{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:5P2PLLHM7RX7HKNCZEVZKNGZQ2","short_pith_number":"pith:5P2PLLHM","canonical_record":{"source":{"id":"2308.09932","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-08-19T07:25:39Z","cross_cats_sorted":[],"title_canon_sha256":"10e0230d40c7a703c8bff28a2088a56d7efcfb16a52cc7cb8cd34fd1be682fc4","abstract_canon_sha256":"a6a9e281658db9a148008c87a43ba27f1a4f69abca408a1295c416771be25bbd"},"schema_version":"1.0"},"canonical_sha256":"ebf4f5acecfc6ff3a9a2c92b9534d986bd3e4fb4b1423a553c7a9c1994c1a0cd","source":{"kind":"arxiv","id":"2308.09932","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.09932","created_at":"2026-07-05T07:32:43Z"},{"alias_kind":"arxiv_version","alias_value":"2308.09932v2","created_at":"2026-07-05T07:32:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.09932","created_at":"2026-07-05T07:32:43Z"},{"alias_kind":"pith_short_12","alias_value":"5P2PLLHM7RX7","created_at":"2026-07-05T07:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"5P2PLLHM7RX7HKNC","created_at":"2026-07-05T07:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"5P2PLLHM","created_at":"2026-07-05T07:32:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:5P2PLLHM7RX7HKNCZEVZKNGZQ2","target":"record","payload":{"canonical_record":{"source":{"id":"2308.09932","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-08-19T07:25:39Z","cross_cats_sorted":[],"title_canon_sha256":"10e0230d40c7a703c8bff28a2088a56d7efcfb16a52cc7cb8cd34fd1be682fc4","abstract_canon_sha256":"a6a9e281658db9a148008c87a43ba27f1a4f69abca408a1295c416771be25bbd"},"schema_version":"1.0"},"canonical_sha256":"ebf4f5acecfc6ff3a9a2c92b9534d986bd3e4fb4b1423a553c7a9c1994c1a0cd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:32:43.919780Z","signature_b64":"Z3b/vTBUOYDJePVgcytK1cOIvFOYePFbXUCoBVVnVJU58/WZA/GrdSsI70Ix2+2ieV9Kx40eKVAHU1yvORUVAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebf4f5acecfc6ff3a9a2c92b9534d986bd3e4fb4b1423a553c7a9c1994c1a0cd","last_reissued_at":"2026-07-05T07:32:43.919291Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:32:43.919291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.09932","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:32:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lj4bJEJEPHzo2nOhv3pYhCegOhyBO/16y63xjTONiWmSEE7Q8t84jvMPiUWDZ7RgCLVHDg5qoDpWcZIJuEdjCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T10:49:45.658578Z"},"content_sha256":"7c6437bdab91e51cf00022ffb35439b5bbda2d2c9ac532f0d18660dc25e7c890","schema_version":"1.0","event_id":"sha256:7c6437bdab91e51cf00022ffb35439b5bbda2d2c9ac532f0d18660dc25e7c890"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:5P2PLLHM7RX7HKNCZEVZKNGZQ2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unveiling Memorization in Code Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Chenyu Wang, David Lo, DongGyun Han, Dongsun Kim, Jieke Shi, Zhipeng Zhao, Zhou Yang","submitted_at":"2023-08-19T07:25:39Z","abstract_excerpt":"The availability of large-scale datasets, advanced architectures, and powerful computational resources have led to effective code models that automate diverse software engineering activities. The datasets usually consist of billions of lines of code from both open-source and private repositories. A code model memorizes and produces source code verbatim, which potentially contains vulnerabilities, sensitive information, or code with strict licenses, leading to potential security and privacy issues. This paper investigates an important problem: to what extent do code models memorize their traini"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.09932","kind":"arxiv","version":2},"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/2308.09932/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":"2026-07-05T07:32:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KSYGONRiKEHMWcXLDoeWcVjd4wX+ooJg5Du9P5xhweQyxQrQIk7Yoj1kTC0kGVz8CMWgM7u4sY4kxQQ2VYw5AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T10:49:45.659167Z"},"content_sha256":"ef4d6de8b0909f9ce8b911e857acc1e2024c62132194fe80e6fa69a5b1fa8822","schema_version":"1.0","event_id":"sha256:ef4d6de8b0909f9ce8b911e857acc1e2024c62132194fe80e6fa69a5b1fa8822"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5P2PLLHM7RX7HKNCZEVZKNGZQ2/bundle.json","state_url":"https://pith.science