{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:4WCPTRT46YMTWHUA44NH7DHI2V","short_pith_number":"pith:4WCPTRT4","canonical_record":{"source":{"id":"2312.10007","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-15T18:23:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a4b3bf9aa341806d39c84fc071309e93cec184a87a6c2fbca01bea6281a3b93b","abstract_canon_sha256":"041fb082a42093c844aec9a8c16744c2fd3b629dadef8fbcbb45b1839b043afb"},"schema_version":"1.0"},"canonical_sha256":"e584f9c67cf6193b1e80e71a7f8ce8d564bffc92a05fa7ddea427949bdb9018b","source":{"kind":"arxiv","id":"2312.10007","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.10007","created_at":"2026-07-05T07:24:43Z"},{"alias_kind":"arxiv_version","alias_value":"2312.10007v1","created_at":"2026-07-05T07:24:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.10007","created_at":"2026-07-05T07:24:43Z"},{"alias_kind":"pith_short_12","alias_value":"4WCPTRT46YMT","created_at":"2026-07-05T07:24:43Z"},{"alias_kind":"pith_short_16","alias_value":"4WCPTRT46YMTWHUA","created_at":"2026-07-05T07:24:43Z"},{"alias_kind":"pith_short_8","alias_value":"4WCPTRT4","created_at":"2026-07-05T07:24:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:4WCPTRT46YMTWHUA44NH7DHI2V","target":"record","payload":{"canonical_record":{"source":{"id":"2312.10007","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-15T18:23:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a4b3bf9aa341806d39c84fc071309e93cec184a87a6c2fbca01bea6281a3b93b","abstract_canon_sha256":"041fb082a42093c844aec9a8c16744c2fd3b629dadef8fbcbb45b1839b043afb"},"schema_version":"1.0"},"canonical_sha256":"e584f9c67cf6193b1e80e71a7f8ce8d564bffc92a05fa7ddea427949bdb9018b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:43.625551Z","signature_b64":"v/qyEWe0+CWsq/nPN8yPTpuPAI3uW54MsFUt0vb+HL975Gl4oQePn3glrKwnEWYlA/ma2Id+Uj23ADKSiISoAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e584f9c67cf6193b1e80e71a7f8ce8d564bffc92a05fa7ddea427949bdb9018b","last_reissued_at":"2026-07-05T07:24:43.625063Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:43.625063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.10007","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":"2026-07-05T07:24:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iBYGGpHlvudPZa37kBW1JzsHk/EyQtuChz8j/z6jK+NNVML/ixjLehpICYtUqbOjhr11RybdQm1w3T+ZSZVeDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T12:10:56.524326Z"},"content_sha256":"75ea59a607334207d14215f81c7917ce4e6a4b7b1f892c7764c9c1fdf4d5701d","schema_version":"1.0","event_id":"sha256:75ea59a607334207d14215f81c7917ce4e6a4b7b1f892c7764c9c1fdf4d5701d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:4WCPTRT46YMTWHUA44NH7DHI2V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Faithful Persona-based Conversational Dataset Generation with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Hakim Sidahmed, Jay Pujara, Pegah Jandaghi, XiangHai Sheng, Xinyi Bai","submitted_at":"2023-12-15T18:23:50Z","abstract_excerpt":"High-quality conversational datasets are essential for developing AI models that can communicate with users. One way to foster deeper interactions between a chatbot and its user is through personas, aspects of the user's character that provide insights into their personality, motivations, and behaviors. Training Natural Language Processing (NLP) models on a diverse and comprehensive persona-based dataset can lead to conversational models that create a deeper connection with the user, and maintain their engagement. In this paper, we leverage the power of Large Language Models (LLMs) to create a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.10007","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/2312.10007/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":"2026-07-05T07:24:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XzriwBnYnmPa/KEnUGkv2EwkHb0sAHTxJE2UGXKFzYPJ2M3qk/PUN/He3sYh2S9t37I0U7IKES1rqNmvzS4nDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T12:10:56.524882Z"},"content_sha256":"384226889095539192d57650eb8f48f377cc567fe6ecf39b557bb0265944f649","schema_version":"1.0","event_id":"sha256:384226889095539192d57650eb8f48f377cc567fe6ecf39b557bb0265944f649"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4WCPTRT46YMTWHUA44NH7DHI2V/bundle.json","state_url":"https://pith.science