{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GEQ7SXKY2C5YED7G6KMD7WJ5GG","short_pith_number":"pith:GEQ7SXKY","canonical_record":{"source":{"id":"2509.02330","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-09-02T13:58:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dbcee00c666ec6b0d8752a494402a8295d914acd5bd92ebdd45dc0d8067aa50d","abstract_canon_sha256":"c47a67c2aaa31ff883cade2b9a3fd6b12b17f7237b0926f8affe41feb887a1d7"},"schema_version":"1.0"},"canonical_sha256":"3121f95d58d0bb820fe6f2983fd93d318c1fdff438a4eb70045071df32055702","source":{"kind":"arxiv","id":"2509.02330","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.02330","created_at":"2026-07-05T12:03:36Z"},{"alias_kind":"arxiv_version","alias_value":"2509.02330v1","created_at":"2026-07-05T12:03:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02330","created_at":"2026-07-05T12:03:36Z"},{"alias_kind":"pith_short_12","alias_value":"GEQ7SXKY2C5Y","created_at":"2026-07-05T12:03:36Z"},{"alias_kind":"pith_short_16","alias_value":"GEQ7SXKY2C5YED7G","created_at":"2026-07-05T12:03:36Z"},{"alias_kind":"pith_short_8","alias_value":"GEQ7SXKY","created_at":"2026-07-05T12:03:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GEQ7SXKY2C5YED7G6KMD7WJ5GG","target":"record","payload":{"canonical_record":{"source":{"id":"2509.02330","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-09-02T13:58:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dbcee00c666ec6b0d8752a494402a8295d914acd5bd92ebdd45dc0d8067aa50d","abstract_canon_sha256":"c47a67c2aaa31ff883cade2b9a3fd6b12b17f7237b0926f8affe41feb887a1d7"},"schema_version":"1.0"},"canonical_sha256":"3121f95d58d0bb820fe6f2983fd93d318c1fdff438a4eb70045071df32055702","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:03:36.402112Z","signature_b64":"a9owI6j7ipRkalnuKxoO8dc6SbWI3MZmUfC9V05/PLT97FJipLvGuVcnLfCVSWnJi8jBD7amr0pFtvaVNxVSDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3121f95d58d0bb820fe6f2983fd93d318c1fdff438a4eb70045071df32055702","last_reissued_at":"2026-07-05T12:03:36.401594Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:03:36.401594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.02330","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":"2026-07-05T12:03:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SzvwCYoGy1r5kGAjzZjfigiixjAt9n56XRoOFUIWFeq6ykSPcR2BF84rCu4p6W0AwfZ9Jp/XEsxiHvx7olIMAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T19:40:10.087543Z"},"content_sha256":"fa98751e1d8f5e5c4722882ed84e14000d6637c061d9e57ff2cd9d92f334b344","schema_version":"1.0","event_id":"sha256:fa98751e1d8f5e5c4722882ed84e14000d6637c061d9e57ff2cd9d92f334b344"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GEQ7SXKY2C5YED7G6KMD7WJ5GG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ReCode: Improving LLM-based Code Repair with Fine-Grained Retrieval-Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Jiacheng Zhang, Shisong Chen, Yicong Zhao, Zhixu Li","submitted_at":"2025-09-02T13:58:48Z","abstract_excerpt":"Recent advances in large language models (LLMs) have demonstrated impressive capabilities in code-related tasks, such as code generation and automated program repair. Despite their promising performance, most existing approaches for code repair suffer from high training costs or computationally expensive inference. Retrieval-augmented generation (RAG), with its efficient in-context learning paradigm, offers a more scalable alternative. However, conventional retrieval strategies, which are often based on holistic code-text embeddings, fail to capture the structural intricacies of code, resultin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02330","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/2509.02330/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":"2026-07-05T12:03:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i+h0ldwmkWWK1hfT0Uw0D2EN6eoupQKa1zGdo3ShpiLEWJDa5hWDUqCbVA//mICBfeOuBi1Kppq+ZfIoqU9VDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T19:40:10.088472Z"},"content_sha256":"3402d34cab7b71609115d2983b9718ff88eae246b1034d9cfcd8e1b6e0d72f68","schema_version":"1.0","event_id":"sha256:3402d34cab7b71609115d2983b9718ff88eae246b1034d9cfcd8e1b6e0d72f68"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GEQ7SXKY2C5YED7G6KMD7WJ5GG/bundle.json","state_url":"https