{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BVNT5NGGPYUHWGBJTBBIZ4SY2Z","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":"93400ac8a380356bc3f54ce5bd807f559f1adc87f6006aa2b84099d086ed64e9","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T17:59:53Z","title_canon_sha256":"837bdfddf728c638869dadc200c7be58ea6f18b1896d29698fad39a83775458b"},"schema_version":"1.0","source":{"id":"2605.30348","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30348","created_at":"2026-05-29T02:06:17Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30348v1","created_at":"2026-05-29T02:06:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30348","created_at":"2026-05-29T02:06:17Z"},{"alias_kind":"pith_short_12","alias_value":"BVNT5NGGPYUH","created_at":"2026-05-29T02:06:17Z"},{"alias_kind":"pith_short_16","alias_value":"BVNT5NGGPYUHWGBJ","created_at":"2026-05-29T02:06:17Z"},{"alias_kind":"pith_short_8","alias_value":"BVNT5NGG","created_at":"2026-05-29T02:06:17Z"}],"graph_snapshots":[{"event_id":"sha256:da93899c9c1a8a6d1f266b51724bd20d308fdd8846da8d03a11e83f0dc0bd881","target":"graph","created_at":"2026-05-29T02:06:17Z","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/2605.30348/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The pretraining data mixture of Large Language Models (LLMs) constitutes their \"digital DNA\", shaping model behaviors, capabilities, and failure modes. Yet this composition is rarely disclosed, making post-hoc auditing of data combination or provenance difficult. In this work, we formalize $\\textbf{{Data Mixture Surgery (DMS)}}$: given only generated text from a target LLM, estimate the domain-level distribution of its pretraining corpus under a predefined taxonomy. We propose $\\textbf{{LLMSurgeon}}$, a strong framework that casts DMS as an inverse problem under the label-shift assumption. Rat","authors_text":"Jiacheng Cui, Jiacheng Liu, Xiaohan Zhao, Xinyi Shang, Xinyue Bi, Yaxin Luo, Zhaoyi Li, Zhiqiang Shen","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T17:59:53Z","title":"LLMSurgeon: Diagnosing Data Mixture of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30348","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:c843d991e9c1ff04341ce81f97b920af6d75d61d679cbb92386c034a3567d125","target":"record","created_at":"2026-05-29T02:06:17Z","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":"93400ac8a380356bc3f54ce5bd807f559f1adc87f6006aa2b84099d086ed64e9","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T17:59:53Z","title_canon_sha256":"837bdfddf728c638869dadc200c7be58ea6f18b1896d29698fad39a83775458b"},"schema_version":"1.0","source":{"id":"2605.30348","kind":"arxiv","version":1}},"canonical_sha256":"0d5b3eb4c67e287b182998428cf258d673facf83f2c02149f22e193f838b2209","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d5b3eb4c67e287b182998428cf258d673facf83f2c02149f22e193f838b2209","first_computed_at":"2026-05-29T02:06:17.280792Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:06:17.280792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2D1aBe/U5G0tvesY6FQFPO3iyk2yEPA03VIJRS4oiYEX4uA/NysL4qSpKVbglueuuowBDjzRtf67uhr/v6I0Dw==","signature_status":"signed_v1","signed_at":"2026-05-29T02:06:17.281219Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30348","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c843d991e9c1ff04341ce81f97b920af6d75d61d679cbb92386c034a3567d125","sha256:da93899c9c1a8a6d1f266b51724bd20d308fdd8846da8d03a11e83f0dc0bd881"],"state_sha256":"8bc2d38d4f093c2dd8dedb173f1d74103c619dcc853e0217c4cea6dfbb915260"}