{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:DQKENHY27DA2OZRZLXAOXBETRW","short_pith_number":"pith:DQKENHY2","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"},"canonical_sha256":"1c14469f1af8c1a766395dc0eb84938d88e347e539e010be31fd43b28c31bba8","source":{"kind":"arxiv","id":"1603.01661","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1603.01661","created_at":"2026-05-17T23:44:49Z"},{"alias_kind":"arxiv_version","alias_value":"1603.01661v1","created_at":"2026-05-17T23:44:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.01661","created_at":"2026-05-17T23:44:49Z"},{"alias_kind":"pith_short_12","alias_value":"DQKENHY27DA2","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_16","alias_value":"DQKENHY27DA2OZRZ","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_8","alias_value":"DQKENHY2","created_at":"2026-05-18T12:30:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:DQKENHY27DA2OZRZLXAOXBETRW","target":"record","payload":{"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"},"canonical_sha256":"1c14469f1af8c1a766395dc0eb84938d88e347e539e010be31fd43b28c31bba8","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"},"source_kind":"arxiv","source_id":"1603.01661","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":"2026-05-17T23:44:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"INeLW9ACXAkREILwOGhzqkMsUrAF7T1YQgCzbOY9dyWdmBp2dYxb1MC4cM9TlqFMRyjWwvkfKsyck+jFlrspAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T01:15:00.521727Z"},"content_sha256":"1e232d6361b3668ce891214cd62316d9fc24218d0899f6e7ec6b77d03748b46b","schema_version":"1.0","event_id":"sha256:1e232d6361b3668ce891214cd62316d9fc24218d0899f6e7ec6b77d03748b46b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:DQKENHY27DA2OZRZLXAOXBETRW","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:44:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"px3V7qUjBy8ioVKA6evxn0pSW7PbU7pswWWwLPdGA6QrS0sWnYGQqGhZwF82rF4yE5GWsm6uF4DRZSZuQ/vSAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T01:15:00.522376Z"},"content_sha256":"d7328bb51a03dcc5beaaeb919fabe45c9c94c7f93e78f2098c3f252aef422913","schema_version":"1.0","event_id":"sha256:d7328bb51a03dcc5beaaeb919fabe45c9c94c7f93e78f2098c3f252aef422913"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DQKENHY27DA2OZRZLXAOXBETRW/bundle.json","state_url":"https://pith.science/pith/DQKENHY27DA2OZRZLXAOXBETRW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DQKENHY27DA2OZRZLXAOXBETRW/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":"2026-05-26T01:15:00Z","links":{"resolver":"https://pith.science/pith/DQKENHY27DA2OZRZLXAOXBETRW","bundle":"https://pith.science/pith/DQKENHY27DA2OZRZLXAOXBETRW/bundle.json","state":"https://pith.science/pith/DQKENHY27DA2OZRZLXAOXBETRW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DQKENHY27DA2OZRZLXAOXBETRW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:DQKENHY27DA2OZRZLXAOXBETRW","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":"d8a52ec9949b7507da145df0fda8b5c59754cdde57dccd0b36dc18ccf8e26dc6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2016-03-05T00:12:38Z","title_canon_sha256":"f2a992341c73f0923260475a34861a5571ce86e6bf941616017bae2656f3cb92"},"schema_version":"1.0","source":{"id":"1603.01661","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1603.01661","created_at":"2026-05-17T23:44:49Z"},{"alias_kind":"arxiv_version","alias_value":"1603.01661v1","created_at":"2026-05-17T23:44:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.01661","created_at":"2026-05-17T23:44:49Z"},{"alias_kind":"pith_short_12","alias_value":"DQKENHY27DA2","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_16","alias_value":"DQKENHY27DA2OZRZ","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_8","alias_value":"DQKENHY2","created_at":"2026-05-18T12:30:12Z"}],"graph_snapshots":[{"event_id":"sha256:d7328bb51a03dcc5beaaeb919fabe45c9c94c7f93e78f2098c3f252aef422913","target":"graph","created_at":"2026-05-17T23:44:49Z","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"},"paper":{"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","authors_text":"Cristina Lopes, Hitesh Sajnani, Jaewoo Kim, Vaibhav Saini","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2016-03-05T00:12:38Z","title":"SourcererCC and SourcererCC-I: Tools to Detect Clones in Batch mode and During Software Development"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.01661","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":"sha256:1e232d6361b3668ce891214cd62316d9fc24218d0899f6e7ec6b77d03748b46b","target":"record","created_at":"2026-05-17T23:44:49Z","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":"d8a52ec9949b7507da145df0fda8b5c59754cdde57dccd0b36dc18ccf8e26dc6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2016-03-05T00:12:38Z","title_canon_sha256":"f2a992341c73f0923260475a34861a5571ce86e6bf941616017bae2656f3cb92"},"schema_version":"1.0","source":{"id":"1603.01661","kind":"arxiv","version":1}},"canonical_sha256":"1c14469f1af8c1a766395dc0eb84938d88e347e539e010be31fd43b28c31bba8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1c14469f1af8c1a766395dc0eb84938d88e347e539e010be31fd43b28c31bba8","first_computed_at":"2026-05-17T23:44:49.750284Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:49.750284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y/phiNU89ec5DmakZe40SbqCMpvFSa5A2VLL+g87zpqp2AIiJxz78DLK97JNWJ8BRMoo5ADbagLvnrW/Mcn7Aw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:49.750853Z","signed_message":"canonical_sha256_bytes"},"source_id":"1603.01661","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e232d6361b3668ce891214cd62316d9fc24218d0899f6e7ec6b77d03748b46b","sha256:d7328bb51a03dcc5beaaeb919fabe45c9c94c7f93e78f2098c3f252aef422913"],"state_sha256":"4ec2a3bf13bf91343415f711887c7708a97a180cbdd0affe5ef89c389fc5d16c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eiDi/Ud6CU7gCs07LWz4HD+kIUlBHytSVD0dJwff+5LuoYc6NbMR66YOdA27kfevcwe9LodOIEGVLB0Jljr9AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T01:15:00.525997Z","bundle_sha256":"08703b119f70ac372b968a8130c225ccc0d870977bd349101f72f0cf78255ca9"}}