{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BITE7BHAHLVJNGGYATD2MHAMRN","short_pith_number":"pith:BITE7BHA","canonical_record":{"source":{"id":"2409.14200","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-21T17:12:18Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"cf023c44494bd579a1845a2668ef20a1a59eff5a24f5ddf2606c9fac67888697","abstract_canon_sha256":"026b4bcb838066f1c4582cbfd3ad494dd4716d5755aff0534106d486449e6a7c"},"schema_version":"1.0"},"canonical_sha256":"0a264f84e03aea9698d804c7a61c0c8b45cfadff1f7aae39f0be6d507adaa770","source":{"kind":"arxiv","id":"2409.14200","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.14200","created_at":"2026-07-05T09:10:13Z"},{"alias_kind":"arxiv_version","alias_value":"2409.14200v1","created_at":"2026-07-05T09:10:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.14200","created_at":"2026-07-05T09:10:13Z"},{"alias_kind":"pith_short_12","alias_value":"BITE7BHAHLVJ","created_at":"2026-07-05T09:10:13Z"},{"alias_kind":"pith_short_16","alias_value":"BITE7BHAHLVJNGGY","created_at":"2026-07-05T09:10:13Z"},{"alias_kind":"pith_short_8","alias_value":"BITE7BHA","created_at":"2026-07-05T09:10:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BITE7BHAHLVJNGGYATD2MHAMRN","target":"record","payload":{"canonical_record":{"source":{"id":"2409.14200","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-21T17:12:18Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"cf023c44494bd579a1845a2668ef20a1a59eff5a24f5ddf2606c9fac67888697","abstract_canon_sha256":"026b4bcb838066f1c4582cbfd3ad494dd4716d5755aff0534106d486449e6a7c"},"schema_version":"1.0"},"canonical_sha256":"0a264f84e03aea9698d804c7a61c0c8b45cfadff1f7aae39f0be6d507adaa770","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:13.233170Z","signature_b64":"q+FMB1v49S5nDNsxo4QQdEFkpygo5ZhPNl6KMgISPAuLQsvt8ckgFTCCmd/TyL9BCxr7fV3+n+449tJG+3ThCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a264f84e03aea9698d804c7a61c0c8b45cfadff1f7aae39f0be6d507adaa770","last_reissued_at":"2026-07-05T09:10:13.232680Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:13.232680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.14200","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":"2026-07-05T09:10:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9/Rn1x0ZKJr5e/mTPO+WOwZkpoSbo042u9uEhvKdGN2RtDRMxk5RIdFZvIiCknrS11U5pmoQspLq5nli51m8Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T20:59:31.301938Z"},"content_sha256":"7420546847ec1ce9de8bfa5205a553a86ba5fd338a6b28c08ac0ac8a8d073d8a","schema_version":"1.0","event_id":"sha256:7420546847ec1ce9de8bfa5205a553a86ba5fd338a6b28c08ac0ac8a8d073d8a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BITE7BHAHLVJNGGYATD2MHAMRN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data-centric NLP Backdoor Defense from the Lens of Memorization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Juan Zhai, Mengnan Du, Mingyu Jin, Shiqing Ma, Zhenting Wang, Zhizhi Wang","submitted_at":"2024-09-21T17:12:18Z","abstract_excerpt":"Backdoor attack is a severe threat to the trustworthiness of DNN-based language models. In this paper, we first extend the definition of memorization of language models from sample-wise to more fine-grained sentence element-wise (e.g., word, phrase, structure, and style), and then point out that language model backdoors are a type of element-wise memorization. Through further analysis, we find that the strength of such memorization is positively correlated to the frequency of duplicated elements in the training dataset. In conclusion, duplicated sentence elements are necessary for successful b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.14200","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/2409.14200/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":"2026-07-05T09:10:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mcg2FtLsCvNt6X2GNhb7docCFLyhBkXnhqoVimbLHIzo3A5uOdXuTY4rAhBiaimoXJtESGiLLtFuUPpaesr6Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T20:59:31.302443Z"},"content_sha256":"ad394f9b1bfb0bf853fd980bbd3907ef65cd129903fff4e35628c974f59bc301","schema_version":"1.0","event_id":"sha256:ad394f9b1bfb0bf853fd980bbd3907ef65cd129903fff4e35628c974f59bc301"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BITE7BHAHLVJNGGYATD2MHAMRN/bundle.json","state_url":"https://pith.science/pith/BITE7BHAHLVJNGGYATD2MHAMRN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BITE7BHAHLVJNGGYATD2MHAMRN/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":"2026-08-07T20:59:31Z","links":{"resolver":"https://pith.science/pith/BITE7BHAHLVJNGGYATD2MHAMRN","bundle":"https://pith.science/pith/BITE7BHAHLVJNGGYATD2MHAMRN/bundle.json","state":"https://pith.science/pith/BITE7BHAHLVJNGGYATD2MHAMRN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BITE7BHAHLVJNGGYATD2MHAMRN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BITE7BHAHLVJNGGYATD2MHAMRN","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":"026b4bcb838066f1c4582cbfd3ad494dd4716d5755aff0534106d486449e6a7c","cross_cats_sorted":["cs.CR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-21T17:12:18Z","title_canon_sha256":"cf023c44494bd579a1845a2668ef20a1a59eff5a24f5ddf2606c9fac67888697"},"schema_version":"1.0","source":{"id":"2409.14200","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.14200","created_at":"2026-07-05T09:10:13Z"},{"alias_kind":"arxiv_version","alias_value":"2409.14200v1","created_at":"2026-07-05T09:10:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.14200","created_at":"2026-07-05T09:10:13Z"},{"alias_kind":"pith_short_12","alias_value":"BITE7BHAHLVJ","created_at":"2026-07-05T09:10:13Z"},{"alias_kind":"pith_short_16","alias_value":"BITE7BHAHLVJNGGY","created_at":"2026-07-05T09:10:13Z"},{"alias_kind":"pith_short_8","alias_value":"BITE7BHA","created_at":"2026-07-05T09:10:13Z"}],"graph_snapshots":[{"event_id":"sha256:ad394f9b1bfb0bf853fd980bbd3907ef65cd129903fff4e35628c974f59bc301","target":"graph","created_at":"2026-07-05T09:10:13Z","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/2409.14200/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Backdoor attack is a severe threat to the trustworthiness of DNN-based language models. In this paper, we first extend the definition of memorization of language models from sample-wise to more fine-grained sentence element-wise (e.g., word, phrase, structure, and style), and then point out that language model backdoors are a type of element-wise memorization. Through further analysis, we find that the strength of such memorization is positively correlated to the frequency of duplicated elements in the training dataset. In conclusion, duplicated sentence elements are necessary for successful b","authors_text":"Juan Zhai, Mengnan Du, Mingyu Jin, Shiqing Ma, Zhenting Wang, Zhizhi Wang","cross_cats":["cs.CR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-21T17:12:18Z","title":"Data-centric NLP Backdoor Defense from the Lens of Memorization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.14200","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":"sha256:7420546847ec1ce9de8bfa5205a553a86ba5fd338a6b28c08ac0ac8a8d073d8a","target":"record","created_at":"2026-07-05T09:10:13Z","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":"026b4bcb838066f1c4582cbfd3ad494dd4716d5755aff0534106d486449e6a7c","cross_cats_sorted":["cs.CR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-21T17:12:18Z","title_canon_sha256":"cf023c44494bd579a1845a2668ef20a1a59eff5a24f5ddf2606c9fac67888697"},"schema_version":"1.0","source":{"id":"2409.14200","kind":"arxiv","version":1}},"canonical_sha256":"0a264f84e03aea9698d804c7a61c0c8b45cfadff1f7aae39f0be6d507adaa770","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0a264f84e03aea9698d804c7a61c0c8b45cfadff1f7aae39f0be6d507adaa770","first_computed_at":"2026-07-05T09:10:13.232680Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:10:13.232680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q+FMB1v49S5nDNsxo4QQdEFkpygo5ZhPNl6KMgISPAuLQsvt8ckgFTCCmd/TyL9BCxr7fV3+n+449tJG+3ThCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:10:13.233170Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.14200","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7420546847ec1ce9de8bfa5205a553a86ba5fd338a6b28c08ac0ac8a8d073d8a","sha256:ad394f9b1bfb0bf853fd980bbd3907ef65cd129903fff4e35628c974f59bc301"],"state_sha256":"28cf158a019817b679b3c6f0164f1b0654705e972dcc78f5a1b39509a428544c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XTz2pvjPQxHOFVG8LsYLhKnXiTaDtJIE8Fs904Y/HA/OZZ6C9+NUDLQ8Igl1nT+KE3ahFxMA3fSoMb7g3vjPBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T20:59:31.306516Z","bundle_sha256":"183d83c4711cbdde63e9ae74600adcad7235f938652d3c75033ca395de1771b0"}}