{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:5Z3JONAG7RBUS7AIQECD4PJMCQ","short_pith_number":"pith:5Z3JONAG","canonical_record":{"source":{"id":"1812.06469","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2018-12-16T14:19:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c1782d99866225869c137754d6cbc75a2005babbdaa17d4b66ba22ca6f88f05f","abstract_canon_sha256":"e3a01ae039d94d24e02d1559644b56f40244c5ad441c119b191b8309a84f5d94"},"schema_version":"1.0"},"canonical_sha256":"ee76973406fc43497c0881043e3d2c1407b61de20b71eef24df71e266861fa0c","source":{"kind":"arxiv","id":"1812.06469","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.06469","created_at":"2026-07-04T23:53:11Z"},{"alias_kind":"arxiv_version","alias_value":"1812.06469v6","created_at":"2026-07-04T23:53:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.06469","created_at":"2026-07-04T23:53:11Z"},{"alias_kind":"pith_short_12","alias_value":"5Z3JONAG7RBU","created_at":"2026-07-04T23:53:11Z"},{"alias_kind":"pith_short_16","alias_value":"5Z3JONAG7RBUS7AI","created_at":"2026-07-04T23:53:11Z"},{"alias_kind":"pith_short_8","alias_value":"5Z3JONAG","created_at":"2026-07-04T23:53:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:5Z3JONAG7RBUS7AIQECD4PJMCQ","target":"record","payload":{"canonical_record":{"source":{"id":"1812.06469","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2018-12-16T14:19:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c1782d99866225869c137754d6cbc75a2005babbdaa17d4b66ba22ca6f88f05f","abstract_canon_sha256":"e3a01ae039d94d24e02d1559644b56f40244c5ad441c119b191b8309a84f5d94"},"schema_version":"1.0"},"canonical_sha256":"ee76973406fc43497c0881043e3d2c1407b61de20b71eef24df71e266861fa0c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:53:11.107434Z","signature_b64":"jSkhJ6GOznvNNvRfS00GuGBaa4+wfl30e3QacIieWt7mlp+x1WesXReuD9JStAJZf8ff6ca0NORtXMY2WA94CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee76973406fc43497c0881043e3d2c1407b61de20b71eef24df71e266861fa0c","last_reissued_at":"2026-07-04T23:53:11.106990Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:53:11.106990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.06469","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-04T23:53:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6Z+k5SoCKFQUtcXEZ23AnwXxTKim4pSCqsX8xDUSEtdokw9/O5PAoF4/os4tyF1oTr8NzOZ/7EK6IGaVaZf4Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:54:29.317720Z"},"content_sha256":"3cffe55f931d51527db64c35894c035eb3726e0cdf45eb247dad3229736c3504","schema_version":"1.0","event_id":"sha256:3cffe55f931d51527db64c35894c035eb3726e0cdf45eb247dad3229736c3504"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:5Z3JONAG7RBUS7AIQECD4PJMCQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Adverse Effects of Code Duplication in Machine Learning Models of Code","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Miltiadis Allamanis","submitted_at":"2018-12-16T14:19:44Z","abstract_excerpt":"The field of big code relies on mining large corpora of code to perform some learning task. A significant threat to this approach has been recently identified by Lopes et al. (2017) who found a large amount of near-duplicate code on GitHub. However, the impact of code duplication has not been noticed by researchers devising machine learning models for source code. In this work, we explore the effects of code duplication on machine learning models showing that reported performance metrics are sometimes inflated by up to 100% when testing on duplicated code corpora compared to the performance on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.06469","kind":"arxiv","version":6},"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/1812.06469/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":"2026-07-04T23:53:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fUgMzinjMj9pZUGyc5WRh3Cboox5aCbmEkskt5odiEi6aiRn1byl7/jeUdl7A1V5LNspMNNUp//sRVhWwD6XCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:54:29.318109Z"},"content_sha256":"97ac2af30fd932eac4598752d39b7ddd7943e7fb28f110423ccf600f1565f921","schema_version":"1.0","event_id":"sha256:97ac2af30fd932eac4598752d39b7ddd7943e7fb28f110423ccf600f1565f921"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5Z3JONAG7RBUS7AIQECD4PJMCQ/bundle.json","state_url":"https://pith.science/pith/5Z3