{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GV6O6XCBECKPDNI3PQRYY5IDVM","short_pith_number":"pith:GV6O6XCB","canonical_record":{"source":{"id":"2409.18365","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-09-27T00:49:27Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"16f4a7f405fdf0c137ce9e0612c61915c61862dbd55a243e173daca3fbb7e785","abstract_canon_sha256":"f08fca591bcef93257e411335311eb345cc01dc10d71e4f017c81efb2eb9407c"},"schema_version":"1.0"},"canonical_sha256":"357cef5c412094f1b51b7c238c7503ab3ce3ff1fd3999c6e1b09acd327e317f0","source":{"kind":"arxiv","id":"2409.18365","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.18365","created_at":"2026-07-05T09:12:34Z"},{"alias_kind":"arxiv_version","alias_value":"2409.18365v1","created_at":"2026-07-05T09:12:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.18365","created_at":"2026-07-05T09:12:34Z"},{"alias_kind":"pith_short_12","alias_value":"GV6O6XCBECKP","created_at":"2026-07-05T09:12:34Z"},{"alias_kind":"pith_short_16","alias_value":"GV6O6XCBECKPDNI3","created_at":"2026-07-05T09:12:34Z"},{"alias_kind":"pith_short_8","alias_value":"GV6O6XCB","created_at":"2026-07-05T09:12:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GV6O6XCBECKPDNI3PQRYY5IDVM","target":"record","payload":{"canonical_record":{"source":{"id":"2409.18365","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-09-27T00:49:27Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"16f4a7f405fdf0c137ce9e0612c61915c61862dbd55a243e173daca3fbb7e785","abstract_canon_sha256":"f08fca591bcef93257e411335311eb345cc01dc10d71e4f017c81efb2eb9407c"},"schema_version":"1.0"},"canonical_sha256":"357cef5c412094f1b51b7c238c7503ab3ce3ff1fd3999c6e1b09acd327e317f0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:12:34.878536Z","signature_b64":"5WluowzYexFFL/3X44J+cBCGpeZq44h47AXifC6PWul36dcAhb6JtDqPZG8BvCn5nMve4Mawlp5Hfv+3lefeAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"357cef5c412094f1b51b7c238c7503ab3ce3ff1fd3999c6e1b09acd327e317f0","last_reissued_at":"2026-07-05T09:12:34.878031Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:12:34.878031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.18365","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":"2026-07-05T09:12:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nLYDwG+fbztrJCSqpKq2MnB4zSfcAvhEzEt8JcuDS8Fp9yPyjx95RtRCB9+qFFMCtK1eXSEM0GVnoH9M3jTCAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T07:06:18.091259Z"},"content_sha256":"4c5a3c7c0304be9ad839309ead4d9a27ce572d617b5d426d943796924dc8b08c","schema_version":"1.0","event_id":"sha256:4c5a3c7c0304be9ad839309ead4d9a27ce572d617b5d426d943796924dc8b08c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GV6O6XCBECKPDNI3PQRYY5IDVM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Defect Prediction with Content-based Features","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.SE","authors_text":"Hung Viet Pham, Tung Thanh Nguyen","submitted_at":"2024-09-27T00:49:27Z","abstract_excerpt":"Traditional defect prediction approaches often use metrics that measure the complexity of the design or implementing code of a software system, such as the number of lines of code in a source file. In this paper, we explore a different approach based on content of source code. Our key assumption is that source code of a software system contains information about its technical aspects and those aspects might have different levels of defect-proneness. Thus, content-based features such as words, topics, data types, and package names extracted from a source code file could be used to predict its d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.18365","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/2409.18365/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":"2026-07-05T09:12:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tGdM3DflOIzwJgPjRItm8kmYYRrKoWeIGyYLrY+OgR+Chq2mLV01oDD/jAyxHcu3X8uaZDwKaU7mOhV28giFDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T07:06:18.091658Z"},"content_sha256":"e7d3d2473f51e87a507f73b80a29945e5dd825d70a8a4dfd43cc1ee7b907d3a4","schema_version":"1.0","event_id":"sha256:e7d3d2473f51e87a507f73b80a29945e5dd825d70a8a4dfd43cc1ee7b907d3a4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GV6O6XCBECKPDNI3PQRYY5IDVM/bundle.json","state_url":"https