{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:J7IYASYI2EODHVMKWZGFEFDDYO","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":"2fe6f6a88d3677a47b8b198230f1d9d36d1547468093ad396b2faa0220db471f","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-30T17:21:44Z","title_canon_sha256":"a2abdc1d00f895d58feaded1c22e4416ae95302eb2b0f50a2f941e314993c704"},"schema_version":"1.0","source":{"id":"2501.18511","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.18511","created_at":"2026-07-05T11:08:15Z"},{"alias_kind":"arxiv_version","alias_value":"2501.18511v2","created_at":"2026-07-05T11:08:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18511","created_at":"2026-07-05T11:08:15Z"},{"alias_kind":"pith_short_12","alias_value":"J7IYASYI2EOD","created_at":"2026-07-05T11:08:15Z"},{"alias_kind":"pith_short_16","alias_value":"J7IYASYI2EODHVMK","created_at":"2026-07-05T11:08:15Z"},{"alias_kind":"pith_short_8","alias_value":"J7IYASYI","created_at":"2026-07-05T11:08:15Z"}],"graph_snapshots":[{"event_id":"sha256:e563809cca097d16bc8dc87dd02cd4c7dbb07fc639d67a4b48a43460e213b8ee","target":"graph","created_at":"2026-07-05T11:08:15Z","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/2501.18511/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Benjamin Feuer, Chinmay Hegde","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-30T17:21:44Z","title":"WILDCHAT-50M: A Deep Dive Into the Role of Synthetic Data in Post-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18511","kind":"arxiv","version":2},"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:d712ed59a275d64ec108dec31939e09f47ad0dd5033433cca7be6b55b9fda1e9","target":"record","created_at":"2026-07-05T11:08:15Z","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":"2fe6f6a88d3677a47b8b198230f1d9d36d1547468093ad396b2faa0220db471f","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-30T17:21:44Z","title_canon_sha256":"a2abdc1d00f895d58feaded1c22e4416ae95302eb2b0f50a2f941e314993c704"},"schema_version":"1.0","source":{"id":"2501.18511","kind":"arxiv","version":2}},"canonical_sha256":"4fd1804b08d11c33d58ab64c521463c3b48271ab415c3888f5e4925d9e02b37f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4fd1804b08d11c33d58ab64c521463c3b48271ab415c3888f5e4925d9e02b37f","first_computed_at":"2026-07-05T11:08:15.687631Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:08:15.687631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9hwJSMMgW3WxAN5/uj4XYopc6R3xkCOoMmcgS7SC1Vc48cDjeVfJ7f2xenLplgRl0IEJYY6gHMMO9aFn9ltsAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:08:15.688118Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.18511","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d712ed59a275d64ec108dec31939e09f47ad0dd5033433cca7be6b55b9fda1e9","sha256:e563809cca097d16bc8dc87dd02cd4c7dbb07fc639d67a4b48a43460e213b8ee"],"state_sha256":"86a04665d507d20c1f4e1e2ba61e0caee1ead9b1b5cc2cd33a3e72a367f78377"}