{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:57RAVD2EVDHNJXNV73EG5M4ZV4","short_pith_number":"pith:57RAVD2E","canonical_record":{"source":{"id":"2406.19240","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-06-27T15:04:49Z","cross_cats_sorted":[],"title_canon_sha256":"f0259d8dcc2448653bfb2933a9ba69c13e312fd9cd4a82de03e1e51351fec2b9","abstract_canon_sha256":"00a12527db8564780b7bd870e4470a9fa0c4aac69d6e3e4a297c8a7808579624"},"schema_version":"1.0"},"canonical_sha256":"efe20a8f44a8ced4ddb5fec86eb399af2713a0770442bf88f135ce9c77368566","source":{"kind":"arxiv","id":"2406.19240","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.19240","created_at":"2026-07-05T08:37:32Z"},{"alias_kind":"arxiv_version","alias_value":"2406.19240v1","created_at":"2026-07-05T08:37:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.19240","created_at":"2026-07-05T08:37:32Z"},{"alias_kind":"pith_short_12","alias_value":"57RAVD2EVDHN","created_at":"2026-07-05T08:37:32Z"},{"alias_kind":"pith_short_16","alias_value":"57RAVD2EVDHNJXNV","created_at":"2026-07-05T08:37:32Z"},{"alias_kind":"pith_short_8","alias_value":"57RAVD2E","created_at":"2026-07-05T08:37:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:57RAVD2EVDHNJXNV73EG5M4ZV4","target":"record","payload":{"canonical_record":{"source":{"id":"2406.19240","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-06-27T15:04:49Z","cross_cats_sorted":[],"title_canon_sha256":"f0259d8dcc2448653bfb2933a9ba69c13e312fd9cd4a82de03e1e51351fec2b9","abstract_canon_sha256":"00a12527db8564780b7bd870e4470a9fa0c4aac69d6e3e4a297c8a7808579624"},"schema_version":"1.0"},"canonical_sha256":"efe20a8f44a8ced4ddb5fec86eb399af2713a0770442bf88f135ce9c77368566","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:32.189322Z","signature_b64":"DJWag6W6hhZ5KYA+1EtWBkaWUR5qznq+mgrUNvcO6wO57z7yi4v7/8scePedKSYdxTuALBDV7blDlTcHntrWDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efe20a8f44a8ced4ddb5fec86eb399af2713a0770442bf88f135ce9c77368566","last_reissued_at":"2026-07-05T08:37:32.188899Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:32.188899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.19240","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":"2026-07-05T08:37:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DakAPymnykyqHuA2ayTUx3cqHKkH6AJrAGz0vNd+In+4YVjvkTieVHugaeLIVRj0AvNgAhNTLIB0gVTAFdVpAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T15:07:03.092599Z"},"content_sha256":"207499e7ea8ed75511a1bb1a85160e0da2432cb27dd209787c5b4ebe9507463a","schema_version":"1.0","event_id":"sha256:207499e7ea8ed75511a1bb1a85160e0da2432cb27dd209787c5b4ebe9507463a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:57RAVD2EVDHNJXNV73EG5M4ZV4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Preparation for Deep Learning based Code Smell Detection: A Systematic Literature Review","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Fengji Zhang, Jacky Wai Keung, Wenhua Hu, Xiangru Tang, Xiao Yu, Zexian Zhang, Zhen Yang","submitted_at":"2024-06-27T15:04:49Z","abstract_excerpt":"Code Smell Detection (CSD) plays a crucial role in improving software quality and maintainability. And Deep Learning (DL) techniques have emerged as a promising approach for CSD due to their superior performance. However, the effectiveness of DL-based CSD methods heavily relies on the quality of the training data. Despite its importance, little attention has been paid to analyzing the data preparation process. This systematic literature review analyzes the data preparation techniques used in DL-based CSD methods. We identify 36 relevant papers published by December 2023 and provide a thorough "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.19240","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/2406.19240/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":"2026-07-05T08:37:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Npq1CjT+esOQfhYah15id6lkoYxg2BCht+0DgkiekEHzzezl9yj7kGSAAH3j8FdLOwdH6VPKjp3MYvF+Ui8YDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T15:07:03.094787Z"},"content_sha256":"a346d661d90dedc04b13607aeb279ed58acd5bf10e4f61c9995758ac3377354a","schema_version":"1.0","event_id":"sha256:a346d661d90dedc04b13607aeb279ed58acd5bf10e4f61c9995758ac3377354a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/57RAVD2EVDHNJXNV73EG5M4ZV4/bundle.json","state_url":"https://pith.science