/pith/5P2PLLHM7RX7HKNCZEVZKNGZQ2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5P2PLLHM7RX7HKNCZEVZKNGZQ2/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":"2026-08-10T10:49:45Z","links":{"resolver":"https://pith.science/pith/5P2PLLHM7RX7HKNCZEVZKNGZQ2","bundle":"https://pith.science/pith/5P2PLLHM7RX7HKNCZEVZKNGZQ2/bundle.json","state":"https://pith.science/pith/5P2PLLHM7RX7HKNCZEVZKNGZQ2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5P2PLLHM7RX7HKNCZEVZKNGZQ2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5P2PLLHM7RX7HKNCZEVZKNGZQ2","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":"a6a9e281658db9a148008c87a43ba27f1a4f69abca408a1295c416771be25bbd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-08-19T07:25:39Z","title_canon_sha256":"10e0230d40c7a703c8bff28a2088a56d7efcfb16a52cc7cb8cd34fd1be682fc4"},"schema_version":"1.0","source":{"id":"2308.09932","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.09932","created_at":"2026-07-05T07:32:43Z"},{"alias_kind":"arxiv_version","alias_value":"2308.09932v2","created_at":"2026-07-05T07:32:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.09932","created_at":"2026-07-05T07:32:43Z"},{"alias_kind":"pith_short_12","alias_value":"5P2PLLHM7RX7","created_at":"2026-07-05T07:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"5P2PLLHM7RX7HKNC","created_at":"2026-07-05T07:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"5P2PLLHM","created_at":"2026-07-05T07:32:43Z"}],"graph_snapshots":[{"event_id":"sha256:ef4d6de8b0909f9ce8b911e857acc1e2024c62132194fe80e6fa69a5b1fa8822","target":"graph","created_at":"2026-07-05T07:32:43Z","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/2308.09932/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The availability of large-scale datasets, advanced architectures, and powerful computational resources have led to effective code models that automate diverse software engineering activities. The datasets usually consist of billions of lines of code from both open-source and private repositories. A code model memorizes and produces source code verbatim, which potentially contains vulnerabilities, sensitive information, or code with strict licenses, leading to potential security and privacy issues. This paper investigates an important problem: to what extent do code models memorize their traini","authors_text":"Chenyu Wang, David Lo, DongGyun Han, Dongsun Kim, Jieke Shi, Zhipeng Zhao, Zhou Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-08-19T07:25:39Z","title":"Unveiling Memorization in Code Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.09932","kind":"arxiv","version":2},"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":"sha256:7c6437bdab91e51cf00022ffb35439b5bbda2d2c9ac532f0d18660dc25e7c890","target":"record","created_at":"2026-07-05T07:32:43Z","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":"a6a9e281658db9a148008c87a43ba27f1a4f69abca408a1295c416771be25bbd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-08-19T07:25:39Z","title_canon_sha256":"10e0230d40c7a703c8bff28a2088a56d7efcfb16a52cc7cb8cd34fd1be682fc4"},"schema_version":"1.0","source":{"id":"2308.09932","kind":"arxiv","version":2}},"canonical_sha256":"ebf4f5acecfc6ff3a9a2c92b9534d986bd3e4fb4b1423a553c7a9c1994c1a0cd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ebf4f5acecfc6ff3a9a2c92b9534d986bd3e4fb4b1423a553c7a9c1994c1a0cd","first_computed_at":"2026-07-05T07:32:43.919291Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:32:43.919291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z3b/vTBUOYDJePVgcytK1cOIvFOYePFbXUCoBVVnVJU58/WZA/GrdSsI70Ix2+2ieV9Kx40eKVAHU1yvORUVAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:32:43.919780Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.09932","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7c6437bdab91e51cf00022ffb35439b5bbda2d2c9ac532f0d18660dc25e7c890","sha256:ef4d6de8b0909f9ce8b911e857acc1e2024c62132194fe80e6fa69a5b1fa8822"],"state_sha256":"b1d8ae60c8251624bf0c2de95ea61658567576cd0f953f4bf7ce830c3caeb45a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CJv9qxDzExwAoLZjGq2YF8wSOmdQ7RHj0YFFGbmfWTaCRlzVU3OJhMeUrmuRyEvf1qCsOVe9nOadWnXoKQpZBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T10:49:45.663528Z","bundle_sha256":"4d7145edd77eb8c2a2d0fd7eda8f711a27c637659dabe6aa2028cfb963aaf885"}}