{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XSCZRBKJ3CTYDE3L4RPK3PGCFZ","short_pith_number":"pith:XSCZRBKJ","canonical_record":{"source":{"id":"2507.17389","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-07-23T10:34:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"16fcef25879c60b60199037aef64ca992650cdf44011adb30c7d7867d2aa1c2a","abstract_canon_sha256":"f5c649940b290d4c9b1dfdb7dc51dc712f706cbc8a401d9d7035e61ce56a0538"},"schema_version":"1.0"},"canonical_sha256":"bc85988549d8a781936be45eadbcc22e6d7c303997e9ae04233dd8877ffe97e2","source":{"kind":"arxiv","id":"2507.17389","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.17389","created_at":"2026-07-05T11:42:06Z"},{"alias_kind":"arxiv_version","alias_value":"2507.17389v1","created_at":"2026-07-05T11:42:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.17389","created_at":"2026-07-05T11:42:06Z"},{"alias_kind":"pith_short_12","alias_value":"XSCZRBKJ3CTY","created_at":"2026-07-05T11:42:06Z"},{"alias_kind":"pith_short_16","alias_value":"XSCZRBKJ3CTYDE3L","created_at":"2026-07-05T11:42:06Z"},{"alias_kind":"pith_short_8","alias_value":"XSCZRBKJ","created_at":"2026-07-05T11:42:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XSCZRBKJ3CTYDE3L4RPK3PGCFZ","target":"record","payload":{"canonical_record":{"source":{"id":"2507.17389","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-07-23T10:34:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"16fcef25879c60b60199037aef64ca992650cdf44011adb30c7d7867d2aa1c2a","abstract_canon_sha256":"f5c649940b290d4c9b1dfdb7dc51dc712f706cbc8a401d9d7035e61ce56a0538"},"schema_version":"1.0"},"canonical_sha256":"bc85988549d8a781936be45eadbcc22e6d7c303997e9ae04233dd8877ffe97e2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:06.777827Z","signature_b64":"hld89Ah1WfvlDf8myR2yyDVJxZdJv3/aogOPJs3+5icV/9SnNiqEeNveHFFQJRjJrJ6ECRYaNd1JaSw2VFo+AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc85988549d8a781936be45eadbcc22e6d7c303997e9ae04233dd8877ffe97e2","last_reissued_at":"2026-07-05T11:42:06.777157Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:06.777157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.17389","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":"2026-07-05T11:42:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vv5nNK98SB6Rfl3cxkWqLrSUXLuGAQJNuRfSV9wox6QWqp/YYtgsL+r+yy/cOoptF3ymqq5KhEmCpSOrbSq4Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T07:16:17.699827Z"},"content_sha256":"a9f780c9a3978495e29108742e6e724032a28595033b36a1d23ec14dd99b7d11","schema_version":"1.0","event_id":"sha256:a9f780c9a3978495e29108742e6e724032a28595033b36a1d23ec14dd99b7d11"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XSCZRBKJ3CTYDE3L4RPK3PGCFZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Investigating Training Data Detection in AI Coders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Aishan Liu, Dongning Sun, Qing Guo, Tianlin Li, Xianglong Liu, Yang Liu, Yunxiang Wei, Zhiming Li","submitted_at":"2025-07-23T10:34:22Z","abstract_excerpt":"Recent advances in code large language models (CodeLLMs) have made them indispensable tools in modern software engineering. However, these models occasionally produce outputs that contain proprietary or sensitive code snippets, raising concerns about potential non-compliant use of training data, and posing risks to privacy and intellectual property. To ensure responsible and compliant deployment of CodeLLMs, training data detection (TDD) has become a critical task. While recent TDD methods have shown promise in natural language settings, their effectiveness on code data remains largely underex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.17389","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/2507.17389/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":"2026-07-05T11:42:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h4eYD2xs9uI1KbVQS2p//E3iDjHtP8q4FAitT6j3b5VKmZiMkwgV6JYPX2/87JPPoBOLvf6RUb59H4mu7zWHBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T07:16:17.700363Z"},"content_sha256":"2a70f3a3e36fee924054a1d4f7bd2c23ed8afee3ef5a92f3868133845370021c","schema_version":"1.0","event_id":"sha256:2a70f3a3e36fee924054a1d4f7bd2c23ed8afee3ef5a92f3868133845370021c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XSCZRBKJ3CTYDE3L4RPK3PGCFZ/bundle.json","state_url":"https