{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:HCD6DJZZDEZKCHCNQCAIO5A47T","short_pith_number":"pith:HCD6DJZZ","canonical_record":{"source":{"id":"2606.12114","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-10T14:07:41Z","cross_cats_sorted":[],"title_canon_sha256":"83c6c4ec53dbcf125c3716f3c83fd35439f44622c362d1bd52688bbfb46ff11d","abstract_canon_sha256":"0da3d110fd74c571f550b0fa29f3a89c2ec565be4eb1e0b8ff294bcc948a39a1"},"schema_version":"1.0"},"canonical_sha256":"3887e1a7391932a11c4d808087741cfcee208f42852d03a39b4766d150eba17d","source":{"kind":"arxiv","id":"2606.12114","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.12114","created_at":"2026-06-11T01:10:49Z"},{"alias_kind":"arxiv_version","alias_value":"2606.12114v1","created_at":"2026-06-11T01:10:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12114","created_at":"2026-06-11T01:10:49Z"},{"alias_kind":"pith_short_12","alias_value":"HCD6DJZZDEZK","created_at":"2026-06-11T01:10:49Z"},{"alias_kind":"pith_short_16","alias_value":"HCD6DJZZDEZKCHCN","created_at":"2026-06-11T01:10:49Z"},{"alias_kind":"pith_short_8","alias_value":"HCD6DJZZ","created_at":"2026-06-11T01:10:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:HCD6DJZZDEZKCHCNQCAIO5A47T","target":"record","payload":{"canonical_record":{"source":{"id":"2606.12114","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-10T14:07:41Z","cross_cats_sorted":[],"title_canon_sha256":"83c6c4ec53dbcf125c3716f3c83fd35439f44622c362d1bd52688bbfb46ff11d","abstract_canon_sha256":"0da3d110fd74c571f550b0fa29f3a89c2ec565be4eb1e0b8ff294bcc948a39a1"},"schema_version":"1.0"},"canonical_sha256":"3887e1a7391932a11c4d808087741cfcee208f42852d03a39b4766d150eba17d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:10:49.186035Z","signature_b64":"ZoYFMfrl1pwzS962F1M2LbelzeR90KzH0HBYUTvaMGu6UriRulAay0d1PVFHSxbRZIEJYbu5qZ0iwm2iOtR4BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3887e1a7391932a11c4d808087741cfcee208f42852d03a39b4766d150eba17d","last_reissued_at":"2026-06-11T01:10:49.185384Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:10:49.185384Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.12114","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":"2026-06-11T01:10:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YPdhUpBgjhA84iW1zJXZJ6sICyxroPI/TPPF99pYyOscv1DFeYJe6xwHHUAllt/zIFRXcWrPs8dczqfDebtDBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T18:29:16.163652Z"},"content_sha256":"6187dbe63d77bce04710b43aefff75bc4fb7c6d6df3c78daf8795db052c8e4b7","schema_version":"1.0","event_id":"sha256:6187dbe63d77bce04710b43aefff75bc4fb7c6d6df3c78daf8795db052c8e4b7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:HCD6DJZZDEZKCHCNQCAIO5A47T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Detecting Sensitive Personal Information in Japanese Pre-Training Corpora for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daisuke Kawahara, Rei Minamoto, Yusuke Oda","submitted_at":"2026-06-10T14:07:41Z","abstract_excerpt":"Sensitive personal information can appear in large-scale pre-training corpora for large language models (LLMs). Detecting and filtering such information is therefore essential to ensure compliance with privacy regulations and prevent unintended information leakage. However, in contrast to English and other languages, research into sensitive personal information has been limited in the Japanese language. In this study, we focus on sensitive personal data defined as special care-required personal information (SCPI) under Japan's Act on the Protection of Personal Information (APPI). We construct "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12114","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/2606.12114/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":"2026-06-11T01:10:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ej0ojbs6iyuC2LUc+Nar3kc8pacKFqXCvj8WjMloQ6K1vEmVQ5gD2ufFOboKCXRyM2Rgj0HiZnxP0HFDyWKfDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T18:29:16.164017Z"},"content_sha256":"60215ba646cd842b3024831c3253e0a7099554bc63d720f660e75bb623bf199d","schema_version":"1.0","event_id":"sha256:60215ba646cd842b3024831c3253e0a7099554bc63d720f660e75bb623bf199d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HCD6DJZZDEZKCHCNQCAIO5A47T/bundle.json","state_url":"https://pith.science