{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TLVLBZXLXPUP3MMLZVXCE4F6WJ","short_pith_number":"pith:TLVLBZXL","canonical_record":{"source":{"id":"2405.01470","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-02T17:00:02Z","cross_cats_sorted":[],"title_canon_sha256":"050f37ac94c115de31819627bb2d1efd7df3e488fcfb6923270c7f118167b764","abstract_canon_sha256":"bbea487f1520b1acdffe8c1ab90cb28c38e1c7a4e1eda33deb94693d5ca43609"},"schema_version":"1.0"},"canonical_sha256":"9aeab0e6ebbbe8fdb18bcd6e2270beb25f386b7378992db39b4145729627175e","source":{"kind":"arxiv","id":"2405.01470","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.01470","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"arxiv_version","alias_value":"2405.01470v1","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.01470","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"pith_short_12","alias_value":"TLVLBZXLXPUP","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"TLVLBZXLXPUP3MML","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"TLVLBZXL","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TLVLBZXLXPUP3MMLZVXCE4F6WJ","target":"record","payload":{"canonical_record":{"source":{"id":"2405.01470","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-02T17:00:02Z","cross_cats_sorted":[],"title_canon_sha256":"050f37ac94c115de31819627bb2d1efd7df3e488fcfb6923270c7f118167b764","abstract_canon_sha256":"bbea487f1520b1acdffe8c1ab90cb28c38e1c7a4e1eda33deb94693d5ca43609"},"schema_version":"1.0"},"canonical_sha256":"9aeab0e6ebbbe8fdb18bcd6e2270beb25f386b7378992db39b4145729627175e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:48.151870Z","signature_b64":"9oDpxXCl2at1tZzzCVL/Ixx30kRE4637wJPaD1z/8yCe+gJklD4nNGt+1g2Y/mObwMF84I35UeEe0QHSi4BqBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9aeab0e6ebbbe8fdb18bcd6e2270beb25f386b7378992db39b4145729627175e","last_reissued_at":"2026-05-17T23:38:48.151382Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:48.151382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.01470","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":"2026-05-17T23:38:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/Ov+y+jVZTPupHrb90JpGaH2SErtt1l19tRhZW9qWpfNcUVYGmTs4KbLqlM4CXjTuxjvPaNzInpphjKscXG9Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T20:43:28.921625Z"},"content_sha256":"2327c0ba7001733e6c652fe8a6c125c46f55956e0e324065e3901a42898b5080","schema_version":"1.0","event_id":"sha256:2327c0ba7001733e6c652fe8a6c125c46f55956e0e324065e3901a42898b5080"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TLVLBZXLXPUP3MMLZVXCE4F6WJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"WildChat: 1M ChatGPT Interaction Logs in the Wild","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A corpus of one million real ChatGPT conversations was assembled from users who opted in for free access.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Claire Cardie, Jack Hessel, Wenting Zhao, Xiang Ren, Yejin Choi, Yuntian Deng","submitted_at":"2024-05-02T17:00:02Z","abstract_excerpt":"Chatbots such as GPT-4 and ChatGPT are now serving millions of users. Despite their widespread use, there remains a lack of public datasets showcasing how these tools are used by a population of users in practice. To bridge this gap, we offered free access to ChatGPT for online users in exchange for their affirmative, consensual opt-in to anonymously collect their chat transcripts and request headers. From this, we compiled WildChat, a corpus of 1 million user-ChatGPT conversations, which consists of over 2.5 million interaction turns. We compare WildChat with other popular user-chatbot intera"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"we compiled WildChat, a corpus of 1 million user-ChatGPT conversations... offers the most diverse user prompts, contains the largest number of languages, and presents the richest variety of potentially toxic use-cases for researchers to study.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The opt-in consent process produces a representative sample of ChatGPT users without major selection bias from users who choose to participate or from the free-access incentive.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"WildChat releases a dataset of 1 million ChatGPT conversations with timestamps, demographics, and headers, claimed to be the most diverse and multilingual such resource available.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A corpus of one million real ChatGPT conversations was assembled from users who opted in for free access.