{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HQQ5MAVWSF3SMTBO7TUMXWLL7A","short_pith_number":"pith:HQQ5MAVW","canonical_record":{"source":{"id":"2502.20246","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-27T16:30:00Z","cross_cats_sorted":[],"title_canon_sha256":"be23676da479d7fb74aedd57fade35983b1494a42752247acb6c10ccfbfce3fd","abstract_canon_sha256":"5db07e357888fc40727a2db4a75e5125186ab031c070f45e008b25f97306b673"},"schema_version":"1.0"},"canonical_sha256":"3c21d602b69177264c2efce8cbd96bf800ff2e2760cd914f7637abe96a151053","source":{"kind":"arxiv","id":"2502.20246","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.20246","created_at":"2026-07-05T10:21:32Z"},{"alias_kind":"arxiv_version","alias_value":"2502.20246v2","created_at":"2026-07-05T10:21:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.20246","created_at":"2026-07-05T10:21:32Z"},{"alias_kind":"pith_short_12","alias_value":"HQQ5MAVWSF3S","created_at":"2026-07-05T10:21:32Z"},{"alias_kind":"pith_short_16","alias_value":"HQQ5MAVWSF3SMTBO","created_at":"2026-07-05T10:21:32Z"},{"alias_kind":"pith_short_8","alias_value":"HQQ5MAVW","created_at":"2026-07-05T10:21:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HQQ5MAVWSF3SMTBO7TUMXWLL7A","target":"record","payload":{"canonical_record":{"source":{"id":"2502.20246","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-27T16:30:00Z","cross_cats_sorted":[],"title_canon_sha256":"be23676da479d7fb74aedd57fade35983b1494a42752247acb6c10ccfbfce3fd","abstract_canon_sha256":"5db07e357888fc40727a2db4a75e5125186ab031c070f45e008b25f97306b673"},"schema_version":"1.0"},"canonical_sha256":"3c21d602b69177264c2efce8cbd96bf800ff2e2760cd914f7637abe96a151053","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:32.146539Z","signature_b64":"lvkGEhRaJbNPgcXq3zY/p9ZTFKO5WQVYwgvB5FsaAWdMYhJhyZLVjWlHTaQRXu8LTeBtDYQBE8OpMp9mTJ0TCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c21d602b69177264c2efce8cbd96bf800ff2e2760cd914f7637abe96a151053","last_reissued_at":"2026-07-05T10:21:32.145782Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:32.145782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.20246","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":"2026-07-05T10:21:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ChKTlwMS0+U/VcrfLVzhGcWIdwvTLXuu+TTZgMnKQ0t59Fq12ggIvzhcqPqCN3vSbs0rtfeE/izels7+MLVCCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:33:54.320204Z"},"content_sha256":"1c0b65ee5ee4cd12d07a7731982533cba395220a26bd24efedd6148c6ad4a1b9","schema_version":"1.0","event_id":"sha256:1c0b65ee5ee4cd12d07a7731982533cba395220a26bd24efedd6148c6ad4a1b9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HQQ5MAVWSF3SMTBO7TUMXWLL7A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Natural Language Perplexity: Detecting Dead Code Poisoning in Code Generation Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chia-Mu Yu, Chi-Chien Tsai, Wei-Bin Lee, Ying-Dar Lin, Yu-Sung Wu","submitted_at":"2025-02-27T16:30:00Z","abstract_excerpt":"The increasing adoption of large language models (LLMs) for code-related tasks has raised concerns about the security of their training datasets. One critical threat is dead code poisoning, where syntactically valid but functionally redundant code is injected into training data to manipulate model behavior. Such attacks can degrade the performance of neural code search systems, leading to biased or insecure code suggestions. Existing detection methods, such as token-level perplexity analysis, fail to effectively identify dead code due to the structural and contextual characteristics of program"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.20246","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/2502.20246/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":"2026-07-05T10:21:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MDON0DbWG0PPZ5QE7As9+hSgIgkEeiJMFsNVYTUtkjYO1o/ccrDEvDrwLWHk4Q/YgSbXvX/C14MD7Fre0OBPAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:33:54.320696Z"},"content_sha256":"3da2eafde8ec1d2d14881993f2b40b308b12cb76316971e6f276234a7db38ba5","schema_version":"1.0","event_id":"sha256:3da2eafde8ec1d2d14881993f2b40b308b12cb76316971e6f276234a7db38ba5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HQQ5MAVWSF3SMTBO7TUMXWLL7A/bundle.json","state_url":"https://pith.science/pith