{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:NDDZTFBMGPKNOIKCQGFJ54XEYX","short_pith_number":"pith:NDDZTFBM","canonical_record":{"source":{"id":"2606.30312","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-29T13:54:04Z","cross_cats_sorted":[],"title_canon_sha256":"7d532d3f602b0e3fcac39a142e94de150b0dfe84a4e2cbd32030c1ea8c2140c5","abstract_canon_sha256":"e5990397293f0e346bac2f35d93a01245aee9017f088b862e7944142f7a9b876"},"schema_version":"1.0"},"canonical_sha256":"68c799942c33d4d72142818a9ef2e4c5d0093c119c02e9ceff9bb0c563235c50","source":{"kind":"arxiv","id":"2606.30312","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.30312","created_at":"2026-06-30T02:17:58Z"},{"alias_kind":"arxiv_version","alias_value":"2606.30312v1","created_at":"2026-06-30T02:17:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30312","created_at":"2026-06-30T02:17:58Z"},{"alias_kind":"pith_short_12","alias_value":"NDDZTFBMGPKN","created_at":"2026-06-30T02:17:58Z"},{"alias_kind":"pith_short_16","alias_value":"NDDZTFBMGPKNOIKC","created_at":"2026-06-30T02:17:58Z"},{"alias_kind":"pith_short_8","alias_value":"NDDZTFBM","created_at":"2026-06-30T02:17:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:NDDZTFBMGPKNOIKCQGFJ54XEYX","target":"record","payload":{"canonical_record":{"source":{"id":"2606.30312","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-29T13:54:04Z","cross_cats_sorted":[],"title_canon_sha256":"7d532d3f602b0e3fcac39a142e94de150b0dfe84a4e2cbd32030c1ea8c2140c5","abstract_canon_sha256":"e5990397293f0e346bac2f35d93a01245aee9017f088b862e7944142f7a9b876"},"schema_version":"1.0"},"canonical_sha256":"68c799942c33d4d72142818a9ef2e4c5d0093c119c02e9ceff9bb0c563235c50","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:58.817785Z","signature_b64":"67U9haOChiLfC55GVl6AQWCuT3ixuXXs29X21A+wJqT7nsOr3jlWzkIKMau1BA6Y+F58j52iRzcdsdNHUzGwDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68c799942c33d4d72142818a9ef2e4c5d0093c119c02e9ceff9bb0c563235c50","last_reissued_at":"2026-06-30T02:17:58.817140Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:58.817140Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.30312","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":"2026-06-30T02:17:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VysMyeiBDyC6eTsg6qEjD3EUAckPJtRQn5r/1JaYl7XPLNW82Th1c68O+oFwpISKSK3c4A+jbrLrXMbxh+UrDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:16:56.700554Z"},"content_sha256":"867c83bd41c729586c4e56c58cb4679079f0bb1a7854f535baf785c04fabd8aa","schema_version":"1.0","event_id":"sha256:867c83bd41c729586c4e56c58cb4679079f0bb1a7854f535baf785c04fabd8aa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:NDDZTFBMGPKNOIKCQGFJ54XEYX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DialogPII: A multilingual dataset of synthetic dialog transcripts to detect personal information","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aaron Louis Eidt, Akhil Juneja, Christine Hovhannisyan, Derya Erman, Eletta Giusto, Fr\\'ed\\'eric Blain, Ibrahim Baroud, Lisa Raithel, Luke Flanagan, Maija Poikela, Mariana Neves, Maria S{\\l}owi\\'nska, Roland Roller, Sebastian M\\\"oller, Vera Czehmann, Viviana Cotik","submitted_at":"2026-06-29T13:54:04Z","abstract_excerpt":"Conversational data collected in domains such as healthcare or social sciences is a valuable resource for research and automated analysis. However, responsible data sharing requires the detection and removal of personally identifiable and sensitive information to protect individual privacy. To support the development and evaluation of automatic de-identification systems, we present DialogPII, a multilingual dataset of synthetic dialogs and speech-derived transcripts for personal information detection. DialogPII covers eight interaction scenarios (emergency calls, medical anamnesis interviews, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30312","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/2606.30312/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":"2026-06-30T02:17:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iKEC6VaYK3hdStlmsHN6tFntCC912lJJyWTT35RjPKIlS6GgQfovrrF7qq0u4soG02O7N/hvTO0zFJeAp3EoAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:16:56.701500Z"},"content_sha256":"b26360ba8be46ac7c531bb86112eb6faa466d0c4cfcb84bff5686267e55910a1","schema_version":"1.0","event_id":"sha256:b26360ba8be46ac7c531bb86112eb6faa466d0c4cfcb84bff5686267e55910a1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NDDZTFBMGPKNOIKCQGFJ54XEYX/bundle.json","state_url":"https://pith.science/pith/NDDZTFBMGPKNOIKCQGFJ54XEYX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NDDZTFBMGPKNOIKCQGFJ54XEYX/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":"2026-08-03T19:16:56Z","links":{"resolver":"https://pith.science/pith/NDDZTFBMGPKNOIKCQGFJ54XEYX","bundle":"https://pith.science/pith/NDDZTFBMGPKNOIKCQGFJ54XEYX/bundle.json","state":"https://pith.science/pith/NDDZTFBMGPKNOIKCQGFJ54XEYX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NDDZTFBMGPKNOIKCQGFJ54XEYX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NDDZTFBMGPKNOIKCQGFJ54XEYX","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":"e5990397293f0e346bac2f35d93a01245aee9017f088b862e7944142f7a9b876","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-29T13:54:04Z","title_canon_sha256":"7d532d3f602b0e3fcac39a142e94de150b0dfe84a4e2cbd32030c1ea8c2140c5"},"schema_version":"1.0","source":{"id":"2606.30312","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.30312","created_at":"2026-06-30T02:17:58Z"},{"alias_kind":"arxiv_version","alias_value":"2606.30312v1","created_at":"2026-06-30T02:17:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30312","created_at":"2026-06-30T02:17:58Z"},{"alias_kind":"pith_short_12","alias_value":"NDDZTFBMGPKN","created_at":"2026-06-30T02:17:58Z"},{"alias_kind":"pith_short_16","alias_value":"NDDZTFBMGPKNOIKC","created_at":"2026-06-30T02:17:58Z"},{"alias_kind":"pith_short_8","alias_value":"NDDZTFBM","created_at":"2026-06-30T02:17:58Z"}],"graph_snapshots":[{"event_id":"sha256:b26360ba8be46ac7c531bb86112eb6faa466d0c4cfcb84bff5686267e55910a1","target":"graph","created_at":"2026-06-30T02:17:58Z","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/2606.30312/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Conversational data collected in domains such as healthcare or social sciences is a valuable resource for research and automated analysis. However, responsible data sharing requires the detection and removal of personally identifiable and sensitive information to protect individual privacy. To support the development and evaluation of automatic de-identification systems, we present DialogPII, a multilingual dataset of synthetic dialogs and speech-derived transcripts for personal information detection. DialogPII covers eight interaction scenarios (emergency calls, medical anamnesis interviews, ","authors_text":"Aaron Louis Eidt, Akhil Juneja, Christine Hovhannisyan, Derya Erman, Eletta Giusto, Fr\\'ed\\'eric Blain, Ibrahim Baroud, Lisa Raithel, Luke Flanagan, Maija Poikela, Mariana Neves, Maria S{\\l}owi\\'nska, Roland Roller, Sebastian M\\\"oller, Vera Czehmann, Viviana Cotik","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-29T13:54:04Z","title":"DialogPII: A multilingual dataset of synthetic dialog transcripts to detect personal information"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30312","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":"sha256:867c83bd41c729586c4e56c58cb4679079f0bb1a7854f535baf785c04fabd8aa","target":"record","created_at":"2026-06-30T02:17:58Z","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":"e5990397293f0e346bac2f35d93a01245aee9017f088b862e7944142f7a9b876","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-29T13:54:04Z","title_canon_sha256":"7d532d3f602b0e3fcac39a142e94de150b0dfe84a4e2cbd32030c1ea8c2140c5"},"schema_version":"1.0","source":{"id":"2606.30312","kind":"arxiv","version":1}},"canonical_sha256":"68c799942c33d4d72142818a9ef2e4c5d0093c119c02e9ceff9bb0c563235c50","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68c799942c33d4d72142818a9ef2e4c5d0093c119c02e9ceff9bb0c563235c50","first_computed_at":"2026-06-30T02:17:58.817140Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T02:17:58.817140Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"67U9haOChiLfC55GVl6AQWCuT3ixuXXs29X21A+wJqT7nsOr3jlWzkIKMau1BA6Y+F58j52iRzcdsdNHUzGwDw==","signature_status":"signed_v1","signed_at":"2026-06-30T02:17:58.817785Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.30312","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:867c83bd41c729586c4e56c58cb4679079f0bb1a7854f535baf785c04fabd8aa","sha256:b26360ba8be46ac7c531bb86112eb6faa466d0c4cfcb84bff5686267e55910a1"],"state_sha256":"65b500128ab7bf48d0d0cc524f71b816b9cbe09087f649b8794d9b2b1a475ef5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/6CmuhyXmGWH3ABCe/ED+1lgU6NtHrWqu9wHsG85khHSFZLOzRRxnhH5xGiWCLI2fGUfojNwjKSbUJgayRQGBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T19:16:56.709759Z","bundle_sha256":"7c95a019d9f59918c60901cb2ca3a4a19a6b876c7da28ece14dd24206d854c0d"}}