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"f73a3f640728c594acc0f0d03d22c617a5e4893a169a212d3dc909226787b862"},"source":{"id":"2405.01470","kind":"arxiv","version":1},"verdict":{"id":"71d93274-81a8-481b-a528-8c289477e40d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T10:40:02.109654Z","strongest_claim":"we compiled WildChat, a corpus of 1 million user-ChatGPT conversations... offers the most diverse user prompts, contains the largest number of languages, and presents the richest variety of potentially toxic use-cases for researchers to study.","one_line_summary":"WildChat releases a dataset of 1 million ChatGPT conversations with timestamps, demographics, and headers, claimed to be the most diverse and multilingual such resource available.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The opt-in consent process produces a representative sample of ChatGPT users without major selection bias from users who choose to participate or from the free-access incentive.","pith_extraction_headline":"A corpus of one million real ChatGPT conversations was assembled from users who opted in for free access."},"references":{"count":54,"sample":[{"doi":"","year":2023,"title":"Model card and evaluations for claude models, Jul 2023","work_id":"c66a93f2-bf62-4115-b48b-7f13aff667f3","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Bowman, Zac Hatfield-Dodds, Ben Mann, Dario Amodei, Nicholas Joseph, Sam McCandlish, Tom Brown, and Jared Kaplan","work_id":"19bc1946-1565-4328-92ea-a230a57a8bbf","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Free dolly: Introducing the world’s first truly open instruction-tuned llm, 2023","work_id":"ab41d2b1-6296-4ba7-9db5-c040d5310c3b","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Bard: A conversational ai tool by google, 2023","work_id":"d5be1bf4-947a-4e2c-9cd2-60f9d14ecfd2","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Laura Hanu and Unitary team . Detoxify. Github. https://github.com/unitaryai/detoxify, 2020","work_id":"a383ee20-a51e-4a32-a272-058028fdf086","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":54,"snapshot_sha256":"eac8c3d4ebb3dd7dce7d88f4d040e1a4287d8c941d94479142d0986bba471875","internal_anchors":1},"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":"71d93274-81a8-481b-a528-8c289477e40d"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h1wREQfaXYB+BzD1VE566RRad/p8QV7G5Z1M/wWOUwuGVjXjAzqYOU8tiJpI07SrjuXMd/v9i9aBCoVyORzrCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T20:43:28.922712Z"},"content_sha256":"75310388aa9a4c233aabd0c273d88a7e9b01f86002f735d846c0fd9f35d78cbc","schema_version":"1.0","event_id":"sha256:75310388aa9a4c233aabd0c273d88a7e9b01f86002f735d846c0fd9f35d78cbc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TLVLBZXLXPUP3MMLZVXCE4F6WJ/bundle.json","state_url":"https://pith.science/pith/TLVLBZXLXPUP3MMLZVXCE4F6WJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TLVLBZXLXPUP3MMLZVXCE4F6WJ/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":"2026-05-27T20:43:28Z","links":{"resolver":"https://pith.science/pith/TLVLBZXLXPUP3MMLZVXCE4F6WJ","bundle":"https://pith.science/pith/TLVLBZXLXPUP3MMLZVXCE4F6WJ/bundle.json","state":"https://pith.science/pith/TLVLBZXLXPUP3MMLZVXCE4F6WJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TLVLBZXLXPUP3MMLZVXCE4F6WJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TLVLBZXLXPUP3MMLZVXCE4F6WJ","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":"bbea487f1520b1acdffe8c1ab90cb28c38e1c7a4e1eda33deb94693d5ca43609","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-02T17:00:02Z","title_canon_sha256":"050f37ac94c115de31819627bb2d1efd7df3e488fcfb6923270c7f118167b764"},"schema_version":"1.0","source":{"id":"2405.01470","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.01470","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"arxiv_version","alias_value":"2405.01470v1","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.01470","created_at":"2026-05-17T23:38:48Z"},{"alias_kind":"pith_short_12","alias_value":"TLVLBZXLXPUP","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"TLVLBZXLXPUP3MML","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"TLVLBZXL","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:75310388aa9a4c233aabd0c273d88a7e9b01f86002f735d846c0fd9f35d78cbc","target":"graph","created_at":"2026-05-17T23:38:48Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"we compiled WildChat, a corpus of 1 million user-ChatGPT conversations... offers the most diverse user prompts, contains the largest number of languages, and presents the richest variety of potentially toxic use-cases for researchers to study."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The opt-in consent process produces a representative sample of ChatGPT users without major selection bias from users who choose to participate or from the free-access incentive."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"WildChat releases a dataset of 1 million ChatGPT conversations with timestamps, demographics, and headers, claimed to be the most diverse and multilingual such resource available."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A corpus of one million real ChatGPT conversations was assembled from users who opted in for free access."