://pith.science/pith/XSCZRBKJ3CTYDE3L4RPK3PGCFZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XSCZRBKJ3CTYDE3L4RPK3PGCFZ/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":"2026-08-07T07:16:17Z","links":{"resolver":"https://pith.science/pith/XSCZRBKJ3CTYDE3L4RPK3PGCFZ","bundle":"https://pith.science/pith/XSCZRBKJ3CTYDE3L4RPK3PGCFZ/bundle.json","state":"https://pith.science/pith/XSCZRBKJ3CTYDE3L4RPK3PGCFZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XSCZRBKJ3CTYDE3L4RPK3PGCFZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XSCZRBKJ3CTYDE3L4RPK3PGCFZ","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":"f5c649940b290d4c9b1dfdb7dc51dc712f706cbc8a401d9d7035e61ce56a0538","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-07-23T10:34:22Z","title_canon_sha256":"16fcef25879c60b60199037aef64ca992650cdf44011adb30c7d7867d2aa1c2a"},"schema_version":"1.0","source":{"id":"2507.17389","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.17389","created_at":"2026-07-05T11:42:06Z"},{"alias_kind":"arxiv_version","alias_value":"2507.17389v1","created_at":"2026-07-05T11:42:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.17389","created_at":"2026-07-05T11:42:06Z"},{"alias_kind":"pith_short_12","alias_value":"XSCZRBKJ3CTY","created_at":"2026-07-05T11:42:06Z"},{"alias_kind":"pith_short_16","alias_value":"XSCZRBKJ3CTYDE3L","created_at":"2026-07-05T11:42:06Z"},{"alias_kind":"pith_short_8","alias_value":"XSCZRBKJ","created_at":"2026-07-05T11:42:06Z"}],"graph_snapshots":[{"event_id":"sha256:2a70f3a3e36fee924054a1d4f7bd2c23ed8afee3ef5a92f3868133845370021c","target":"graph","created_at":"2026-07-05T11:42:06Z","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/2507.17389/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in code large language models (CodeLLMs) have made them indispensable tools in modern software engineering. However, these models occasionally produce outputs that contain proprietary or sensitive code snippets, raising concerns about potential non-compliant use of training data, and posing risks to privacy and intellectual property. To ensure responsible and compliant deployment of CodeLLMs, training data detection (TDD) has become a critical task. While recent TDD methods have shown promise in natural language settings, their effectiveness on code data remains largely underex","authors_text":"Aishan Liu, Dongning Sun, Qing Guo, Tianlin Li, Xianglong Liu, Yang Liu, Yunxiang Wei, Zhiming Li","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-07-23T10:34:22Z","title":"Investigating Training Data Detection in AI Coders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.17389","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:a9f780c9a3978495e29108742e6e724032a28595033b36a1d23ec14dd99b7d11","target":"record","created_at":"2026-07-05T11:42:06Z","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":"f5c649940b290d4c9b1dfdb7dc51dc712f706cbc8a401d9d7035e61ce56a0538","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-07-23T10:34:22Z","title_canon_sha256":"16fcef25879c60b60199037aef64ca992650cdf44011adb30c7d7867d2aa1c2a"},"schema_version":"1.0","source":{"id":"2507.17389","kind":"arxiv","version":1}},"canonical_sha256":"bc85988549d8a781936be45eadbcc22e6d7c303997e9ae04233dd8877ffe97e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bc85988549d8a781936be45eadbcc22e6d7c303997e9ae04233dd8877ffe97e2","first_computed_at":"2026-07-05T11:42:06.777157Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:42:06.777157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hld89Ah1WfvlDf8myR2yyDVJxZdJv3/aogOPJs3+5icV/9SnNiqEeNveHFFQJRjJrJ6ECRYaNd1JaSw2VFo+AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:42:06.777827Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.17389","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a9f780c9a3978495e29108742e6e724032a28595033b36a1d23ec14dd99b7d11","sha256:2a70f3a3e36fee924054a1d4f7bd2c23ed8afee3ef5a92f3868133845370021c"],"state_sha256":"468efd8e2483c24d8f96593fea0527910a1325e3bcd9965eb95e310be24d9be7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u/vdHl4xoI9tBBjWogUn0LOU/iB9EgtT4mtwJTAHdoTQSMpj0kejH4ur5G4Dp4iNrIiQ8EQXZ/r6jWnuY0ULCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T07:16:17.705683Z","bundle_sha256":"b89ac708f1b41e5aa450dc98d58995ef2bd663e791160bcbbdb2ce45ab83670d"}}