/pith/4WCPTRT46YMTWHUA44NH7DHI2V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4WCPTRT46YMTWHUA44NH7DHI2V/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":"2026-08-20T12:10:56Z","links":{"resolver":"https://pith.science/pith/4WCPTRT46YMTWHUA44NH7DHI2V","bundle":"https://pith.science/pith/4WCPTRT46YMTWHUA44NH7DHI2V/bundle.json","state":"https://pith.science/pith/4WCPTRT46YMTWHUA44NH7DHI2V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4WCPTRT46YMTWHUA44NH7DHI2V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4WCPTRT46YMTWHUA44NH7DHI2V","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":"041fb082a42093c844aec9a8c16744c2fd3b629dadef8fbcbb45b1839b043afb","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-15T18:23:50Z","title_canon_sha256":"a4b3bf9aa341806d39c84fc071309e93cec184a87a6c2fbca01bea6281a3b93b"},"schema_version":"1.0","source":{"id":"2312.10007","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.10007","created_at":"2026-07-05T07:24:43Z"},{"alias_kind":"arxiv_version","alias_value":"2312.10007v1","created_at":"2026-07-05T07:24:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.10007","created_at":"2026-07-05T07:24:43Z"},{"alias_kind":"pith_short_12","alias_value":"4WCPTRT46YMT","created_at":"2026-07-05T07:24:43Z"},{"alias_kind":"pith_short_16","alias_value":"4WCPTRT46YMTWHUA","created_at":"2026-07-05T07:24:43Z"},{"alias_kind":"pith_short_8","alias_value":"4WCPTRT4","created_at":"2026-07-05T07:24:43Z"}],"graph_snapshots":[{"event_id":"sha256:384226889095539192d57650eb8f48f377cc567fe6ecf39b557bb0265944f649","target":"graph","created_at":"2026-07-05T07:24:43Z","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/2312.10007/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"High-quality conversational datasets are essential for developing AI models that can communicate with users. One way to foster deeper interactions between a chatbot and its user is through personas, aspects of the user's character that provide insights into their personality, motivations, and behaviors. Training Natural Language Processing (NLP) models on a diverse and comprehensive persona-based dataset can lead to conversational models that create a deeper connection with the user, and maintain their engagement. In this paper, we leverage the power of Large Language Models (LLMs) to create a","authors_text":"Hakim Sidahmed, Jay Pujara, Pegah Jandaghi, XiangHai Sheng, Xinyi Bai","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-15T18:23:50Z","title":"Faithful Persona-based Conversational Dataset Generation with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.10007","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":"sha256:75ea59a607334207d14215f81c7917ce4e6a4b7b1f892c7764c9c1fdf4d5701d","target":"record","created_at":"2026-07-05T07:24:43Z","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":"041fb082a42093c844aec9a8c16744c2fd3b629dadef8fbcbb45b1839b043afb","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-15T18:23:50Z","title_canon_sha256":"a4b3bf9aa341806d39c84fc071309e93cec184a87a6c2fbca01bea6281a3b93b"},"schema_version":"1.0","source":{"id":"2312.10007","kind":"arxiv","version":1}},"canonical_sha256":"e584f9c67cf6193b1e80e71a7f8ce8d564bffc92a05fa7ddea427949bdb9018b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e584f9c67cf6193b1e80e71a7f8ce8d564bffc92a05fa7ddea427949bdb9018b","first_computed_at":"2026-07-05T07:24:43.625063Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:24:43.625063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v/qyEWe0+CWsq/nPN8yPTpuPAI3uW54MsFUt0vb+HL975Gl4oQePn3glrKwnEWYlA/ma2Id+Uj23ADKSiISoAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:24:43.625551Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.10007","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:75ea59a607334207d14215f81c7917ce4e6a4b7b1f892c7764c9c1fdf4d5701d","sha256:384226889095539192d57650eb8f48f377cc567fe6ecf39b557bb0265944f649"],"state_sha256":"42a3f8d6615faf427fadb63a81c2f2d74249cd6dc0a321294907aa1a55edc55a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P0OFnH5FEwWDZtsuX9DjXh5WkQc/6Fdn2AaEa71lSQ4qSMawweF3+QG3l7gxEDMxfSLs+FC1+oGfIrd9sNexAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T12:10:56.531926Z","bundle_sha256":"1a716f9f69618b9f88e96c641208aede0ba06b5f7130bde125bd27ae894b9de9"}}