/HQQ5MAVWSF3SMTBO7TUMXWLL7A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HQQ5MAVWSF3SMTBO7TUMXWLL7A/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":"2026-08-06T19:33:54Z","links":{"resolver":"https://pith.science/pith/HQQ5MAVWSF3SMTBO7TUMXWLL7A","bundle":"https://pith.science/pith/HQQ5MAVWSF3SMTBO7TUMXWLL7A/bundle.json","state":"https://pith.science/pith/HQQ5MAVWSF3SMTBO7TUMXWLL7A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HQQ5MAVWSF3SMTBO7TUMXWLL7A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HQQ5MAVWSF3SMTBO7TUMXWLL7A","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":"5db07e357888fc40727a2db4a75e5125186ab031c070f45e008b25f97306b673","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-27T16:30:00Z","title_canon_sha256":"be23676da479d7fb74aedd57fade35983b1494a42752247acb6c10ccfbfce3fd"},"schema_version":"1.0","source":{"id":"2502.20246","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.20246","created_at":"2026-07-05T10:21:32Z"},{"alias_kind":"arxiv_version","alias_value":"2502.20246v2","created_at":"2026-07-05T10:21:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.20246","created_at":"2026-07-05T10:21:32Z"},{"alias_kind":"pith_short_12","alias_value":"HQQ5MAVWSF3S","created_at":"2026-07-05T10:21:32Z"},{"alias_kind":"pith_short_16","alias_value":"HQQ5MAVWSF3SMTBO","created_at":"2026-07-05T10:21:32Z"},{"alias_kind":"pith_short_8","alias_value":"HQQ5MAVW","created_at":"2026-07-05T10:21:32Z"}],"graph_snapshots":[{"event_id":"sha256:3da2eafde8ec1d2d14881993f2b40b308b12cb76316971e6f276234a7db38ba5","target":"graph","created_at":"2026-07-05T10:21:32Z","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/2502.20246/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The increasing adoption of large language models (LLMs) for code-related tasks has raised concerns about the security of their training datasets. One critical threat is dead code poisoning, where syntactically valid but functionally redundant code is injected into training data to manipulate model behavior. Such attacks can degrade the performance of neural code search systems, leading to biased or insecure code suggestions. Existing detection methods, such as token-level perplexity analysis, fail to effectively identify dead code due to the structural and contextual characteristics of program","authors_text":"Chia-Mu Yu, Chi-Chien Tsai, Wei-Bin Lee, Ying-Dar Lin, Yu-Sung Wu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-27T16:30:00Z","title":"Beyond Natural Language Perplexity: Detecting Dead Code Poisoning in Code Generation Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.20246","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":"sha256:1c0b65ee5ee4cd12d07a7731982533cba395220a26bd24efedd6148c6ad4a1b9","target":"record","created_at":"2026-07-05T10:21:32Z","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":"5db07e357888fc40727a2db4a75e5125186ab031c070f45e008b25f97306b673","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-27T16:30:00Z","title_canon_sha256":"be23676da479d7fb74aedd57fade35983b1494a42752247acb6c10ccfbfce3fd"},"schema_version":"1.0","source":{"id":"2502.20246","kind":"arxiv","version":2}},"canonical_sha256":"3c21d602b69177264c2efce8cbd96bf800ff2e2760cd914f7637abe96a151053","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3c21d602b69177264c2efce8cbd96bf800ff2e2760cd914f7637abe96a151053","first_computed_at":"2026-07-05T10:21:32.145782Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:21:32.145782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lvkGEhRaJbNPgcXq3zY/p9ZTFKO5WQVYwgvB5FsaAWdMYhJhyZLVjWlHTaQRXu8LTeBtDYQBE8OpMp9mTJ0TCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:21:32.146539Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.20246","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c0b65ee5ee4cd12d07a7731982533cba395220a26bd24efedd6148c6ad4a1b9","sha256:3da2eafde8ec1d2d14881993f2b40b308b12cb76316971e6f276234a7db38ba5"],"state_sha256":"c3d7e3e4e93c4ae52aaca00179be52c07ded561e50f9ad0a88b039a8686b47e3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HknoAvEv/dWzhNdjpkohbNsW1q30t61jw8NVnvH62PtyUVvs4/TSLs2UcuLjLWnRjaGSnU/8+aUeXmxYyt8SAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T19:33:54.325574Z","bundle_sha256":"2eacaddf908627b6fea935c48ca0f4df418517e09f61ce5265b5ff05cc5a1af4"}}