{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:J7IYASYI2EODHVMKWZGFEFDDYO","short_pith_number":"pith:J7IYASYI","schema_version":"1.0","canonical_sha256":"4fd1804b08d11c33d58ab64c521463c3b48271ab415c3888f5e4925d9e02b37f","source":{"kind":"arxiv","id":"2501.18511","version":2},"attestation_state":"computed","paper":{"title":"WILDCHAT-50M: A Deep Dive Into the Role of Synthetic Data in Post-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Benjamin Feuer, Chinmay Hegde","submitted_at":"2025-01-30T17:21:44Z","abstract_excerpt":"Language model (LLM) post-training, from DPO to distillation, can refine behaviors and unlock new skills, but the open science supporting these post-training techniques is still in its infancy. One limiting factor has been the difficulty of conducting large-scale comparative analyses of synthetic data generating models and LLM judges. To close this gap, we introduce WILDCHAT-50M, the largest public chat dataset to date. We extend the existing WildChat dataset to include responses not only from GPT, but from over 50 different open-weight models, ranging in size from 0.5B to 104B parameters. We "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2501.18511","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-30T17:21:44Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a2abdc1d00f895d58feaded1c22e4416ae95302eb2b0f50a2f941e314993c704","abstract_canon_sha256":"2fe6f6a88d3677a47b8b198230f1d9d36d1547468093ad396b2faa0220db471f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:15.688118Z","signature_b64":"9hwJSMMgW3WxAN5/uj4XYopc6R3xkCOoMmcgS7SC1Vc48cDjeVfJ7f2xenLplgRl0IEJYY6gHMMO9aFn9ltsAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4fd1804b08d11c33d58ab64c521463c3b48271ab415c3888f5e4925d9e02b37f","last_reissued_at":"2026-07-05T11:08:15.687631Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:15.687631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WILDCHAT-50M: A Deep Dive Into the Role of Synthetic Data in Post-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Benjamin Feuer, Chinmay Hegde","submitted_at":"2025-01-30T17:21:44Z","abstract_excerpt":"Language model (LLM) post-training, from DPO to distillation, can refine behaviors and unlock new skills, but the open science supporting these post-training techniques is still in its infancy. One limiting factor has been the difficulty of conducting large-scale comparative analyses of synthetic data generating models and LLM judges. To close this gap, we introduce WILDCHAT-50M, the largest public chat dataset to date. We extend the existing WildChat dataset to include responses not only from GPT, but from over 50 different open-weight models, ranging in size from 0.5B to 104B parameters. We "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18511","kind":"arxiv","version":2},"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/2501.18511/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2501.18511","created_at":"2026-07-05T11:08:15.687697+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.18511v2","created_at":"2026-07-05T11:08:15.687697+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18511","created_at":"2026-07-05T11:08:15.687697+00:00"},{"alias_kind":"pith_short_12","alias_value":"J7IYASYI2EOD","created_at":"2026-07-05T11:08:15.687697+00:00"},{"alias_kind":"pith_short_16","alias_value":"J7IYASYI2EODHVMK","created_at":"2026-07-05T11:08:15.687697+00:00"},{"alias_kind":"pith_short_8","alias_value":"J7IYASYI","created_at":"2026-07-05T11:08:15.687697+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J7IYASYI2EODHVMKWZGFEFDDYO","json":"https://pith.science/pith/J7IYASYI2EODHVMKWZGFEFDDYO.json","graph_json":"https://pith.science/api/pith-number/J7IYASYI2EODHVMKWZGFEFDDYO/graph.json","events_json":"https://pith.science/api/pith-number/J7IYASYI2EODHVMKWZGFEFDDYO/events.json","paper":"https://pith.science/paper/J7IYASYI"},"agent_actions":{"view_html":"https://pith.science/pith/J7IYASYI2EODHVMKWZGFEFDDYO","download_json":"https://pith.science/pith/J7IYASYI2EODHVMKWZGFEFDDYO.json","view_paper":"https://pith.science/paper/J7IYASYI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.18511&json=true","fetch_graph":"https://pith.science/api/pith-number/J7IYASYI2EODHVMKWZGFEFDDYO/graph.json","fetch_events":"https://pith.science/api/pith-number/J7IYASYI2EODHVMKWZGFEFDDYO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J7IYASYI2EODHVMKWZGFEFDDYO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J7IYASYI2EODHVMKWZGFEFDDYO/action/storage_attestation","attest_author":"https://pith.science/pith/J7IYASYI2EODHVMKWZGFEFDDYO/action/author_attestation","sign_citation":"https://pith.science/pith/J7IYASYI2EODHVMKWZGFEFDDYO/action/citation_signature","submit_replication":"https://pith.science/pith/J7IYASYI2EODHVMKWZGFEFDDYO/action/replication_record"}},"created_at":"2026-07-05T11:08:15.687697+00:00","updated_at":"2026-07-05T11:08:15.687697+00:00"}