{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:U2IGGOA7V5AOKYVOKTCTG27FCO","short_pith_number":"pith:U2IGGOA7","canonical_record":{"source":{"id":"2502.02757","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-04T22:48:58Z","cross_cats_sorted":[],"title_canon_sha256":"8833eb99e5397d43d4b94c1e2d42a2aaf5efa3ad5c305e7c9d0bdf2e6c4a45b6","abstract_canon_sha256":"08dd2d5fbac46e4d9ea768e6e963959920ee01ef1ebdbe49a9641e5dc5208b2f"},"schema_version":"1.0"},"canonical_sha256":"a69063381faf40e562ae54c5336be5138083c81b579aaae59cfd47f7bba60cb5","source":{"kind":"arxiv","id":"2502.02757","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.02757","created_at":"2026-07-05T10:10:10Z"},{"alias_kind":"arxiv_version","alias_value":"2502.02757v2","created_at":"2026-07-05T10:10:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02757","created_at":"2026-07-05T10:10:10Z"},{"alias_kind":"pith_short_12","alias_value":"U2IGGOA7V5AO","created_at":"2026-07-05T10:10:10Z"},{"alias_kind":"pith_short_16","alias_value":"U2IGGOA7V5AOKYVO","created_at":"2026-07-05T10:10:10Z"},{"alias_kind":"pith_short_8","alias_value":"U2IGGOA7","created_at":"2026-07-05T10:10:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:U2IGGOA7V5AOKYVOKTCTG27FCO","target":"record","payload":{"canonical_record":{"source":{"id":"2502.02757","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-04T22:48:58Z","cross_cats_sorted":[],"title_canon_sha256":"8833eb99e5397d43d4b94c1e2d42a2aaf5efa3ad5c305e7c9d0bdf2e6c4a45b6","abstract_canon_sha256":"08dd2d5fbac46e4d9ea768e6e963959920ee01ef1ebdbe49a9641e5dc5208b2f"},"schema_version":"1.0"},"canonical_sha256":"a69063381faf40e562ae54c5336be5138083c81b579aaae59cfd47f7bba60cb5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:10.646106Z","signature_b64":"TD478NW0aGsVY7BqDSF/0XZjjsBcZPZozoZgDnqx9AzNoc61g+rp9DHeWhS6/b4XxMOYMva1lW2wztOwRQ0DBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a69063381faf40e562ae54c5336be5138083c81b579aaae59cfd47f7bba60cb5","last_reissued_at":"2026-07-05T10:10:10.645684Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:10.645684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.02757","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":"2026-07-05T10:10:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0QEGN+c4NqpM591lX8BbbVQu0U/gJZzmqgXSp832OmFmzH5ylpcUtxiiCc5l74zln36ZiHEzVamPYFDWZK+FBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:15:16.250811Z"},"content_sha256":"8460c4944554d5c39431fc88327002e3c06ba000bdf59eb20ddbf6931a12c84f","schema_version":"1.0","event_id":"sha256:8460c4944554d5c39431fc88327002e3c06ba000bdf59eb20ddbf6931a12c84f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:U2IGGOA7V5AOKYVOKTCTG27FCO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Too Noisy To Learn: Enhancing Data Quality for Code Review Comment Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Chunhua Liu, Hong Yi Lin, Patanamon Thongtanunam","submitted_at":"2025-02-04T22:48:58Z","abstract_excerpt":"Code review is an important practice in software development, yet it is time-consuming and requires substantial effort. While open-source datasets have been used to train neural models for automating code review tasks, including review comment generation, these datasets contain a significant amount of noisy comments (e.g., vague or non-actionable feedback) that persist despite cleaning methods using heuristics and machine learning approaches. Such remaining noise may lead models to generate low-quality review comments, yet removing them requires a complex semantic understanding of both code ch"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02757","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/2502.02757/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":"2026-07-05T10:10:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iCC9J7IIt+5+IqGAo/+VQl7n2tQfjRe1bpYayUeEROEuDD8xEvPjA2lgfkNXAK7dA/qovAKUMMBILDovGMr/BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:15:16.251302Z"},"content_sha256":"59b0a0b84d425e2c9c5518f6ff4da0e1a85dafd354d83a72331fa70bfac50ac5","schema_version":"1.0","event_id":"sha256:59b0a0b84d425e2c9c5518f6ff4da0e1a85dafd354d83a72331fa70bfac50ac5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U2IGGOA7V5AOKYVOKTCTG27FCO/bundle.json","state_url":"https://pith.science