{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:7XZPPESBLIL4QBNGMC2FR2CBRQ","short_pith_number":"pith:7XZPPESB","canonical_record":{"source":{"id":"2204.04247","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2022-04-08T18:38:02Z","cross_cats_sorted":[],"title_canon_sha256":"c75d9ec7156aba37d02906ac4c79b00643a5bbdba1960e8e10d0272356179954","abstract_canon_sha256":"587305a4e4c71b261e9d05270745cecf7caab23d25a428c25edbd4c1f3e13fbe"},"schema_version":"1.0"},"canonical_sha256":"fdf2f792415a17c805a660b458e8418c0579d993b066a2c9535caf37478d996e","source":{"kind":"arxiv","id":"2204.04247","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.04247","created_at":"2026-07-05T04:12:54Z"},{"alias_kind":"arxiv_version","alias_value":"2204.04247v1","created_at":"2026-07-05T04:12:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.04247","created_at":"2026-07-05T04:12:54Z"},{"alias_kind":"pith_short_12","alias_value":"7XZPPESBLIL4","created_at":"2026-07-05T04:12:54Z"},{"alias_kind":"pith_short_16","alias_value":"7XZPPESBLIL4QBNG","created_at":"2026-07-05T04:12:54Z"},{"alias_kind":"pith_short_8","alias_value":"7XZPPESB","created_at":"2026-07-05T04:12:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:7XZPPESBLIL4QBNGMC2FR2CBRQ","target":"record","payload":{"canonical_record":{"source":{"id":"2204.04247","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2022-04-08T18:38:02Z","cross_cats_sorted":[],"title_canon_sha256":"c75d9ec7156aba37d02906ac4c79b00643a5bbdba1960e8e10d0272356179954","abstract_canon_sha256":"587305a4e4c71b261e9d05270745cecf7caab23d25a428c25edbd4c1f3e13fbe"},"schema_version":"1.0"},"canonical_sha256":"fdf2f792415a17c805a660b458e8418c0579d993b066a2c9535caf37478d996e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:12:54.857767Z","signature_b64":"7zw5e52Po7X8yGmvozg07gcNf8rVJ78MZuZFanKi3nouoUEc/cG0NHwkQL3wc0CUJyI8Fh2mf/kds4pZ4TOBBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fdf2f792415a17c805a660b458e8418c0579d993b066a2c9535caf37478d996e","last_reissued_at":"2026-07-05T04:12:54.857326Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:12:54.857326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.04247","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":"2026-07-05T04:12:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/qVwz7DAJBYmcP8qh7xWC2gXDKLoH0ynXFlhfj3S+LLuR3cQb9+QNt1n6/OiLYBQrCfHrqyFjGyGTj/x4IZXDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:51:31.107344Z"},"content_sha256":"d278cbc5e88493287973f69c919465f7033327b4d483c3250b60ef4265b555f0","schema_version":"1.0","event_id":"sha256:d278cbc5e88493287973f69c919465f7033327b4d483c3250b60ef4265b555f0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:7XZPPESBLIL4QBNGMC2FR2CBRQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Clone Detection on Large Scala Codebases","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Baowen Xu, Fan Pu, Fan Wu, Jifeng Xuan, Leslie Kanthan, Lingbo Li, Michail Basios, Wahidur Rahman, Xiangyang Jia, Yisen Xu","submitted_at":"2022-04-08T18:38:02Z","abstract_excerpt":"Code clones are identical or similar code segments. The wide existence of code clones can increase the cost of maintenance and jeopardise the quality of software. The research community has developed many techniques to detect code clones, however, there is little evidence of how these techniques may perform in industrial use cases. In this paper, we aim to uncover the differences when such techniques are applied in industrial use cases. We conducted large scale experimental research on the performance of two state-of-the-art code clone detection techniques, SourcererCC and AutoenCODE, on both "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.04247","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/2204.04247/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":"2026-07-05T04:12:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zkCOQI1ip3PdMPsSOQ3bb/VjRmhie+arK9xsgd+vy5vJ/CaH4jOLFp4vk/YBmLdljZM793eVtDZNyCIR/YWoAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:51:31.107840Z"},"content_sha256":"daac9097ce3c88244ca424a59b935cb5d18ba593f9be457fc1e8659ccbde1076","schema_version":"1.0","event_id":"sha256:daac9097ce3c88244ca424a59b935cb5d18ba593f9be457fc1e8659ccbde1076"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7XZPPESBLIL4QBNGMC2FR2CBRQ/bundle.json","state_url":"https://pith.science