{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TNBEHQGNPZAIJK6OEKAUG7G6TG","short_pith_number":"pith:TNBEHQGN","canonical_record":{"source":{"id":"2502.07046","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-10T21:28:15Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0a09b20c0119e5432a97e3946fdd8030b8eea3de3b24383e59ace0d1e994d5e5","abstract_canon_sha256":"bf422af79e979d095565f7b106fd2cd2b65413e2245c6115323dc879064d9588"},"schema_version":"1.0"},"canonical_sha256":"9b4243c0cd7e4084abce2281437cde998db2795e20dc62b4e48dd658eee9875e","source":{"kind":"arxiv","id":"2502.07046","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.07046","created_at":"2026-07-05T10:14:50Z"},{"alias_kind":"arxiv_version","alias_value":"2502.07046v2","created_at":"2026-07-05T10:14:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07046","created_at":"2026-07-05T10:14:50Z"},{"alias_kind":"pith_short_12","alias_value":"TNBEHQGNPZAI","created_at":"2026-07-05T10:14:50Z"},{"alias_kind":"pith_short_16","alias_value":"TNBEHQGNPZAIJK6O","created_at":"2026-07-05T10:14:50Z"},{"alias_kind":"pith_short_8","alias_value":"TNBEHQGN","created_at":"2026-07-05T10:14:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TNBEHQGNPZAIJK6OEKAUG7G6TG","target":"record","payload":{"canonical_record":{"source":{"id":"2502.07046","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-10T21:28:15Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0a09b20c0119e5432a97e3946fdd8030b8eea3de3b24383e59ace0d1e994d5e5","abstract_canon_sha256":"bf422af79e979d095565f7b106fd2cd2b65413e2245c6115323dc879064d9588"},"schema_version":"1.0"},"canonical_sha256":"9b4243c0cd7e4084abce2281437cde998db2795e20dc62b4e48dd658eee9875e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:50.998447Z","signature_b64":"sPZPaJFap+BaeBNgnupX2FLa9YbYJ4rrRuOeKUwwdauGqmL7yNa/ukaOyNYEWHc2HQtm4aLeBrDkytNgZobDBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b4243c0cd7e4084abce2281437cde998db2795e20dc62b4e48dd658eee9875e","last_reissued_at":"2026-07-05T10:14:50.997942Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:50.997942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.07046","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":"2026-07-05T10:14:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iqbuFXzGSGa9QtWfK2VmTqBpFdCvZfCe0n2MyPTBKz1WhIM5UOcOjSM1qYXzs5LqgwCVwYmPU3VbF85+FA8qAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T21:04:47.910009Z"},"content_sha256":"36e5d30cd64bc175518eba91f1943f457f5c7d7a0922c752e0b78ef1707a5b81","schema_version":"1.0","event_id":"sha256:36e5d30cd64bc175518eba91f1943f457f5c7d7a0922c752e0b78ef1707a5b81"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TNBEHQGNPZAIJK6OEKAUG7G6TG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SnipGen: A Mining Repository Framework for Evaluating LLMs for Code","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.SE","authors_text":"Alejandro Velasco, Daniel Rodriguez-Cardenas, Denys Poshyvanyk","submitted_at":"2025-02-10T21:28:15Z","abstract_excerpt":"Language Models (LLMs), such as transformer-based neural networks trained on billions of parameters, have become increasingly prevalent in software engineering (SE). These models, trained on extensive datasets that include code repositories, exhibit remarkable capabilities for SE tasks. However, evaluating their effectiveness poses significant challenges, primarily due to the potential overlap between the datasets used for training and those employed for evaluation. To address this issue, we introduce SnipGen, a comprehensive repository mining framework designed to leverage prompt engineering "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07046","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/2502.07046/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":"2026-07-05T10:14:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TkvKNJ6gtGTB+yBg31UBZJHSBD8LWY7a3OaRaIxr4PmZ1t8CSgjSiw1M0oaOHxaUlV0rkQ6zo2TkfYxq6od8Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T21:04:47.910645Z"},"content_sha256":"3a8ceb62c585eda5532b7ffe295e798cfa2b616fdbcdd907710c4be532b28f72","schema_version":"1.0","event_id":"sha256:3a8ceb62c585eda5532b7ffe295e798cfa2b616fdbcdd907710c4be532b28f72"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TNBEHQGNPZAIJK6OEKAUG7G6TG/bundle.json","state_url":"https