/pith/HCD6DJZZDEZKCHCNQCAIO5A47T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HCD6DJZZDEZKCHCNQCAIO5A47T/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":"2026-06-29T18:29:16Z","links":{"resolver":"https://pith.science/pith/HCD6DJZZDEZKCHCNQCAIO5A47T","bundle":"https://pith.science/pith/HCD6DJZZDEZKCHCNQCAIO5A47T/bundle.json","state":"https://pith.science/pith/HCD6DJZZDEZKCHCNQCAIO5A47T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HCD6DJZZDEZKCHCNQCAIO5A47T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HCD6DJZZDEZKCHCNQCAIO5A47T","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":"0da3d110fd74c571f550b0fa29f3a89c2ec565be4eb1e0b8ff294bcc948a39a1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-10T14:07:41Z","title_canon_sha256":"83c6c4ec53dbcf125c3716f3c83fd35439f44622c362d1bd52688bbfb46ff11d"},"schema_version":"1.0","source":{"id":"2606.12114","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.12114","created_at":"2026-06-11T01:10:49Z"},{"alias_kind":"arxiv_version","alias_value":"2606.12114v1","created_at":"2026-06-11T01:10:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12114","created_at":"2026-06-11T01:10:49Z"},{"alias_kind":"pith_short_12","alias_value":"HCD6DJZZDEZK","created_at":"2026-06-11T01:10:49Z"},{"alias_kind":"pith_short_16","alias_value":"HCD6DJZZDEZKCHCN","created_at":"2026-06-11T01:10:49Z"},{"alias_kind":"pith_short_8","alias_value":"HCD6DJZZ","created_at":"2026-06-11T01:10:49Z"}],"graph_snapshots":[{"event_id":"sha256:60215ba646cd842b3024831c3253e0a7099554bc63d720f660e75bb623bf199d","target":"graph","created_at":"2026-06-11T01:10:49Z","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/2606.12114/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sensitive personal information can appear in large-scale pre-training corpora for large language models (LLMs). Detecting and filtering such information is therefore essential to ensure compliance with privacy regulations and prevent unintended information leakage. However, in contrast to English and other languages, research into sensitive personal information has been limited in the Japanese language. In this study, we focus on sensitive personal data defined as special care-required personal information (SCPI) under Japan's Act on the Protection of Personal Information (APPI). We construct ","authors_text":"Daisuke Kawahara, Rei Minamoto, Yusuke Oda","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-10T14:07:41Z","title":"Detecting Sensitive Personal Information in Japanese Pre-Training Corpora for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12114","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":"sha256:6187dbe63d77bce04710b43aefff75bc4fb7c6d6df3c78daf8795db052c8e4b7","target":"record","created_at":"2026-06-11T01:10:49Z","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":"0da3d110fd74c571f550b0fa29f3a89c2ec565be4eb1e0b8ff294bcc948a39a1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-10T14:07:41Z","title_canon_sha256":"83c6c4ec53dbcf125c3716f3c83fd35439f44622c362d1bd52688bbfb46ff11d"},"schema_version":"1.0","source":{"id":"2606.12114","kind":"arxiv","version":1}},"canonical_sha256":"3887e1a7391932a11c4d808087741cfcee208f42852d03a39b4766d150eba17d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3887e1a7391932a11c4d808087741cfcee208f42852d03a39b4766d150eba17d","first_computed_at":"2026-06-11T01:10:49.185384Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T01:10:49.185384Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZoYFMfrl1pwzS962F1M2LbelzeR90KzH0HBYUTvaMGu6UriRulAay0d1PVFHSxbRZIEJYbu5qZ0iwm2iOtR4BA==","signature_status":"signed_v1","signed_at":"2026-06-11T01:10:49.186035Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.12114","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6187dbe63d77bce04710b43aefff75bc4fb7c6d6df3c78daf8795db052c8e4b7","sha256:60215ba646cd842b3024831c3253e0a7099554bc63d720f660e75bb623bf199d"],"state_sha256":"c7f01b2ae13fd273d7075751665357f636834e7821aab5c65d4db39f0e4ad92b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ANIITfihSXwwcY0LNESC466u835hlXhaFolVFJl6WEdDaQnI2x30uC8AnzKU1+dzspNRsu51u42H4UQSpYy8DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T18:29:16.166094Z","bundle_sha256":"9a584ada6f8665c89b2c57edb0d62ceb1592faf7d59dc25ea1d597d2c67fcab5"}}