}],"snapshot_sha256":"f73a3f640728c594acc0f0d03d22c617a5e4893a169a212d3dc909226787b862"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Chatbots such as GPT-4 and ChatGPT are now serving millions of users. Despite their widespread use, there remains a lack of public datasets showcasing how these tools are used by a population of users in practice. To bridge this gap, we offered free access to ChatGPT for online users in exchange for their affirmative, consensual opt-in to anonymously collect their chat transcripts and request headers. From this, we compiled WildChat, a corpus of 1 million user-ChatGPT conversations, which consists of over 2.5 million interaction turns. We compare WildChat with other popular user-chatbot intera","authors_text":"Claire Cardie, Jack Hessel, Wenting Zhao, Xiang Ren, Yejin Choi, Yuntian Deng","cross_cats":[],"headline":"A corpus of one million real ChatGPT conversations was assembled from users who opted in for free access.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-02T17:00:02Z","title":"WildChat: 1M ChatGPT Interaction Logs in the Wild"},"references":{"count":54,"internal_anchors":1,"resolved_work":54,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Model card and evaluations for claude models, Jul 2023","work_id":"c66a93f2-bf62-4115-b48b-7f13aff667f3","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Bowman, Zac Hatfield-Dodds, Ben Mann, Dario Amodei, Nicholas Joseph, Sam McCandlish, Tom Brown, and Jared Kaplan","work_id":"19bc1946-1565-4328-92ea-a230a57a8bbf","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Free dolly: Introducing the world’s first truly open instruction-tuned llm, 2023","work_id":"ab41d2b1-6296-4ba7-9db5-c040d5310c3b","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Bard: A conversational ai tool by google, 2023","work_id":"d5be1bf4-947a-4e2c-9cd2-60f9d14ecfd2","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Laura Hanu and Unitary team . Detoxify. Github. https://github.com/unitaryai/detoxify, 2020","work_id":"a383ee20-a51e-4a32-a272-058028fdf086","year":2020}],"snapshot_sha256":"eac8c3d4ebb3dd7dce7d88f4d040e1a4287d8c941d94479142d0986bba471875"},"source":{"id":"2405.01470","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-16T10:40:02.109654Z","id":"71d93274-81a8-481b-a528-8c289477e40d","model_set":{"reader":"grok-4.3"},"one_line_summary":"WildChat releases a dataset of 1 million ChatGPT conversations with timestamps, demographics, and headers, claimed to be the most diverse and multilingual such resource available.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A corpus of one million real ChatGPT conversations was assembled from users who opted in for free access.","strongest_claim":"we compiled WildChat, a corpus of 1 million user-ChatGPT conversations... offers the most diverse user prompts, contains the largest number of languages, and presents the richest variety of potentially toxic use-cases for researchers to study.","weakest_assumption":"The opt-in consent process produces a representative sample of ChatGPT users without major selection bias from users who choose to participate or from the free-access incentive."}},"verdict_id":"71d93274-81a8-481b-a528-8c289477e40d"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2327c0ba7001733e6c652fe8a6c125c46f55956e0e324065e3901a42898b5080","target":"record","created_at":"2026-05-17T23:38:48Z","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":"bbea487f1520b1acdffe8c1ab90cb28c38e1c7a4e1eda33deb94693d5ca43609","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-02T17:00:02Z","title_canon_sha256":"050f37ac94c115de31819627bb2d1efd7df3e488fcfb6923270c7f118167b764"},"schema_version":"1.0","source":{"id":"2405.01470","kind":"arxiv","version":1}},"canonical_sha256":"9aeab0e6ebbbe8fdb18bcd6e2270beb25f386b7378992db39b4145729627175e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9aeab0e6ebbbe8fdb18bcd6e2270beb25f386b7378992db39b4145729627175e","first_computed_at":"2026-05-17T23:38:48.151382Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:48.151382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9oDpxXCl2at1tZzzCVL/Ixx30kRE4637wJPaD1z/8yCe+gJklD4nNGt+1g2Y/mObwMF84I35UeEe0QHSi4BqBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:48.151870Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.01470","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2327c0ba7001733e6c652fe8a6c125c46f55956e0e324065e3901a42898b5080","sha256:75310388aa9a4c233aabd0c273d88a7e9b01f86002f735d846c0fd9f35d78cbc"],"state_sha256":"cebd833abb8553b0a5bbab5510d315fd8ce066caa01abcd23043ff3963c960c6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eLi9apu48RlU+svDcy9gO+3WFVIaT0xY+3beh8ro6+xs0vq8gPgREe5eGUREsYt1qqDjbTRhmBAR1BeO5uU2Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T20:43:28.926465Z","bundle_sha256":"332d3318ac5bdcf6572a93f8b158e990fb0749576e1ae4e84fa75f9dda5ce899"}}