{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GA4V5EKFEGLVEC34TLAYBTV2ZK","short_pith_number":"pith:GA4V5EKF","canonical_record":{"source":{"id":"2502.07611","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-11T15:02:19Z","cross_cats_sorted":[],"title_canon_sha256":"094c399fd40038a379fe4dcc43195ae11029c5098cfb513ee1548bfe1ed951bf","abstract_canon_sha256":"03b92443ab376ac1d21ecd47ed8abc908535ab221e53ca0b34a2f879ad5bcf8b"},"schema_version":"1.0"},"canonical_sha256":"30395e91452197520b7c9ac180cebacab958770011bbc4baaaeefb40b4d84517","source":{"kind":"arxiv","id":"2502.07611","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.07611","created_at":"2026-07-05T10:12:40Z"},{"alias_kind":"arxiv_version","alias_value":"2502.07611v1","created_at":"2026-07-05T10:12:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07611","created_at":"2026-07-05T10:12:40Z"},{"alias_kind":"pith_short_12","alias_value":"GA4V5EKFEGLV","created_at":"2026-07-05T10:12:40Z"},{"alias_kind":"pith_short_16","alias_value":"GA4V5EKFEGLVEC34","created_at":"2026-07-05T10:12:40Z"},{"alias_kind":"pith_short_8","alias_value":"GA4V5EKF","created_at":"2026-07-05T10:12:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GA4V5EKFEGLVEC34TLAYBTV2ZK","target":"record","payload":{"canonical_record":{"source":{"id":"2502.07611","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-11T15:02:19Z","cross_cats_sorted":[],"title_canon_sha256":"094c399fd40038a379fe4dcc43195ae11029c5098cfb513ee1548bfe1ed951bf","abstract_canon_sha256":"03b92443ab376ac1d21ecd47ed8abc908535ab221e53ca0b34a2f879ad5bcf8b"},"schema_version":"1.0"},"canonical_sha256":"30395e91452197520b7c9ac180cebacab958770011bbc4baaaeefb40b4d84517","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:40.030858Z","signature_b64":"3vizvu+Uyyn1HVj1e8wwUD8LxRBjsAgjlujMgwt31m5taXh8QS55kA1u50jXO6kzYk/OS5iwOFPeKBJozmqDBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30395e91452197520b7c9ac180cebacab958770011bbc4baaaeefb40b4d84517","last_reissued_at":"2026-07-05T10:12:40.030298Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:40.030298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.07611","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":"2026-07-05T10:12:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gyhi8uMjiv44JaupM6ByGZ5tYfFhdA2X5weZa2MLG4iDfc4tEdc+fDzsWnTb1+X6/l9mKSz22xS9UQsT8d96AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:51:00.185988Z"},"content_sha256":"7cbb5a4d8ab02b400546c2f663508837928b9df9459fa1c3a7bfcb3ddb0f266f","schema_version":"1.0","event_id":"sha256:7cbb5a4d8ab02b400546c2f663508837928b9df9459fa1c3a7bfcb3ddb0f266f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GA4V5EKFEGLVEC34TLAYBTV2ZK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimizing Datasets for Code Summarization: Is Code-Comment Coherence Enough?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Antonio Mastropaolo, Antonio Vitale, Massimiliano Di Penta, Rocco Oliveto, Simone Scalabrino","submitted_at":"2025-02-11T15:02:19Z","abstract_excerpt":"Automated code summarization is a long-standing goal for code comprehension. This task automatically generates documentation using a given method. Deep Learning (DL)-based approaches have been proven beneficial for various software engineering (SE) tasks, including this one. Most state-of-the-art datasets for code summarization are automatically mined from GitHub and, thus, might contain erroneous or sub-optimal examples. Previous work showed that using a simple rule-based approach for removing noisy instances allows for a tangible reduction of the training set size while not reducing the effe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07611","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/2502.07611/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":"2026-07-05T10:12:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5FObRRvbI0mLcHOSQGZyEbVbFmAU/IWa2guyqLdBQCX6FCwcJOvEfJR+Sgng9FygRJOAT1jkb4iiBicQoAJnCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:51:00.186945Z"},"content_sha256":"80d1a58d736e616ff0caef51e69751969dcd55adf50118cf1185c9bded5f4be7","schema_version":"1.0","event_id":"sha256:80d1a58d736e616ff0caef51e69751969dcd55adf50118cf1185c9bded5f4be7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GA4V5EKFEGLVEC34TLAYBTV2ZK/bundle.json","state_url":"https://pith.science/