{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XUIX6G5QHN3UYWBPBVHYH56HOF","short_pith_number":"pith:XUIX6G5Q","canonical_record":{"source":{"id":"2501.16655","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-28T02:38:56Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"c69d21b96f6d50478c41f9606e93212a71e32e34e8dbbb9a0cc71bf4dac826b1","abstract_canon_sha256":"a33f2743ee5677e8a25f58f5854537d05e8c1b1362c31efeceaf69bdfcd3c378"},"schema_version":"1.0"},"canonical_sha256":"bd117f1bb03b774c582f0d4f83f7c7714e2041eb6007170b6a8ef5bdc7b126c7","source":{"kind":"arxiv","id":"2501.16655","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.16655","created_at":"2026-07-05T10:06:16Z"},{"alias_kind":"arxiv_version","alias_value":"2501.16655v1","created_at":"2026-07-05T10:06:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16655","created_at":"2026-07-05T10:06:16Z"},{"alias_kind":"pith_short_12","alias_value":"XUIX6G5QHN3U","created_at":"2026-07-05T10:06:16Z"},{"alias_kind":"pith_short_16","alias_value":"XUIX6G5QHN3UYWBP","created_at":"2026-07-05T10:06:16Z"},{"alias_kind":"pith_short_8","alias_value":"XUIX6G5Q","created_at":"2026-07-05T10:06:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XUIX6G5QHN3UYWBPBVHYH56HOF","target":"record","payload":{"canonical_record":{"source":{"id":"2501.16655","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-28T02:38:56Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"c69d21b96f6d50478c41f9606e93212a71e32e34e8dbbb9a0cc71bf4dac826b1","abstract_canon_sha256":"a33f2743ee5677e8a25f58f5854537d05e8c1b1362c31efeceaf69bdfcd3c378"},"schema_version":"1.0"},"canonical_sha256":"bd117f1bb03b774c582f0d4f83f7c7714e2041eb6007170b6a8ef5bdc7b126c7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:06:16.458602Z","signature_b64":"3uUIc/q0OpeIFWIL3BnvFqRlNmz+slUW+zoXepSXOihBcKmHMfV42lwa1f/DxsKV+RasoK92n7Nee50RyOgMAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd117f1bb03b774c582f0d4f83f7c7714e2041eb6007170b6a8ef5bdc7b126c7","last_reissued_at":"2026-07-05T10:06:16.458086Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:06:16.458086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.16655","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":"2026-07-05T10:06:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eg8pySAV6rlQ60KC8MP5W/nN6y4PhU36jx0UZhi7WiKHnKeK1seZKtudLE0bvmPBPZikrox737FMU44a0fN5Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:59:49.551099Z"},"content_sha256":"5a0fec976642e09ce66dcffde654f5c0164954b0b097accc3526282c6c72137e","schema_version":"1.0","event_id":"sha256:5a0fec976642e09ce66dcffde654f5c0164954b0b097accc3526282c6c72137e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XUIX6G5QHN3UYWBPBVHYH56HOF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large Language Model Critics for Execution-Free Evaluation of Code Changes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.CL","authors_text":"Aashish Yadavally, Gauthier Guinet, Hoan Nguyen, Laurent Callot","submitted_at":"2025-01-28T02:38:56Z","abstract_excerpt":"Large language models (LLMs) offer a promising way forward for automating software engineering tasks, such as bug fixes, feature additions, etc., via multi-step LLM-based agentic workflows. However, existing metrics for evaluating such workflows, mainly build status and occasionally log analysis, are too sparse and limited in providing the information needed to assess the quality of changes made. In this work, we designed LLM-based critics to derive well-structured and rigorous intermediate/step-level, execution-free evaluation proxies for repo-level code changes. Importantly, we assume access"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16655","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/2501.16655/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":"2026-07-05T10:06:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BEXczDDry0GndfTuuCbLtxPb5bd3T78s/rU0EX3d3Qwn4vCCcYFTZ1fVlGB/DADWdGF4qDwQY6eq8FR20RvODw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:59:49.551485Z"},"content_sha256":"b8ae26353d23eae251b215cc80acdbb5d1a41696e49e41fe313089d2eea2b566","schema_version":"1.0","event_id":"sha256:b8ae26353d23eae251b215cc80acdbb5d1a41696e49e41fe313089d2eea2b566"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XUIX6G5QHN3UYWBPBVHYH56HOF/bundle.json","state_url":"https://pith.science/pith/XUIX6G5QHN3UYWBPBVHYH56HOF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XUIX6G5QHN3UYWBPBVHYH56HOF/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":"2026-07-07T05:59:49Z","links":{"resolver":"https://pith.science/pith/XUIX6G5QHN3UYWBPBVHYH56HOF","bundle":"https://pith.science/pith/XUIX6G5QHN3UYWBPBVHYH56HOF/bundle.json","state":"https://pith.science/pith/XUIX6G5QHN3UYWBPBVHYH56HOF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XUIX6G5QHN3UYWBPBVHYH56HOF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XUIX6G5QHN3UYWBPBVHYH56HOF","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":"a33f2743ee5677e8a25f58f5854537d05e8c1b1362c31efeceaf69bdfcd3c378","cross_cats_sorted":["cs.AI","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-28T02:38:56Z","title_canon_sha256":"c69d21b96f6d50478c41f9606e93212a71e32e34e8dbbb9a0cc71bf4dac826b1"},"schema_version":"1.0","source":{"id":"2501.16655","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.16655","created_at":"2026-07-05T10:06:16Z"},{"alias_kind":"arxiv_version","alias_value":"2501.16655v1","created_at":"2026-07-05T10:06:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16655","created_at":"2026-07-05T10:06:16Z"},{"alias_kind":"pith_short_12","alias_value":"XUIX6G5QHN3U","created_at":"2026-07-05T10:06:16Z"},{"alias_kind":"pith_short_16","alias_value":"XUIX6G5QHN3UYWBP","created_at":"2026-07-05T10:06:16Z"},{"alias_kind":"pith_short_8","alias_value":"XUIX6G5Q","created_at":"2026-07-05T10:06:16Z"}],"graph_snapshots":[{"event_id":"sha256:b8ae26353d23eae251b215cc80acdbb5d1a41696e49e41fe313089d2eea2b566","target":"graph","created_at":"2026-07-05T10:06:16Z","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/2501.16655/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) offer a promising way forward for automating software engineering tasks, such as bug fixes, feature additions, etc., via multi-step LLM-based agentic workflows. However, existing metrics for evaluating such workflows, mainly build status and occasionally log analysis, are too sparse and limited in providing the information needed to assess the quality of changes made. In this work, we designed LLM-based critics to derive well-structured and rigorous intermediate/step-level, execution-free evaluation proxies for repo-level code changes. Importantly, we assume access","authors_text":"Aashish Yadavally, Gauthier Guinet, Hoan Nguyen, Laurent Callot","cross_cats":["cs.AI","cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-28T02:38:56Z","title":"Large Language Model Critics for Execution-Free Evaluation of Code Changes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16655","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":"sha256:5a0fec976642e09ce66dcffde654f5c0164954b0b097accc3526282c6c72137e","target":"record","created_at":"2026-07-05T10:06:16Z","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":"a33f2743ee5677e8a25f58f5854537d05e8c1b1362c31efeceaf69bdfcd3c378","cross_cats_sorted":["cs.AI","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-28T02:38:56Z","title_canon_sha256":"c69d21b96f6d50478c41f9606e93212a71e32e34e8dbbb9a0cc71bf4dac826b1"},"schema_version":"1.0","source":{"id":"2501.16655","kind":"arxiv","version":1}},"canonical_sha256":"bd117f1bb03b774c582f0d4f83f7c7714e2041eb6007170b6a8ef5bdc7b126c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd117f1bb03b774c582f0d4f83f7c7714e2041eb6007170b6a8ef5bdc7b126c7","first_computed_at":"2026-07-05T10:06:16.458086Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:06:16.458086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3uUIc/q0OpeIFWIL3BnvFqRlNmz+slUW+zoXepSXOihBcKmHMfV42lwa1f/DxsKV+RasoK92n7Nee50RyOgMAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:06:16.458602Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.16655","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a0fec976642e09ce66dcffde654f5c0164954b0b097accc3526282c6c72137e","sha256:b8ae26353d23eae251b215cc80acdbb5d1a41696e49e41fe313089d2eea2b566"],"state_sha256":"29d267d0d75180c8c17178232bd0487f4b934afd25c66b01609c016630208516"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AP5d4yFQmGexq5xogIg3Rni4ip+fDKhSnQ1uKQF7e5mtzCGalvNRZrkkNZhRrOfoiFvRaoZTP7qJsm2IBUU1Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T05:59:49.553415Z","bundle_sha256":"b4b4306f7a9959b91b687b0bcf20d77d56e104e5f95d9c202efd4c7cc906d437"}}