/pith/7XZPPESBLIL4QBNGMC2FR2CBRQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7XZPPESBLIL4QBNGMC2FR2CBRQ/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":"2026-08-05T20:51:31Z","links":{"resolver":"https://pith.science/pith/7XZPPESBLIL4QBNGMC2FR2CBRQ","bundle":"https://pith.science/pith/7XZPPESBLIL4QBNGMC2FR2CBRQ/bundle.json","state":"https://pith.science/pith/7XZPPESBLIL4QBNGMC2FR2CBRQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7XZPPESBLIL4QBNGMC2FR2CBRQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:7XZPPESBLIL4QBNGMC2FR2CBRQ","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":"587305a4e4c71b261e9d05270745cecf7caab23d25a428c25edbd4c1f3e13fbe","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2022-04-08T18:38:02Z","title_canon_sha256":"c75d9ec7156aba37d02906ac4c79b00643a5bbdba1960e8e10d0272356179954"},"schema_version":"1.0","source":{"id":"2204.04247","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.04247","created_at":"2026-07-05T04:12:54Z"},{"alias_kind":"arxiv_version","alias_value":"2204.04247v1","created_at":"2026-07-05T04:12:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.04247","created_at":"2026-07-05T04:12:54Z"},{"alias_kind":"pith_short_12","alias_value":"7XZPPESBLIL4","created_at":"2026-07-05T04:12:54Z"},{"alias_kind":"pith_short_16","alias_value":"7XZPPESBLIL4QBNG","created_at":"2026-07-05T04:12:54Z"},{"alias_kind":"pith_short_8","alias_value":"7XZPPESB","created_at":"2026-07-05T04:12:54Z"}],"graph_snapshots":[{"event_id":"sha256:daac9097ce3c88244ca424a59b935cb5d18ba593f9be457fc1e8659ccbde1076","target":"graph","created_at":"2026-07-05T04:12:54Z","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/2204.04247/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Code clones are identical or similar code segments. The wide existence of code clones can increase the cost of maintenance and jeopardise the quality of software. The research community has developed many techniques to detect code clones, however, there is little evidence of how these techniques may perform in industrial use cases. In this paper, we aim to uncover the differences when such techniques are applied in industrial use cases. We conducted large scale experimental research on the performance of two state-of-the-art code clone detection techniques, SourcererCC and AutoenCODE, on both ","authors_text":"Baowen Xu, Fan Pu, Fan Wu, Jifeng Xuan, Leslie Kanthan, Lingbo Li, Michail Basios, Wahidur Rahman, Xiangyang Jia, Yisen Xu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2022-04-08T18:38:02Z","title":"Clone Detection on Large Scala Codebases"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.04247","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:d278cbc5e88493287973f69c919465f7033327b4d483c3250b60ef4265b555f0","target":"record","created_at":"2026-07-05T04:12:54Z","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":"587305a4e4c71b261e9d05270745cecf7caab23d25a428c25edbd4c1f3e13fbe","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2022-04-08T18:38:02Z","title_canon_sha256":"c75d9ec7156aba37d02906ac4c79b00643a5bbdba1960e8e10d0272356179954"},"schema_version":"1.0","source":{"id":"2204.04247","kind":"arxiv","version":1}},"canonical_sha256":"fdf2f792415a17c805a660b458e8418c0579d993b066a2c9535caf37478d996e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fdf2f792415a17c805a660b458e8418c0579d993b066a2c9535caf37478d996e","first_computed_at":"2026-07-05T04:12:54.857326Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:12:54.857326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7zw5e52Po7X8yGmvozg07gcNf8rVJ78MZuZFanKi3nouoUEc/cG0NHwkQL3wc0CUJyI8Fh2mf/kds4pZ4TOBBA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:12:54.857767Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.04247","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d278cbc5e88493287973f69c919465f7033327b4d483c3250b60ef4265b555f0","sha256:daac9097ce3c88244ca424a59b935cb5d18ba593f9be457fc1e8659ccbde1076"],"state_sha256":"39866c188c81bde3d6dbd569ff637b5d65cc692d9cc7419dca7e04ad76dc1379"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rx+LSWtBWNBZgGs/3TdekCgbfrDevmhsuXieiU1yOdcqebcCTDQCAaPvC/FCsKn2944jvN6rI6ifPRKWBDohAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T20:51:31.111528Z","bundle_sha256":"bbc9becd4fbef094ae5c638368117e3f0671fe2e28ad459c2c4aa1467fb9b5df"}}