{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:WUK4TVABPDKLYUOURTYXQ2NDG6","short_pith_number":"pith:WUK4TVAB","canonical_record":{"source":{"id":"2308.14401","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2023-08-28T08:36:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6440ecacf88c1e9cdad38d2898b2734366bc7f2d77034336e38b813680101d5b","abstract_canon_sha256":"26ab6a88236adbfa5278cb091d62b5e416ae816f0c733500c100987b63c45b8a"},"schema_version":"1.0"},"canonical_sha256":"b515c9d40178d4bc51d48cf17869a337ba282cf1d10eb114721f9b84051603bc","source":{"kind":"arxiv","id":"2308.14401","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.14401","created_at":"2026-07-05T06:45:25Z"},{"alias_kind":"arxiv_version","alias_value":"2308.14401v1","created_at":"2026-07-05T06:45:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.14401","created_at":"2026-07-05T06:45:25Z"},{"alias_kind":"pith_short_12","alias_value":"WUK4TVABPDKL","created_at":"2026-07-05T06:45:25Z"},{"alias_kind":"pith_short_16","alias_value":"WUK4TVABPDKLYUOU","created_at":"2026-07-05T06:45:25Z"},{"alias_kind":"pith_short_8","alias_value":"WUK4TVAB","created_at":"2026-07-05T06:45:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:WUK4TVABPDKLYUOURTYXQ2NDG6","target":"record","payload":{"canonical_record":{"source":{"id":"2308.14401","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2023-08-28T08:36:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6440ecacf88c1e9cdad38d2898b2734366bc7f2d77034336e38b813680101d5b","abstract_canon_sha256":"26ab6a88236adbfa5278cb091d62b5e416ae816f0c733500c100987b63c45b8a"},"schema_version":"1.0"},"canonical_sha256":"b515c9d40178d4bc51d48cf17869a337ba282cf1d10eb114721f9b84051603bc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:45:25.855997Z","signature_b64":"z5pRmmkhS1lfoBk5t6fjWO02UcxPlUqQLbXxzZT2zlEwj3cEGyVuZP9noItkyQej5co+B13WJPZYdt4XsBjEDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b515c9d40178d4bc51d48cf17869a337ba282cf1d10eb114721f9b84051603bc","last_reissued_at":"2026-07-05T06:45:25.855593Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:45:25.855593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.14401","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":"2026-07-05T06:45:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y500gFf7hdTtC2qHxmvzSRVOIBZFXI5/Sc9HfFNXxcJkTxxjgH5P3zL+zCbro03T4vUmS8g/8WBMUrLmG+VNDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:01:57.138477Z"},"content_sha256":"7029528679832e4b2a66219113446289f1dc5a52668e5b8372c668857f1df0af","schema_version":"1.0","event_id":"sha256:7029528679832e4b2a66219113446289f1dc5a52668e5b8372c668857f1df0af"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:WUK4TVABPDKLYUOURTYXQ2NDG6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CodeMark: Imperceptible Watermarking for Code Datasets against Neural Code Completion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Fu Song, Li Li, Xiaoning Du, Zhensu Sun","submitted_at":"2023-08-28T08:36:53Z","abstract_excerpt":"Code datasets are of immense value for training neural-network-based code completion models, where companies or organizations have made substantial investments to establish and process these datasets. Unluckily, these datasets, either built for proprietary or public usage, face the high risk of unauthorized exploits, resulting from data leakages, license violations, etc. Even worse, the ``black-box'' nature of neural models sets a high barrier for externals to audit their training datasets, which further connives these unauthorized usages. Currently, watermarking methods have been proposed to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.14401","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/2308.14401/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":"2026-07-05T06:45:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"55zB8BWWgmiIsZJnrvYN30JzQ2cZHjW2/thJmcjJ0oQdjCdS9tZqI2oZsPBzzVWInKdu4UoN+dc8bYIHcnDxDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:01:57.139060Z"},"content_sha256":"b62e15641c05b545b1d1338f827752a6d8d8c1e746f4d5150e75259a5519ba15","schema_version":"1.0","event_id":"sha256:b62e15641c05b545b1d1338f827752a6d8d8c1e746f4d5150e75259a5519ba15"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WUK4TVABPDKLYUOURTYXQ2NDG6/bundle.json","state_url":"https://pith.science