{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:JWHJVUOGWB3CB4KGHGIB6EUONF","short_pith_number":"pith:JWHJVUOG","canonical_record":{"source":{"id":"2008.03835","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2020-08-09T23:14:20Z","cross_cats_sorted":[],"title_canon_sha256":"28bc21d82c99ce617d35c655c6013912e6841e950a504148a07c2a1a2f0f80eb","abstract_canon_sha256":"8cad7664e640005303255adc8044577a70ccd1c6c8c01f112b1a0e2031bc2b28"},"schema_version":"1.0"},"canonical_sha256":"4d8e9ad1c6b07620f14639901f128e697007d852b28fff59f9688a31b1e05309","source":{"kind":"arxiv","id":"2008.03835","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.03835","created_at":"2026-07-05T02:33:54Z"},{"alias_kind":"arxiv_version","alias_value":"2008.03835v3","created_at":"2026-07-05T02:33:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.03835","created_at":"2026-07-05T02:33:54Z"},{"alias_kind":"pith_short_12","alias_value":"JWHJVUOGWB3C","created_at":"2026-07-05T02:33:54Z"},{"alias_kind":"pith_short_16","alias_value":"JWHJVUOGWB3CB4KG","created_at":"2026-07-05T02:33:54Z"},{"alias_kind":"pith_short_8","alias_value":"JWHJVUOG","created_at":"2026-07-05T02:33:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:JWHJVUOGWB3CB4KGHGIB6EUONF","target":"record","payload":{"canonical_record":{"source":{"id":"2008.03835","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2020-08-09T23:14:20Z","cross_cats_sorted":[],"title_canon_sha256":"28bc21d82c99ce617d35c655c6013912e6841e950a504148a07c2a1a2f0f80eb","abstract_canon_sha256":"8cad7664e640005303255adc8044577a70ccd1c6c8c01f112b1a0e2031bc2b28"},"schema_version":"1.0"},"canonical_sha256":"4d8e9ad1c6b07620f14639901f128e697007d852b28fff59f9688a31b1e05309","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:33:54.419570Z","signature_b64":"ZQ5DKeSmMaeLIHFWUVg9vSK76BA2GRXNh2KfpbVFRX2/zFugkBk/4AqfwflLU1MglNl1ezvcChOw7UnahiUXAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d8e9ad1c6b07620f14639901f128e697007d852b28fff59f9688a31b1e05309","last_reissued_at":"2026-07-05T02:33:54.419099Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:33:54.419099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2008.03835","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":"2026-07-05T02:33:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lSFao8Rpr34rPxVn6gseCX/Y9Zj2VvpFuCY3oltlG71z0+AYlbe7QncGMiQBv7K8vJskB4/fkPIixYqc+FP8Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T14:38:18.758889Z"},"content_sha256":"60cca480ea2e9712fb7a66d5086bf6362f1756b0e93f2ff0322d67199152b9d1","schema_version":"1.0","event_id":"sha256:60cca480ea2e9712fb7a66d5086bf6362f1756b0e93f2ff0322d67199152b9d1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:JWHJVUOGWB3CB4KGHGIB6EUONF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Value of Oversampling for Deep Learning in Software Defect Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Rahul Yedida, Tim Menzies","submitted_at":"2020-08-09T23:14:20Z","abstract_excerpt":"One truism of deep learning is that the automatic feature engineering (seen in the first layers of those networks) excuses data scientists from performing tedious manual feature engineering prior to running DL. For the specific case of deep learning for defect prediction, we show that that truism is false. Specifically, when we preprocess data with a novel oversampling technique called fuzzy sampling, as part of a larger pipeline called GHOST (Goal-oriented Hyper-parameter Optimization for Scalable Training), then we can do significantly better than the prior DL state of the art in 14/20 defec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.03835","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/2008.03835/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":"2026-07-05T02:33:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"woa3o6/MvQ5JzinkI4BNi9SQGAx6jg/5c4wrisNaaIbYLJlZeb0Zw9eusVcQPrvjKlD90gLi1KIEOz6sXuzQDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T14:38:18.759273Z"},"content_sha256":"6acceed34524f7496f6e5d1d727f5047aae3552645d78c2b5caedfc7c40d0571","schema_version":"1.0","event_id":"sha256:6acceed34524f7496f6e5d1d727f5047aae3552645d78c2b5caedfc7c40d0571"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JWHJVUOGWB3CB4KGHGIB6EUONF/bundle.json","state_url":"https://pith.science/pith/JWHJVUOGWB3CB4KGHGIB6EUONF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JWHJVUOGWB3CB4KGHGIB6EUONF/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":"2026-07-11T14:38:18Z","links":{"resolver":"https://pith.science/pith/JWHJVUOGWB3CB4KGHGIB6EUONF","bundle":"https://pith.science/pith/JWHJVUOGWB3CB4KGHGIB6EUONF/bundle.json","state":"https://pith.science/pith/JWHJVUOGWB3CB4KGHGIB6EUONF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JWHJVUOGWB3CB4KGHGIB6EUONF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:JWHJVUOGWB3CB4KGHGIB6EUONF","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":"8cad7664e640005303255adc8044577a70ccd1c6c8c01f112b1a0e2031bc2b28","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2020-08-09T23:14:20Z","title_canon_sha256":"28bc21d82c99ce617d35c655c6013912e6841e950a504148a07c2a1a2f0f80eb"},"schema_version":"1.0","source":{"id":"2008.03835","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.03835","created_at":"2026-07-05T02:33:54Z"},{"alias_kind":"arxiv_version","alias_value":"2008.03835v3","created_at":"2026-07-05T02:33:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.03835","created_at":"2026-07-05T02:33:54Z"},{"alias_kind":"pith_short_12","alias_value":"JWHJVUOGWB3C","created_at":"2026-07-05T02:33:54Z"},{"alias_kind":"pith_short_16","alias_value":"JWHJVUOGWB3CB4KG","created_at":"2026-07-05T02:33:54Z"},{"alias_kind":"pith_short_8","alias_value":"JWHJVUOG","created_at":"2026-07-05T02:33:54Z"}],"graph_snapshots":[{"event_id":"sha256:6acceed34524f7496f6e5d1d727f5047aae3552645d78c2b5caedfc7c40d0571","target":"graph","created_at":"2026-07-05T02:33:54Z","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/2008.03835/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One truism of deep learning is that the automatic feature engineering (seen in the first layers of those networks) excuses data scientists from performing tedious manual feature engineering prior to running DL. For the specific case of deep learning for defect prediction, we show that that truism is false. Specifically, when we preprocess data with a novel oversampling technique called fuzzy sampling, as part of a larger pipeline called GHOST (Goal-oriented Hyper-parameter Optimization for Scalable Training), then we can do significantly better than the prior DL state of the art in 14/20 defec","authors_text":"Rahul Yedida, Tim Menzies","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2020-08-09T23:14:20Z","title":"On the Value of Oversampling for Deep Learning in Software Defect Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.03835","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":"sha256:60cca480ea2e9712fb7a66d5086bf6362f1756b0e93f2ff0322d67199152b9d1","target":"record","created_at":"2026-07-05T02:33:54Z","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":"8cad7664e640005303255adc8044577a70ccd1c6c8c01f112b1a0e2031bc2b28","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2020-08-09T23:14:20Z","title_canon_sha256":"28bc21d82c99ce617d35c655c6013912e6841e950a504148a07c2a1a2f0f80eb"},"schema_version":"1.0","source":{"id":"2008.03835","kind":"arxiv","version":3}},"canonical_sha256":"4d8e9ad1c6b07620f14639901f128e697007d852b28fff59f9688a31b1e05309","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d8e9ad1c6b07620f14639901f128e697007d852b28fff59f9688a31b1e05309","first_computed_at":"2026-07-05T02:33:54.419099Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:33:54.419099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZQ5DKeSmMaeLIHFWUVg9vSK76BA2GRXNh2KfpbVFRX2/zFugkBk/4AqfwflLU1MglNl1ezvcChOw7UnahiUXAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:33:54.419570Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.03835","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:60cca480ea2e9712fb7a66d5086bf6362f1756b0e93f2ff0322d67199152b9d1","sha256:6acceed34524f7496f6e5d1d727f5047aae3552645d78c2b5caedfc7c40d0571"],"state_sha256":"403e8ad17c73aa639f6c78c05713cf4963dfa230f0dd8f5135ede883b0feb385"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C65BO96CQN7u71KL94gtH6+c9Zu1t0ocwfqvdECJWHNQZYvH54gGLKc9PJ9YzQNFT0sCIVUZAeFdcZ4PYYBQBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-11T14:38:18.761525Z","bundle_sha256":"acc779dc4a6d6c8e08861071736cd4fa4099336560922f6296915557a751a7ce"}}