://pith.science/pith/TNBEHQGNPZAIJK6OEKAUG7G6TG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TNBEHQGNPZAIJK6OEKAUG7G6TG/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":"2026-08-09T21:04:47Z","links":{"resolver":"https://pith.science/pith/TNBEHQGNPZAIJK6OEKAUG7G6TG","bundle":"https://pith.science/pith/TNBEHQGNPZAIJK6OEKAUG7G6TG/bundle.json","state":"https://pith.science/pith/TNBEHQGNPZAIJK6OEKAUG7G6TG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TNBEHQGNPZAIJK6OEKAUG7G6TG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TNBEHQGNPZAIJK6OEKAUG7G6TG","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":"bf422af79e979d095565f7b106fd2cd2b65413e2245c6115323dc879064d9588","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-10T21:28:15Z","title_canon_sha256":"0a09b20c0119e5432a97e3946fdd8030b8eea3de3b24383e59ace0d1e994d5e5"},"schema_version":"1.0","source":{"id":"2502.07046","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.07046","created_at":"2026-07-05T10:14:50Z"},{"alias_kind":"arxiv_version","alias_value":"2502.07046v2","created_at":"2026-07-05T10:14:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07046","created_at":"2026-07-05T10:14:50Z"},{"alias_kind":"pith_short_12","alias_value":"TNBEHQGNPZAI","created_at":"2026-07-05T10:14:50Z"},{"alias_kind":"pith_short_16","alias_value":"TNBEHQGNPZAIJK6O","created_at":"2026-07-05T10:14:50Z"},{"alias_kind":"pith_short_8","alias_value":"TNBEHQGN","created_at":"2026-07-05T10:14:50Z"}],"graph_snapshots":[{"event_id":"sha256:3a8ceb62c585eda5532b7ffe295e798cfa2b616fdbcdd907710c4be532b28f72","target":"graph","created_at":"2026-07-05T10:14:50Z","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/2502.07046/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language Models (LLMs), such as transformer-based neural networks trained on billions of parameters, have become increasingly prevalent in software engineering (SE). These models, trained on extensive datasets that include code repositories, exhibit remarkable capabilities for SE tasks. However, evaluating their effectiveness poses significant challenges, primarily due to the potential overlap between the datasets used for training and those employed for evaluation. To address this issue, we introduce SnipGen, a comprehensive repository mining framework designed to leverage prompt engineering ","authors_text":"Alejandro Velasco, Daniel Rodriguez-Cardenas, Denys Poshyvanyk","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-10T21:28:15Z","title":"SnipGen: A Mining Repository Framework for Evaluating LLMs for Code"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07046","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":"sha256:36e5d30cd64bc175518eba91f1943f457f5c7d7a0922c752e0b78ef1707a5b81","target":"record","created_at":"2026-07-05T10:14:50Z","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":"bf422af79e979d095565f7b106fd2cd2b65413e2245c6115323dc879064d9588","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-10T21:28:15Z","title_canon_sha256":"0a09b20c0119e5432a97e3946fdd8030b8eea3de3b24383e59ace0d1e994d5e5"},"schema_version":"1.0","source":{"id":"2502.07046","kind":"arxiv","version":2}},"canonical_sha256":"9b4243c0cd7e4084abce2281437cde998db2795e20dc62b4e48dd658eee9875e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9b4243c0cd7e4084abce2281437cde998db2795e20dc62b4e48dd658eee9875e","first_computed_at":"2026-07-05T10:14:50.997942Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:14:50.997942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sPZPaJFap+BaeBNgnupX2FLa9YbYJ4rrRuOeKUwwdauGqmL7yNa/ukaOyNYEWHc2HQtm4aLeBrDkytNgZobDBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:14:50.998447Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.07046","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36e5d30cd64bc175518eba91f1943f457f5c7d7a0922c752e0b78ef1707a5b81","sha256:3a8ceb62c585eda5532b7ffe295e798cfa2b616fdbcdd907710c4be532b28f72"],"state_sha256":"ca0726714560c3a265c68c42ec3d10b7327420edf849b69fa1e13e64df8756f4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JVHAMsT0FfeIC/48llOD1mAy1ow2MGzafOGbvqCZoGAhZzCfWwfV5icHMS1ZDOYNiliVMuileNTXT2/wA7OLDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T21:04:47.917845Z","bundle_sha256":"2b14dda00841d4e4feadcd1ea69fcb956e280a1eb2ef1de38ecc4b11989f7092"}}