{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:DQKENHY27DA2OZRZLXAOXBETRW","short_pith_number":"pith:DQKENHY2","schema_version":"1.0","canonical_sha256":"1c14469f1af8c1a766395dc0eb84938d88e347e539e010be31fd43b28c31bba8","source":{"kind":"arxiv","id":"1603.01661","version":1},"attestation_state":"computed","paper":{"title":"SourcererCC and SourcererCC-I: Tools to Detect Clones in Batch mode and During Software Development","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Cristina Lopes, Hitesh Sajnani, Jaewoo Kim, Vaibhav Saini","submitted_at":"2016-03-05T00:12:38Z","abstract_excerpt":"Given the availability of large source-code repositories, there has been a large number of applications for large-scale clone detection. Unfortunately, despite a decade of active research, there is a marked lack in clone detectors that scale to big software systems or large repositories, specifically for detecting near-miss (Type 3) clones where significant editing activities may take place in the cloned code. This paper demonstrates: (i) SourcererCC, a token-based clone detector that targets the first three clone types, and exploits an index to achieve scalability to large inter-project repos"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1603.01661","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2016-03-05T00:12:38Z","cross_cats_sorted":[],"title_canon_sha256":"f2a992341c73f0923260475a34861a5571ce86e6bf941616017bae2656f3cb92","abstract_canon_sha256":"d8a52ec9949b7507da145df0fda8b5c59754cdde57dccd0b36dc18ccf8e26dc6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:49.750853Z","signature_b64":"y/phiNU89ec5DmakZe40SbqCMpvFSa5A2VLL+g87zpqp2AIiJxz78DLK97JNWJ8BRMoo5ADbagLvnrW/Mcn7Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c14469f1af8c1a766395dc0eb84938d88e347e539e010be31fd43b28c31bba8","last_reissued_at":"2026-05-17T23:44:49.750284Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:49.750284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SourcererCC and SourcererCC-I: Tools to Detect Clones in Batch mode and During Software Development","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Cristina Lopes, Hitesh Sajnani, Jaewoo Kim, Vaibhav Saini","submitted_at":"2016-03-05T00:12:38Z","abstract_excerpt":"Given the availability of large source-code repositories, there has been a large number of applications for large-scale clone detection. Unfortunately, despite a decade of active research, there is a marked lack in clone detectors that scale to big software systems or large repositories, specifically for detecting near-miss (Type 3) clones where significant editing activities may take place in the cloned code. This paper demonstrates: (i) SourcererCC, a token-based clone detector that targets the first three clone types, and exploits an index to achieve scalability to large inter-project repos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.01661","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":""},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1603.01661","created_at":"2026-05-17T23:44:49.750376+00:00"},{"alias_kind":"arxiv_version","alias_value":"1603.01661v1","created_at":"2026-05-17T23:44:49.750376+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.01661","created_at":"2026-05-17T23:44:49.750376+00:00"},{"alias_kind":"pith_short_12","alias_value":"DQKENHY27DA2","created_at":"2026-05-18T12:30:12.583610+00:00"},{"alias_kind":"pith_short_16","alias_value":"DQKENHY27DA2OZRZ","created_at":"2026-05-18T12:30:12.583610+00:00"},{"alias_kind":"pith_short_8","alias_value":"DQKENHY2","created_at":"2026-05-18T12:30:12.583610+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DQKENHY27DA2OZRZLXAOXBETRW","json":"https://pith.science/pith/DQKENHY27DA2OZRZLXAOXBETRW.json","graph_json":"https://pith.science/api/pith-number/DQKENHY27DA2OZRZLXAOXBETRW/graph.json","events_json":"https://pith.science/api/pith-number/DQKENHY27DA2OZRZLXAOXBETRW/events.json","paper":"https://pith.science/paper/DQKENHY2"},"agent_actions":{"view_html":"https://pith.science/pith/DQKENHY27DA2OZRZLXAOXBETRW","download_json":"https://pith.science/pith/DQKENHY27DA2OZRZLXAOXBETRW.json","view_paper":"https://pith.science/paper/DQKENHY2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1603.01661&json=true","fetch_graph":"https://pith.science/api/pith-number/DQKENHY27DA2OZRZLXAOXBETRW/graph.json","fetch_events":"https://pith.science/api/pith-number/DQKENHY27DA2OZRZLXAOXBETRW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DQKENHY27DA2OZRZLXAOXBETRW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DQKENHY27DA2OZRZLXAOXBETRW/action/storage_attestation","attest_author":"https://pith.science/pith/DQKENHY27DA2OZRZLXAOXBETRW/action/author_attestation","sign_citation":"https://pith.science/pith/DQKENHY27DA2OZRZLXAOXBETRW/action/citation_signature","submit_replication":"https://pith.science/pith/DQKENHY27DA2OZRZLXAOXBETRW/action/replication_record"}},"created_at":"2026-05-17T23:44:49.750376+00:00","updated_at":"2026-05-17T23:44:49.750376+00:00"}