-file modifications across a large codebase. While recent gains on SWE-bench rely heavily on complex agent scaffolding, it remains unclear how much of this capability can be internalised via high-quality training signals. To address this, we propose Clean Pull Request (Clean-PR), a mid-training paradigm that leverages real-world GitHub pull requests as a training signal for repository-level editing. We introduce a scalable pipeline that converts noisy pull request diffs into Search/Replace"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.07457","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/2602.07457/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":"2026-06-01T01:02:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dyLwxzIzkCoXhTAXvbvvgNZ2LwGSXXxhn4lUlJvWZgko52kvMFodHIJDR3B1dRCsnWotaCQSUai78Rg4tJ0SAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T18:39:57.284284Z"},"content_sha256":"78c6cba0ac89abc62329b992388143d1034520cc588eb9d846487ba42f95f8a8","schema_version":"1.0","event_id":"sha256:78c6cba0ac89abc62329b992388143d1034520cc588eb9d846487ba42f95f8a8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VTPOX5ZNBHOMPBPMFNEZTCWWLI/bundle.json","state_url":"https://pith.science/pith/VTPOX5ZNBHOMPBPMFNEZTCWWLI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VTPOX5ZNBHOMPBPMFNEZTCWWLI/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":"2026-06-01T18:39:57Z","links":{"resolver":"https://pith.science/pith/VTPOX5ZNBHOMPBPMFNEZTCWWLI","bundle":"https://pith.science/pith/VTPOX5ZNBHOMPBPMFNEZTCWWLI/bundle.json","state":"https://pith.science/pith/VTPOX5ZNBHOMPBPMFNEZTCWWLI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VTPOX5ZNBHOMPBPMFNEZTCWWLI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VTPOX5ZNBHOMPBPMFNEZTCWWLI","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":"9730115e7db0b34873c3fc817e30d507f9b80d901e48a46e69d2c83f3dc21f64","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-02-07T09:22:25Z","title_canon_sha256":"06d9566f9bc3ba6b53b176066e61e436ea47ce6ac2e50c8f66631d88de2f663e"},"schema_version":"1.0","source":{"id":"2602.07457","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.07457","created_at":"2026-06-01T01:02:32Z"},{"alias_kind":"arxiv_version","alias_value":"2602.07457v2","created_at":"2026-06-01T01:02:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.07457","created_at":"2026-06-01T01:02:32Z"},{"alias_kind":"pith_short_12","alias_value":"VTPOX5ZNBHOM","created_at":"2026-06-01T01:02:32Z"},{"alias_kind":"pith_short_16","alias_value":"VTPOX5ZNBHOMPBPM","created_at":"2026-06-01T01:02:32Z"},{"alias_kind":"pith_short_8","alias_value":"VTPOX5ZN","created_at":"2026-06-01T01:02:32Z"}],"graph_snapshots":[{"event_id":"sha256:78c6cba0ac89abc62329b992388143d1034520cc588eb9d846487ba42f95f8a8","target":"graph","created_at":"2026-06-01T01:02:32Z","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/2602.07457/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Repository-level code editing requires models to understand complex dependencies and execute precise multi-file modifications across a large codebase. While recent gains on SWE-bench rely heavily on complex agent scaffolding, it remains unclear how much of this capability can be internalised via high-quality training signals. To address this, we propose Clean Pull Request (Clean-PR), a mid-training paradigm that leverages real-world GitHub pull requests as a training signal for repository-level editing. We introduce a scalable pipeline that converts noisy pull request diffs into Search/Replace","authors_text":"Lei Ji, Lin Gui, Murong Ma, Peng Cheng, Qinglin Zhu, Runcong Zhao, Shuai Lu, Tianyu Chen, Xiangxiang Dai, Yeyun Gong, Yulan He","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-02-07T09:22:25Z","title":"Pull Requests as a Training Signal for Repo-Level Code Editing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.07457","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":"sha256:6d90be74808cc1a35be37613fdec91e66d3ae54204359ddb8aee14795fba84e3","target":"record","created_at":"2026-06-01T01:02:32Z","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":"9730115e7db0b34873c3fc817e30d507f9b80d901e48a46e69d2c83f3dc21f64","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-02-07T09:22:25Z","title_canon_sha256":"06d9566f9bc3ba6b53b176066e61e436ea47ce6ac2e50c8f66631d88de2f663e"},"schema_version":"1.0","source":{"id":"2602.07457","kind":"arxiv","version":2}},"canonical_sha256":"acdeebf72d09dcc785ec2b49998ad65a2691f2b9a7b9c64c949afb8ac61b3475","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"acdeebf72d09dcc785ec2b49998ad65a2691f2b9a7b9c64c949afb8ac61b3475","first_computed_at":"2026-06-01T01:02:32.572630Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:02:32.572630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ibMDK9Zg9bpvCH1ZOGlfSyZdI0TCU0OP8U96rIQ9g3ll1A5fzgGXeXgBmXdty5MHewvrPtqSnJw1LNcxAfekCw==","signature_status":"signed_v1","signed_at":"2026-06-01T01:02:32.573523Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.07457","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d90be74808cc1a35be37613fdec91e66d3ae54204359ddb8aee14795fba84e3","sha256:78c6cba0ac89abc62329b992388143d1034520cc588eb9d846487ba42f95f8a8"],"state_sha256":"fea4994c2dac3562eaf52bd2488e2c3f6130ae5a91f11a2dcb2d2e9840aae8fc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EE2HQvikPUDXxOb6+eZ3E83zD6E3tDSh7Fw7+0StAZOaJaha939UvDWWRQY4OUKU0y9c0orVK3IWKi+Ud0UaBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T18:39:57.286534Z","bundle_sha256":"62428c04a0269a8f3de5e1820acf25ecbf645412f19bbda55741e8663de27a97"}}