{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ANW3I3YIY5OUNKX5IEPD5LQYE2","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":"ada3234314508a6e4273a6e4001b8c2a6012a98a41e3880f841ce4483ddee932","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-27T06:42:28Z","title_canon_sha256":"71bb72b00f103f0c34ec377b21536da1f768f81b71ddb914fd0d08a5862938c3"},"schema_version":"1.0","source":{"id":"2605.26121","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.26121","created_at":"2026-05-27T00:04:24Z"},{"alias_kind":"arxiv_version","alias_value":"2605.26121v1","created_at":"2026-05-27T00:04:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26121","created_at":"2026-05-27T00:04:24Z"},{"alias_kind":"pith_short_12","alias_value":"ANW3I3YIY5OU","created_at":"2026-05-27T00:04:24Z"},{"alias_kind":"pith_short_16","alias_value":"ANW3I3YIY5OUNKX5","created_at":"2026-05-27T00:04:24Z"},{"alias_kind":"pith_short_8","alias_value":"ANW3I3YI","created_at":"2026-05-27T00:04:24Z"}],"graph_snapshots":[{"event_id":"sha256:497cfe6da874659197cb95d76254ddc06832dd336c9fa21fbbb3196e49ffbe2b","target":"graph","created_at":"2026-05-27T00:04:24Z","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/2605.26121/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLM pre-training efficacy increasingly depends on data composition rather than sheer volume. Yet, optimal mixing is hindered by categorization flaws: human taxonomies suffer from ontological misalignment, and Euclidean clustering fails to address embedding anisotropy. We introduce GEM (Geometric Entropy Mixing), a framework reformulating data curation as a variational problem on the hypersphere augmented with a mixing-balance regularizer. By decoupling the generative prior and optimizing the objective via a provable MM (Minorize-Maximize) algorithm, GEM effectively counteracts the cluster coll","authors_text":"Ruining Chen, Yue Min, Yujun Li, Ziyun Qiao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-27T06:42:28Z","title":"GEM: Geometric Entropy Mixing for Optimal LLM Data Curation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26121","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:da128120828b2a9ca800ad4944894a2b547a502cb04ba7ae4785e15e8a41990d","target":"record","created_at":"2026-05-27T00:04:24Z","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":"ada3234314508a6e4273a6e4001b8c2a6012a98a41e3880f841ce4483ddee932","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-27T06:42:28Z","title_canon_sha256":"71bb72b00f103f0c34ec377b21536da1f768f81b71ddb914fd0d08a5862938c3"},"schema_version":"1.0","source":{"id":"2605.26121","kind":"arxiv","version":1}},"canonical_sha256":"036db46f08c75d46aafd411e3eae1826a88d1e1baa959eea4b556ba45930762b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"036db46f08c75d46aafd411e3eae1826a88d1e1baa959eea4b556ba45930762b","first_computed_at":"2026-05-27T00:04:24.846809Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T00:04:24.846809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QFy4cS0+/nsDPNZFR3txif91RNN7x1wnWL4rDOQBCknmV76Y0R6FXcZQLOr2nqVPOi701JtjEXRNlsyaUY20Dw==","signature_status":"signed_v1","signed_at":"2026-05-27T00:04:24.847689Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.26121","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da128120828b2a9ca800ad4944894a2b547a502cb04ba7ae4785e15e8a41990d","sha256:497cfe6da874659197cb95d76254ddc06832dd336c9fa21fbbb3196e49ffbe2b"],"state_sha256":"7545e4bac70d0b219b47005f10f529abbdd186c75b0d20b9ba7501a689a6a3e1"}