://pith.science/pith/GEQ7SXKY2C5YED7G6KMD7WJ5GG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GEQ7SXKY2C5YED7G6KMD7WJ5GG/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":"2026-08-18T19:40:10Z","links":{"resolver":"https://pith.science/pith/GEQ7SXKY2C5YED7G6KMD7WJ5GG","bundle":"https://pith.science/pith/GEQ7SXKY2C5YED7G6KMD7WJ5GG/bundle.json","state":"https://pith.science/pith/GEQ7SXKY2C5YED7G6KMD7WJ5GG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GEQ7SXKY2C5YED7G6KMD7WJ5GG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GEQ7SXKY2C5YED7G6KMD7WJ5GG","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":"c47a67c2aaa31ff883cade2b9a3fd6b12b17f7237b0926f8affe41feb887a1d7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-09-02T13:58:48Z","title_canon_sha256":"dbcee00c666ec6b0d8752a494402a8295d914acd5bd92ebdd45dc0d8067aa50d"},"schema_version":"1.0","source":{"id":"2509.02330","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.02330","created_at":"2026-07-05T12:03:36Z"},{"alias_kind":"arxiv_version","alias_value":"2509.02330v1","created_at":"2026-07-05T12:03:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02330","created_at":"2026-07-05T12:03:36Z"},{"alias_kind":"pith_short_12","alias_value":"GEQ7SXKY2C5Y","created_at":"2026-07-05T12:03:36Z"},{"alias_kind":"pith_short_16","alias_value":"GEQ7SXKY2C5YED7G","created_at":"2026-07-05T12:03:36Z"},{"alias_kind":"pith_short_8","alias_value":"GEQ7SXKY","created_at":"2026-07-05T12:03:36Z"}],"graph_snapshots":[{"event_id":"sha256:3402d34cab7b71609115d2983b9718ff88eae246b1034d9cfcd8e1b6e0d72f68","target":"graph","created_at":"2026-07-05T12:03:36Z","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/2509.02330/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in large language models (LLMs) have demonstrated impressive capabilities in code-related tasks, such as code generation and automated program repair. Despite their promising performance, most existing approaches for code repair suffer from high training costs or computationally expensive inference. Retrieval-augmented generation (RAG), with its efficient in-context learning paradigm, offers a more scalable alternative. However, conventional retrieval strategies, which are often based on holistic code-text embeddings, fail to capture the structural intricacies of code, resultin","authors_text":"Jiacheng Zhang, Shisong Chen, Yicong Zhao, Zhixu Li","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-09-02T13:58:48Z","title":"ReCode: Improving LLM-based Code Repair with Fine-Grained Retrieval-Augmented Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02330","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:fa98751e1d8f5e5c4722882ed84e14000d6637c061d9e57ff2cd9d92f334b344","target":"record","created_at":"2026-07-05T12:03:36Z","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":"c47a67c2aaa31ff883cade2b9a3fd6b12b17f7237b0926f8affe41feb887a1d7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-09-02T13:58:48Z","title_canon_sha256":"dbcee00c666ec6b0d8752a494402a8295d914acd5bd92ebdd45dc0d8067aa50d"},"schema_version":"1.0","source":{"id":"2509.02330","kind":"arxiv","version":1}},"canonical_sha256":"3121f95d58d0bb820fe6f2983fd93d318c1fdff438a4eb70045071df32055702","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3121f95d58d0bb820fe6f2983fd93d318c1fdff438a4eb70045071df32055702","first_computed_at":"2026-07-05T12:03:36.401594Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:03:36.401594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a9owI6j7ipRkalnuKxoO8dc6SbWI3MZmUfC9V05/PLT97FJipLvGuVcnLfCVSWnJi8jBD7amr0pFtvaVNxVSDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:03:36.402112Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.02330","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fa98751e1d8f5e5c4722882ed84e14000d6637c061d9e57ff2cd9d92f334b344","sha256:3402d34cab7b71609115d2983b9718ff88eae246b1034d9cfcd8e1b6e0d72f68"],"state_sha256":"0cd3565f1707f15f7f584193e983be6cc1003f19ab5dbec5c6249b654b64bfc2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t0Dz9DzHeaRQJRU0eIEIRNK0cxz6TFmTihjr5ZGIGpaayig9zWsyd0JaG77R13VsV9u/LtxTnlodSzTYVtxjCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T19:40:10.094812Z","bundle_sha256":"844f0c8fb557b5dabb69e7db571cb7bdd637eb7c5d8eeaa0ba04c357a4427671"}}