JONAG7RBUS7AIQECD4PJMCQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5Z3JONAG7RBUS7AIQECD4PJMCQ/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":"2026-07-09T06:54:29Z","links":{"resolver":"https://pith.science/pith/5Z3JONAG7RBUS7AIQECD4PJMCQ","bundle":"https://pith.science/pith/5Z3JONAG7RBUS7AIQECD4PJMCQ/bundle.json","state":"https://pith.science/pith/5Z3JONAG7RBUS7AIQECD4PJMCQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5Z3JONAG7RBUS7AIQECD4PJMCQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:5Z3JONAG7RBUS7AIQECD4PJMCQ","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":"e3a01ae039d94d24e02d1559644b56f40244c5ad441c119b191b8309a84f5d94","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2018-12-16T14:19:44Z","title_canon_sha256":"c1782d99866225869c137754d6cbc75a2005babbdaa17d4b66ba22ca6f88f05f"},"schema_version":"1.0","source":{"id":"1812.06469","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.06469","created_at":"2026-07-04T23:53:11Z"},{"alias_kind":"arxiv_version","alias_value":"1812.06469v6","created_at":"2026-07-04T23:53:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.06469","created_at":"2026-07-04T23:53:11Z"},{"alias_kind":"pith_short_12","alias_value":"5Z3JONAG7RBU","created_at":"2026-07-04T23:53:11Z"},{"alias_kind":"pith_short_16","alias_value":"5Z3JONAG7RBUS7AI","created_at":"2026-07-04T23:53:11Z"},{"alias_kind":"pith_short_8","alias_value":"5Z3JONAG","created_at":"2026-07-04T23:53:11Z"}],"graph_snapshots":[{"event_id":"sha256:97ac2af30fd932eac4598752d39b7ddd7943e7fb28f110423ccf600f1565f921","target":"graph","created_at":"2026-07-04T23:53:11Z","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/1812.06469/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The field of big code relies on mining large corpora of code to perform some learning task. A significant threat to this approach has been recently identified by Lopes et al. (2017) who found a large amount of near-duplicate code on GitHub. However, the impact of code duplication has not been noticed by researchers devising machine learning models for source code. In this work, we explore the effects of code duplication on machine learning models showing that reported performance metrics are sometimes inflated by up to 100% when testing on duplicated code corpora compared to the performance on","authors_text":"Miltiadis Allamanis","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2018-12-16T14:19:44Z","title":"The Adverse Effects of Code Duplication in Machine Learning Models of Code"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.06469","kind":"arxiv","version":6},"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":"sha256:3cffe55f931d51527db64c35894c035eb3726e0cdf45eb247dad3229736c3504","target":"record","created_at":"2026-07-04T23:53:11Z","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":"e3a01ae039d94d24e02d1559644b56f40244c5ad441c119b191b8309a84f5d94","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2018-12-16T14:19:44Z","title_canon_sha256":"c1782d99866225869c137754d6cbc75a2005babbdaa17d4b66ba22ca6f88f05f"},"schema_version":"1.0","source":{"id":"1812.06469","kind":"arxiv","version":6}},"canonical_sha256":"ee76973406fc43497c0881043e3d2c1407b61de20b71eef24df71e266861fa0c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ee76973406fc43497c0881043e3d2c1407b61de20b71eef24df71e266861fa0c","first_computed_at":"2026-07-04T23:53:11.106990Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:53:11.106990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jSkhJ6GOznvNNvRfS00GuGBaa4+wfl30e3QacIieWt7mlp+x1WesXReuD9JStAJZf8ff6ca0NORtXMY2WA94CA==","signature_status":"signed_v1","signed_at":"2026-07-04T23:53:11.107434Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.06469","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3cffe55f931d51527db64c35894c035eb3726e0cdf45eb247dad3229736c3504","sha256:97ac2af30fd932eac4598752d39b7ddd7943e7fb28f110423ccf600f1565f921"],"state_sha256":"92ac9ab79a6a2de55c5a5497eebb0d50cc73752191db3a51d6a666e48c6f4ff2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U9Pt42f/R0KfK/bB2+qvA451Eba5WeXfRi9F2u3HUO7ZnD9EVEdODRuRRJ9eMkDh36r27DU8hLYMOHMQkaK2AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T06:54:29.320719Z","bundle_sha256":"8418c7b4210905b590317e1cec8bb400a4a8e8cfc69ce8b6774a71a829d61ac6"}}