{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LJSRK6U4PSKBUCR6YZJQL5JKEN","short_pith_number":"pith:LJSRK6U4","canonical_record":{"source":{"id":"2412.01007","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-01T23:54:12Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"c213275ef454886de154e85488fb9d5ce99240e444a99e17fe30764448e6dee3","abstract_canon_sha256":"810a4265fab0ad872fdb34b0a6c2531ca7f798b578b1c3469b2d17806d1ced11"},"schema_version":"1.0"},"canonical_sha256":"5a65157a9c7c941a0a3ec65305f52a2345abc7e922886bce0cc57a9491d6fc31","source":{"kind":"arxiv","id":"2412.01007","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.01007","created_at":"2026-07-05T10:23:27Z"},{"alias_kind":"arxiv_version","alias_value":"2412.01007v3","created_at":"2026-07-05T10:23:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01007","created_at":"2026-07-05T10:23:27Z"},{"alias_kind":"pith_short_12","alias_value":"LJSRK6U4PSKB","created_at":"2026-07-05T10:23:27Z"},{"alias_kind":"pith_short_16","alias_value":"LJSRK6U4PSKBUCR6","created_at":"2026-07-05T10:23:27Z"},{"alias_kind":"pith_short_8","alias_value":"LJSRK6U4","created_at":"2026-07-05T10:23:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LJSRK6U4PSKBUCR6YZJQL5JKEN","target":"record","payload":{"canonical_record":{"source":{"id":"2412.01007","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-01T23:54:12Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"c213275ef454886de154e85488fb9d5ce99240e444a99e17fe30764448e6dee3","abstract_canon_sha256":"810a4265fab0ad872fdb34b0a6c2531ca7f798b578b1c3469b2d17806d1ced11"},"schema_version":"1.0"},"canonical_sha256":"5a65157a9c7c941a0a3ec65305f52a2345abc7e922886bce0cc57a9491d6fc31","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:23:27.163905Z","signature_b64":"Zje6BUYIVqzWWvLcKN37dAfIW0Ge4zTc1GnZ1o12bqR2qEq1Xln35ffTa4Vl5RutPpW2x8Rz9oyFQ0sOa0WUBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a65157a9c7c941a0a3ec65305f52a2345abc7e922886bce0cc57a9491d6fc31","last_reissued_at":"2026-07-05T10:23:27.163038Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:23:27.163038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.01007","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":"2026-07-05T10:23:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"knK1/KU9bo+ra3l6ZQB989TI4oqh1iRu2zz/MI1aNFYYuQPSB8f+xbWo63hL8vpMkFaXDoOYwVt3N3I4bv8+DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:52:55.443316Z"},"content_sha256":"00636d66c225e2b11068dcd52179bec818cfd4b17419d3a6ec7c2e9003bd4700","schema_version":"1.0","event_id":"sha256:00636d66c225e2b11068dcd52179bec818cfd4b17419d3a6ec7c2e9003bd4700"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LJSRK6U4PSKBUCR6YZJQL5JKEN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Andriy Mulyar, Brandon Duderstadt, Heng Ji, Revanth Gangi Reddy, Tarun Suresh, Yifei Xu, Zach Nussbaum","submitted_at":"2024-12-01T23:54:12Z","abstract_excerpt":"Effective code retrieval plays a crucial role in advancing code generation, bug fixing, and software maintenance, particularly as software systems increase in complexity. While current code embedding models have demonstrated promise in retrieving code snippets for small-scale, well-defined tasks, they often underperform in more demanding real-world applications such as bug localization within GitHub repositories. We hypothesize that a key issue is their reliance on noisy and inconsistent datasets for training, which impedes their ability to generalize to more complex retrieval scenarios. To ad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01007","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/2412.01007/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":"2026-07-05T10:23:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g164c5+GyAXxyFLXwQvba78ZLeKdoziOptH+VMPywHU9R9LHdhpcddIXiNAiqACVOT0zY1ts40tuYbNasyEFBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:52:55.443906Z"},"content_sha256":"5948a3db5ba6b42f3b90829f72543862c0461289aca359a1ec6ff3df3d50f8b0","schema_version":"1.0","event_id":"sha256:5948a3db5ba6b42f3b90829f72543862c0461289aca359a1ec6ff3df3d50f8b0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LJSRK6U4PSKBUCR6YZJQL5JKEN/bundle.json","state_url":"https://pith.science/pith/LJSRK6U4PSKBUCR6YZJQL5JKEN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LJSRK6U4PSKBUCR6YZJQL5JKEN/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":"2026-08-09T22:52:55Z","links":{"resolver":"https://pith.science/pith/LJSRK6U4PSKBUCR6YZJQL5JKEN","bundle":"https://pith.science/pith/LJSRK6U4PSKBUCR6YZJQL5JKEN/bundle.json","state":"https://pith.science/pith/LJSRK6U4PSKBUCR6YZJQL5JKEN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LJSRK6U4PSKBUCR6YZJQL5JKEN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LJSRK6U4PSKBUCR6YZJQL5JKEN","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":"810a4265fab0ad872fdb34b0a6c2531ca7f798b578b1c3469b2d17806d1ced11","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-01T23:54:12Z","title_canon_sha256":"c213275ef454886de154e85488fb9d5ce99240e444a99e17fe30764448e6dee3"},"schema_version":"1.0","source":{"id":"2412.01007","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.01007","created_at":"2026-07-05T10:23:27Z"},{"alias_kind":"arxiv_version","alias_value":"2412.01007v3","created_at":"2026-07-05T10:23:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01007","created_at":"2026-07-05T10:23:27Z"},{"alias_kind":"pith_short_12","alias_value":"LJSRK6U4PSKB","created_at":"2026-07-05T10:23:27Z"},{"alias_kind":"pith_short_16","alias_value":"LJSRK6U4PSKBUCR6","created_at":"2026-07-05T10:23:27Z"},{"alias_kind":"pith_short_8","alias_value":"LJSRK6U4","created_at":"2026-07-05T10:23:27Z"}],"graph_snapshots":[{"event_id":"sha256:5948a3db5ba6b42f3b90829f72543862c0461289aca359a1ec6ff3df3d50f8b0","target":"graph","created_at":"2026-07-05T10:23:27Z","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/2412.01007/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Effective code retrieval plays a crucial role in advancing code generation, bug fixing, and software maintenance, particularly as software systems increase in complexity. While current code embedding models have demonstrated promise in retrieving code snippets for small-scale, well-defined tasks, they often underperform in more demanding real-world applications such as bug localization within GitHub repositories. We hypothesize that a key issue is their reliance on noisy and inconsistent datasets for training, which impedes their ability to generalize to more complex retrieval scenarios. To ad","authors_text":"Andriy Mulyar, Brandon Duderstadt, Heng Ji, Revanth Gangi Reddy, Tarun Suresh, Yifei Xu, Zach Nussbaum","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-01T23:54:12Z","title":"CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01007","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":"sha256:00636d66c225e2b11068dcd52179bec818cfd4b17419d3a6ec7c2e9003bd4700","target":"record","created_at":"2026-07-05T10:23:27Z","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":"810a4265fab0ad872fdb34b0a6c2531ca7f798b578b1c3469b2d17806d1ced11","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-01T23:54:12Z","title_canon_sha256":"c213275ef454886de154e85488fb9d5ce99240e444a99e17fe30764448e6dee3"},"schema_version":"1.0","source":{"id":"2412.01007","kind":"arxiv","version":3}},"canonical_sha256":"5a65157a9c7c941a0a3ec65305f52a2345abc7e922886bce0cc57a9491d6fc31","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a65157a9c7c941a0a3ec65305f52a2345abc7e922886bce0cc57a9491d6fc31","first_computed_at":"2026-07-05T10:23:27.163038Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:23:27.163038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zje6BUYIVqzWWvLcKN37dAfIW0Ge4zTc1GnZ1o12bqR2qEq1Xln35ffTa4Vl5RutPpW2x8Rz9oyFQ0sOa0WUBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:23:27.163905Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.01007","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:00636d66c225e2b11068dcd52179bec818cfd4b17419d3a6ec7c2e9003bd4700","sha256:5948a3db5ba6b42f3b90829f72543862c0461289aca359a1ec6ff3df3d50f8b0"],"state_sha256":"5d8b5cb97485b56e88ab2fc6c9397d952f5580d39de07ba3569ca94e250f200b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J1e6nhuFnzvryJA+Ljyis5apkJBav2kfzc+SOhjJ3wbMxPz/BMP+JHX66nSohI6jkq1+k4QN1xy2y5oGJ1aMCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T22:52:55.449313Z","bundle_sha256":"24ef7465b5b69f20693213c046adb1c9efd09863d45e37f637bbcad21e2c3694"}}