/pith/U2IGGOA7V5AOKYVOKTCTG27FCO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U2IGGOA7V5AOKYVOKTCTG27FCO/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":"2026-08-08T16:15:16Z","links":{"resolver":"https://pith.science/pith/U2IGGOA7V5AOKYVOKTCTG27FCO","bundle":"https://pith.science/pith/U2IGGOA7V5AOKYVOKTCTG27FCO/bundle.json","state":"https://pith.science/pith/U2IGGOA7V5AOKYVOKTCTG27FCO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U2IGGOA7V5AOKYVOKTCTG27FCO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:U2IGGOA7V5AOKYVOKTCTG27FCO","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":"08dd2d5fbac46e4d9ea768e6e963959920ee01ef1ebdbe49a9641e5dc5208b2f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-04T22:48:58Z","title_canon_sha256":"8833eb99e5397d43d4b94c1e2d42a2aaf5efa3ad5c305e7c9d0bdf2e6c4a45b6"},"schema_version":"1.0","source":{"id":"2502.02757","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.02757","created_at":"2026-07-05T10:10:10Z"},{"alias_kind":"arxiv_version","alias_value":"2502.02757v2","created_at":"2026-07-05T10:10:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02757","created_at":"2026-07-05T10:10:10Z"},{"alias_kind":"pith_short_12","alias_value":"U2IGGOA7V5AO","created_at":"2026-07-05T10:10:10Z"},{"alias_kind":"pith_short_16","alias_value":"U2IGGOA7V5AOKYVO","created_at":"2026-07-05T10:10:10Z"},{"alias_kind":"pith_short_8","alias_value":"U2IGGOA7","created_at":"2026-07-05T10:10:10Z"}],"graph_snapshots":[{"event_id":"sha256:59b0a0b84d425e2c9c5518f6ff4da0e1a85dafd354d83a72331fa70bfac50ac5","target":"graph","created_at":"2026-07-05T10:10:10Z","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/2502.02757/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Code review is an important practice in software development, yet it is time-consuming and requires substantial effort. While open-source datasets have been used to train neural models for automating code review tasks, including review comment generation, these datasets contain a significant amount of noisy comments (e.g., vague or non-actionable feedback) that persist despite cleaning methods using heuristics and machine learning approaches. Such remaining noise may lead models to generate low-quality review comments, yet removing them requires a complex semantic understanding of both code ch","authors_text":"Chunhua Liu, Hong Yi Lin, Patanamon Thongtanunam","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-04T22:48:58Z","title":"Too Noisy To Learn: Enhancing Data Quality for Code Review Comment Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02757","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":"sha256:8460c4944554d5c39431fc88327002e3c06ba000bdf59eb20ddbf6931a12c84f","target":"record","created_at":"2026-07-05T10:10:10Z","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":"08dd2d5fbac46e4d9ea768e6e963959920ee01ef1ebdbe49a9641e5dc5208b2f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-04T22:48:58Z","title_canon_sha256":"8833eb99e5397d43d4b94c1e2d42a2aaf5efa3ad5c305e7c9d0bdf2e6c4a45b6"},"schema_version":"1.0","source":{"id":"2502.02757","kind":"arxiv","version":2}},"canonical_sha256":"a69063381faf40e562ae54c5336be5138083c81b579aaae59cfd47f7bba60cb5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a69063381faf40e562ae54c5336be5138083c81b579aaae59cfd47f7bba60cb5","first_computed_at":"2026-07-05T10:10:10.645684Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:10:10.645684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TD478NW0aGsVY7BqDSF/0XZjjsBcZPZozoZgDnqx9AzNoc61g+rp9DHeWhS6/b4XxMOYMva1lW2wztOwRQ0DBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:10:10.646106Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.02757","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8460c4944554d5c39431fc88327002e3c06ba000bdf59eb20ddbf6931a12c84f","sha256:59b0a0b84d425e2c9c5518f6ff4da0e1a85dafd354d83a72331fa70bfac50ac5"],"state_sha256":"0d8c477a700e939b1ac8d17159842fa0080ec14549c56750bd2cc37bc6a9fa0f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2P08x/Ec1VnJHavXqCvUOvR6k18D+jHielEysdBXgUSmtr+4rc1SH/xeJegRFGuBjdCXY++Md34lnbBZBGXLBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T16:15:16.254848Z","bundle_sha256":"b50714601397c869907df554a329f567ae080f73f78293985a31b34593e989eb"}}