pith/GA4V5EKFEGLVEC34TLAYBTV2ZK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GA4V5EKFEGLVEC34TLAYBTV2ZK/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":"2026-08-04T06:51:00Z","links":{"resolver":"https://pith.science/pith/GA4V5EKFEGLVEC34TLAYBTV2ZK","bundle":"https://pith.science/pith/GA4V5EKFEGLVEC34TLAYBTV2ZK/bundle.json","state":"https://pith.science/pith/GA4V5EKFEGLVEC34TLAYBTV2ZK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GA4V5EKFEGLVEC34TLAYBTV2ZK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GA4V5EKFEGLVEC34TLAYBTV2ZK","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":"03b92443ab376ac1d21ecd47ed8abc908535ab221e53ca0b34a2f879ad5bcf8b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-11T15:02:19Z","title_canon_sha256":"094c399fd40038a379fe4dcc43195ae11029c5098cfb513ee1548bfe1ed951bf"},"schema_version":"1.0","source":{"id":"2502.07611","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.07611","created_at":"2026-07-05T10:12:40Z"},{"alias_kind":"arxiv_version","alias_value":"2502.07611v1","created_at":"2026-07-05T10:12:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07611","created_at":"2026-07-05T10:12:40Z"},{"alias_kind":"pith_short_12","alias_value":"GA4V5EKFEGLV","created_at":"2026-07-05T10:12:40Z"},{"alias_kind":"pith_short_16","alias_value":"GA4V5EKFEGLVEC34","created_at":"2026-07-05T10:12:40Z"},{"alias_kind":"pith_short_8","alias_value":"GA4V5EKF","created_at":"2026-07-05T10:12:40Z"}],"graph_snapshots":[{"event_id":"sha256:80d1a58d736e616ff0caef51e69751969dcd55adf50118cf1185c9bded5f4be7","target":"graph","created_at":"2026-07-05T10:12:40Z","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/2502.07611/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automated code summarization is a long-standing goal for code comprehension. This task automatically generates documentation using a given method. Deep Learning (DL)-based approaches have been proven beneficial for various software engineering (SE) tasks, including this one. Most state-of-the-art datasets for code summarization are automatically mined from GitHub and, thus, might contain erroneous or sub-optimal examples. Previous work showed that using a simple rule-based approach for removing noisy instances allows for a tangible reduction of the training set size while not reducing the effe","authors_text":"Antonio Mastropaolo, Antonio Vitale, Massimiliano Di Penta, Rocco Oliveto, Simone Scalabrino","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-11T15:02:19Z","title":"Optimizing Datasets for Code Summarization: Is Code-Comment Coherence Enough?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07611","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":"sha256:7cbb5a4d8ab02b400546c2f663508837928b9df9459fa1c3a7bfcb3ddb0f266f","target":"record","created_at":"2026-07-05T10:12:40Z","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":"03b92443ab376ac1d21ecd47ed8abc908535ab221e53ca0b34a2f879ad5bcf8b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-11T15:02:19Z","title_canon_sha256":"094c399fd40038a379fe4dcc43195ae11029c5098cfb513ee1548bfe1ed951bf"},"schema_version":"1.0","source":{"id":"2502.07611","kind":"arxiv","version":1}},"canonical_sha256":"30395e91452197520b7c9ac180cebacab958770011bbc4baaaeefb40b4d84517","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30395e91452197520b7c9ac180cebacab958770011bbc4baaaeefb40b4d84517","first_computed_at":"2026-07-05T10:12:40.030298Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:12:40.030298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3vizvu+Uyyn1HVj1e8wwUD8LxRBjsAgjlujMgwt31m5taXh8QS55kA1u50jXO6kzYk/OS5iwOFPeKBJozmqDBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:12:40.030858Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.07611","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7cbb5a4d8ab02b400546c2f663508837928b9df9459fa1c3a7bfcb3ddb0f266f","sha256:80d1a58d736e616ff0caef51e69751969dcd55adf50118cf1185c9bded5f4be7"],"state_sha256":"28bb2755d2a37a9732100879de14a7c9eee2eb252033ea1f7b8be442d9803fe4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9RokLZefQ2F833g0w/rkr5vUEOnjnFmZQSo8swxNHauwVxG5vrrCOyZWMkDTJtv4xm9qdpDNW2dBZdhWllnjDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T06:51:00.196194Z","bundle_sha256":"24590225be357c7292f8887aac42b4ec9a3fd5c02d2395789541d0616943180d"}}