/pith/WUK4TVABPDKLYUOURTYXQ2NDG6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WUK4TVABPDKLYUOURTYXQ2NDG6/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":"2026-08-05T08:01:57Z","links":{"resolver":"https://pith.science/pith/WUK4TVABPDKLYUOURTYXQ2NDG6","bundle":"https://pith.science/pith/WUK4TVABPDKLYUOURTYXQ2NDG6/bundle.json","state":"https://pith.science/pith/WUK4TVABPDKLYUOURTYXQ2NDG6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WUK4TVABPDKLYUOURTYXQ2NDG6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WUK4TVABPDKLYUOURTYXQ2NDG6","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":"26ab6a88236adbfa5278cb091d62b5e416ae816f0c733500c100987b63c45b8a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2023-08-28T08:36:53Z","title_canon_sha256":"6440ecacf88c1e9cdad38d2898b2734366bc7f2d77034336e38b813680101d5b"},"schema_version":"1.0","source":{"id":"2308.14401","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.14401","created_at":"2026-07-05T06:45:25Z"},{"alias_kind":"arxiv_version","alias_value":"2308.14401v1","created_at":"2026-07-05T06:45:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.14401","created_at":"2026-07-05T06:45:25Z"},{"alias_kind":"pith_short_12","alias_value":"WUK4TVABPDKL","created_at":"2026-07-05T06:45:25Z"},{"alias_kind":"pith_short_16","alias_value":"WUK4TVABPDKLYUOU","created_at":"2026-07-05T06:45:25Z"},{"alias_kind":"pith_short_8","alias_value":"WUK4TVAB","created_at":"2026-07-05T06:45:25Z"}],"graph_snapshots":[{"event_id":"sha256:b62e15641c05b545b1d1338f827752a6d8d8c1e746f4d5150e75259a5519ba15","target":"graph","created_at":"2026-07-05T06:45:25Z","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/2308.14401/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Code datasets are of immense value for training neural-network-based code completion models, where companies or organizations have made substantial investments to establish and process these datasets. Unluckily, these datasets, either built for proprietary or public usage, face the high risk of unauthorized exploits, resulting from data leakages, license violations, etc. Even worse, the ``black-box'' nature of neural models sets a high barrier for externals to audit their training datasets, which further connives these unauthorized usages. Currently, watermarking methods have been proposed to ","authors_text":"Fu Song, Li Li, Xiaoning Du, Zhensu Sun","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2023-08-28T08:36:53Z","title":"CodeMark: Imperceptible Watermarking for Code Datasets against Neural Code Completion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.14401","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":"sha256:7029528679832e4b2a66219113446289f1dc5a52668e5b8372c668857f1df0af","target":"record","created_at":"2026-07-05T06:45:25Z","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":"26ab6a88236adbfa5278cb091d62b5e416ae816f0c733500c100987b63c45b8a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2023-08-28T08:36:53Z","title_canon_sha256":"6440ecacf88c1e9cdad38d2898b2734366bc7f2d77034336e38b813680101d5b"},"schema_version":"1.0","source":{"id":"2308.14401","kind":"arxiv","version":1}},"canonical_sha256":"b515c9d40178d4bc51d48cf17869a337ba282cf1d10eb114721f9b84051603bc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b515c9d40178d4bc51d48cf17869a337ba282cf1d10eb114721f9b84051603bc","first_computed_at":"2026-07-05T06:45:25.855593Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:45:25.855593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z5pRmmkhS1lfoBk5t6fjWO02UcxPlUqQLbXxzZT2zlEwj3cEGyVuZP9noItkyQej5co+B13WJPZYdt4XsBjEDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:45:25.855997Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.14401","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7029528679832e4b2a66219113446289f1dc5a52668e5b8372c668857f1df0af","sha256:b62e15641c05b545b1d1338f827752a6d8d8c1e746f4d5150e75259a5519ba15"],"state_sha256":"f1ea251393a4fb18f05085240440983a8b137ae45b429728027f84944ae51015"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/ChHwukU9TLhDJ0EdMCUrms8B2OUTTen19z3vQHLSUxG2R4JIn53qlNj1TlEOHL6kVkNRI7DcW5mx6xybV75Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T08:01:57.142672Z","bundle_sha256":"278a1315ba143c20052861d7d7a063b7f9f6c286466843e1d24ebf3f91329c3a"}}