://pith.science/pith/GV6O6XCBECKPDNI3PQRYY5IDVM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GV6O6XCBECKPDNI3PQRYY5IDVM/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":"2026-07-12T07:06:18Z","links":{"resolver":"https://pith.science/pith/GV6O6XCBECKPDNI3PQRYY5IDVM","bundle":"https://pith.science/pith/GV6O6XCBECKPDNI3PQRYY5IDVM/bundle.json","state":"https://pith.science/pith/GV6O6XCBECKPDNI3PQRYY5IDVM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GV6O6XCBECKPDNI3PQRYY5IDVM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GV6O6XCBECKPDNI3PQRYY5IDVM","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":"f08fca591bcef93257e411335311eb345cc01dc10d71e4f017c81efb2eb9407c","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-09-27T00:49:27Z","title_canon_sha256":"16f4a7f405fdf0c137ce9e0612c61915c61862dbd55a243e173daca3fbb7e785"},"schema_version":"1.0","source":{"id":"2409.18365","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.18365","created_at":"2026-07-05T09:12:34Z"},{"alias_kind":"arxiv_version","alias_value":"2409.18365v1","created_at":"2026-07-05T09:12:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.18365","created_at":"2026-07-05T09:12:34Z"},{"alias_kind":"pith_short_12","alias_value":"GV6O6XCBECKP","created_at":"2026-07-05T09:12:34Z"},{"alias_kind":"pith_short_16","alias_value":"GV6O6XCBECKPDNI3","created_at":"2026-07-05T09:12:34Z"},{"alias_kind":"pith_short_8","alias_value":"GV6O6XCB","created_at":"2026-07-05T09:12:34Z"}],"graph_snapshots":[{"event_id":"sha256:e7d3d2473f51e87a507f73b80a29945e5dd825d70a8a4dfd43cc1ee7b907d3a4","target":"graph","created_at":"2026-07-05T09:12:34Z","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/2409.18365/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Traditional defect prediction approaches often use metrics that measure the complexity of the design or implementing code of a software system, such as the number of lines of code in a source file. In this paper, we explore a different approach based on content of source code. Our key assumption is that source code of a software system contains information about its technical aspects and those aspects might have different levels of defect-proneness. Thus, content-based features such as words, topics, data types, and package names extracted from a source code file could be used to predict its d","authors_text":"Hung Viet Pham, Tung Thanh Nguyen","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-09-27T00:49:27Z","title":"Defect Prediction with Content-based Features"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.18365","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":"sha256:4c5a3c7c0304be9ad839309ead4d9a27ce572d617b5d426d943796924dc8b08c","target":"record","created_at":"2026-07-05T09:12:34Z","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":"f08fca591bcef93257e411335311eb345cc01dc10d71e4f017c81efb2eb9407c","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-09-27T00:49:27Z","title_canon_sha256":"16f4a7f405fdf0c137ce9e0612c61915c61862dbd55a243e173daca3fbb7e785"},"schema_version":"1.0","source":{"id":"2409.18365","kind":"arxiv","version":1}},"canonical_sha256":"357cef5c412094f1b51b7c238c7503ab3ce3ff1fd3999c6e1b09acd327e317f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"357cef5c412094f1b51b7c238c7503ab3ce3ff1fd3999c6e1b09acd327e317f0","first_computed_at":"2026-07-05T09:12:34.878031Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:12:34.878031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5WluowzYexFFL/3X44J+cBCGpeZq44h47AXifC6PWul36dcAhb6JtDqPZG8BvCn5nMve4Mawlp5Hfv+3lefeAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:12:34.878536Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.18365","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4c5a3c7c0304be9ad839309ead4d9a27ce572d617b5d426d943796924dc8b08c","sha256:e7d3d2473f51e87a507f73b80a29945e5dd825d70a8a4dfd43cc1ee7b907d3a4"],"state_sha256":"3b555de849ee1a453837b28d14c0ed3529a8a9dcc747a2a14514a5d6beee559c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GnG6kZVFNfxECI5yJzFKM2cJ8E/Ofi3Aqbg7abf1gDKfs92JgruO+QiJqUWH5i0gXnBhYltM8nPOtF2ODk0iBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-12T07:06:18.093751Z","bundle_sha256":"e99ec97002ee5a946d640cbe7d644e7b6e3bf5eb9981e0eece642655cb686cf5"}}