{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XCMOLLDW2SRYYFAJCHR6OLK2MJ","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":"7e068235c356b10362c64499d11a8efbd5cdfa51ebc180291d799c6ac13d8a9a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T15:00:51Z","title_canon_sha256":"89b8e93377fe7a8419c4fd873c8b22300c5e79fba149f79b29dab49992761004"},"schema_version":"1.0","source":{"id":"2505.14464","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.14464","created_at":"2026-07-05T11:07:25Z"},{"alias_kind":"arxiv_version","alias_value":"2505.14464v2","created_at":"2026-07-05T11:07:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14464","created_at":"2026-07-05T11:07:25Z"},{"alias_kind":"pith_short_12","alias_value":"XCMOLLDW2SRY","created_at":"2026-07-05T11:07:25Z"},{"alias_kind":"pith_short_16","alias_value":"XCMOLLDW2SRYYFAJ","created_at":"2026-07-05T11:07:25Z"},{"alias_kind":"pith_short_8","alias_value":"XCMOLLDW","created_at":"2026-07-05T11:07:25Z"}],"graph_snapshots":[{"event_id":"sha256:7bdf0d1a8892822df7b1a691f77f77e92ec40216813328dd525d1697158fb864","target":"graph","created_at":"2026-07-05T11:07:25Z","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/2505.14464/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Distillation has emerged as a practical and effective approach to enhance the reasoning capabilities of open-source language models. In this work, we conduct a large-scale empirical study on reasoning data distillation by collecting verified outputs from three state-of-the-art teacher models-AM-Thinking-v1, Qwen3-235B-A22B, and DeepSeek-R1-on a shared corpus of 1.89 million queries. We construct three parallel datasets and analyze their distributions, revealing that AM-Thinking-v1-distilled data exhibits greater token length diversity and lower perplexity. Student models trained on each datase","authors_text":"Han Zhao, Haotian Wang, Shuaiting Chen, Sitong Zhao, Xiangang Li, Xiaoyu Tian, Yiping Peng, Yunjie Ji","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T15:00:51Z","title":"Not All Correct Answers Are Equal: Why Your Distillation Source Matters"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14464","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:d1d7b4176c77108e04b63abf6627df739bfed0dc52bb842046bb52b1328fb1b5","target":"record","created_at":"2026-07-05T11:07:25Z","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":"7e068235c356b10362c64499d11a8efbd5cdfa51ebc180291d799c6ac13d8a9a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T15:00:51Z","title_canon_sha256":"89b8e93377fe7a8419c4fd873c8b22300c5e79fba149f79b29dab49992761004"},"schema_version":"1.0","source":{"id":"2505.14464","kind":"arxiv","version":2}},"canonical_sha256":"b898e5ac76d4a38c140911e3e72d5a6242e5c1462ac478d3a2005d8ef6381603","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b898e5ac76d4a38c140911e3e72d5a6242e5c1462ac478d3a2005d8ef6381603","first_computed_at":"2026-07-05T11:07:25.302409Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:25.302409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hgW7hHPjQH1yJO+anmGJlGGM6Le3w20M1W62hOus7Qe6As5JWUqSK5ToFakDDlxZeAWUtIMhE1ESKsyNBz0yBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:25.303014Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.14464","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d1d7b4176c77108e04b63abf6627df739bfed0dc52bb842046bb52b1328fb1b5","sha256:7bdf0d1a8892822df7b1a691f77f77e92ec40216813328dd525d1697158fb864"],"state_sha256":"1a78d5c5802532dd6fa14e211946a1116fdb93f2f3cfdc5e1ea516e0ce1267e6"}