/pith/57RAVD2EVDHNJXNV73EG5M4ZV4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/57RAVD2EVDHNJXNV73EG5M4ZV4/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":"2026-08-17T15:07:03Z","links":{"resolver":"https://pith.science/pith/57RAVD2EVDHNJXNV73EG5M4ZV4","bundle":"https://pith.science/pith/57RAVD2EVDHNJXNV73EG5M4ZV4/bundle.json","state":"https://pith.science/pith/57RAVD2EVDHNJXNV73EG5M4ZV4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/57RAVD2EVDHNJXNV73EG5M4ZV4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:57RAVD2EVDHNJXNV73EG5M4ZV4","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":"00a12527db8564780b7bd870e4470a9fa0c4aac69d6e3e4a297c8a7808579624","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-06-27T15:04:49Z","title_canon_sha256":"f0259d8dcc2448653bfb2933a9ba69c13e312fd9cd4a82de03e1e51351fec2b9"},"schema_version":"1.0","source":{"id":"2406.19240","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.19240","created_at":"2026-07-05T08:37:32Z"},{"alias_kind":"arxiv_version","alias_value":"2406.19240v1","created_at":"2026-07-05T08:37:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.19240","created_at":"2026-07-05T08:37:32Z"},{"alias_kind":"pith_short_12","alias_value":"57RAVD2EVDHN","created_at":"2026-07-05T08:37:32Z"},{"alias_kind":"pith_short_16","alias_value":"57RAVD2EVDHNJXNV","created_at":"2026-07-05T08:37:32Z"},{"alias_kind":"pith_short_8","alias_value":"57RAVD2E","created_at":"2026-07-05T08:37:32Z"}],"graph_snapshots":[{"event_id":"sha256:a346d661d90dedc04b13607aeb279ed58acd5bf10e4f61c9995758ac3377354a","target":"graph","created_at":"2026-07-05T08:37:32Z","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/2406.19240/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Code Smell Detection (CSD) plays a crucial role in improving software quality and maintainability. And Deep Learning (DL) techniques have emerged as a promising approach for CSD due to their superior performance. However, the effectiveness of DL-based CSD methods heavily relies on the quality of the training data. Despite its importance, little attention has been paid to analyzing the data preparation process. This systematic literature review analyzes the data preparation techniques used in DL-based CSD methods. We identify 36 relevant papers published by December 2023 and provide a thorough ","authors_text":"Fengji Zhang, Jacky Wai Keung, Wenhua Hu, Xiangru Tang, Xiao Yu, Zexian Zhang, Zhen Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-06-27T15:04:49Z","title":"Data Preparation for Deep Learning based Code Smell Detection: A Systematic Literature Review"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.19240","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":"sha256:207499e7ea8ed75511a1bb1a85160e0da2432cb27dd209787c5b4ebe9507463a","target":"record","created_at":"2026-07-05T08:37:32Z","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":"00a12527db8564780b7bd870e4470a9fa0c4aac69d6e3e4a297c8a7808579624","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-06-27T15:04:49Z","title_canon_sha256":"f0259d8dcc2448653bfb2933a9ba69c13e312fd9cd4a82de03e1e51351fec2b9"},"schema_version":"1.0","source":{"id":"2406.19240","kind":"arxiv","version":1}},"canonical_sha256":"efe20a8f44a8ced4ddb5fec86eb399af2713a0770442bf88f135ce9c77368566","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"efe20a8f44a8ced4ddb5fec86eb399af2713a0770442bf88f135ce9c77368566","first_computed_at":"2026-07-05T08:37:32.188899Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:37:32.188899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DJWag6W6hhZ5KYA+1EtWBkaWUR5qznq+mgrUNvcO6wO57z7yi4v7/8scePedKSYdxTuALBDV7blDlTcHntrWDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:37:32.189322Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.19240","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:207499e7ea8ed75511a1bb1a85160e0da2432cb27dd209787c5b4ebe9507463a","sha256:a346d661d90dedc04b13607aeb279ed58acd5bf10e4f61c9995758ac3377354a"],"state_sha256":"98e91514dbbbe900f7ba3e519c70429d8b63170e13e63c72cb2452e1681530bc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ub1kA5JbchA7dWQNj3wXbzjPyr4NShjzKtycDqW5jTpeAPpXgoY5JoQKy9DIyqczyQAUtIit6PvJbzmoO3pCDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T15:07:03.101065Z","bundle_sha256":"1c746c3bc6f56392c7fbe77309cda897c80ca6f0e34e5aa9cd55f73deaeef8fc"}}