{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FWUQPLDDNI5LTLC5XKC7JD6XJZ","short_pith_number":"pith:FWUQPLDD","schema_version":"1.0","canonical_sha256":"2da907ac636a3ab9ac5dba85f48fd74e405a03b01bfe85c0b7fc9b12739a1131","source":{"kind":"arxiv","id":"2607.27273","version":1},"attestation_state":"computed","paper":{"title":"SDO: Structure-Aware Data Organization for Efficient LLM Post-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Baili Xiao, Hai Wang, Jinliang Gao, Ning Yang, Pin Lyu","submitted_at":"2026-07-29T12:17:18Z","abstract_excerpt":"Post-training of large language models is expensive, and existing efficiency improvements mainly focus on selecting informative samples or designing training schedules. However, data organization itself is usually treated as a static preprocessing step: embedding-based grouping methods construct fixed partitions before training and cannot adapt to the evolving sample exposure during optimization. As a result, all samples receive similar exposure despite their different optimization needs, leading to redundant updates for some samples while leaving others under-optimized. To address this proble"},"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":"2607.27273","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-29T12:17:18Z","cross_cats_sorted":[],"title_canon_sha256":"5caa0984e8975daa2b50ba9ca19e00d448b4a6f8dae78ef7f8111e24bdf8d724","abstract_canon_sha256":"d3792b48ea57fd11f335cd29d6be5685dca53a93c461ec80221ffc3eae854d0f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2da907ac636a3ab9ac5dba85f48fd74e405a03b01bfe85c0b7fc9b12739a1131","last_reissued_at":"2026-07-31T00:10:28.500725Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T00:10:28.500725Z"},"graph_snapshot":{"paper":{"title":"SDO: Structure-Aware Data Organization for Efficient LLM Post-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Baili Xiao, Hai Wang, Jinliang Gao, Ning Yang, Pin Lyu","submitted_at":"2026-07-29T12:17:18Z","abstract_excerpt":"Post-training of large language models is expensive, and existing efficiency improvements mainly focus on selecting informative samples or designing training schedules. However, data organization itself is usually treated as a static preprocessing step: embedding-based grouping methods construct fixed partitions before training and cannot adapt to the evolving sample exposure during optimization. As a result, all samples receive similar exposure despite their different optimization needs, leading to redundant updates for some samples while leaving others under-optimized. To address this proble"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27273","kind":"arxiv","version":1},"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/2607.27273/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":"2607.27273","created_at":"2026-07-31T00:10:28.503091+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.27273v1","created_at":"2026-07-31T00:10:28.503091+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27273","created_at":"2026-07-31T00:10:28.503091+00:00"},{"alias_kind":"pith_short_12","alias_value":"FWUQPLDDNI5L","created_at":"2026-07-31T00:10:28.503091+00:00"},{"alias_kind":"pith_short_16","alias_value":"FWUQPLDDNI5LTLC5","created_at":"2026-07-31T00:10:28.503091+00:00"},{"alias_kind":"pith_short_8","alias_value":"FWUQPLDD","created_at":"2026-07-31T00:10:28.503091+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/FWUQPLDDNI5LTLC5XKC7JD6XJZ","json":"https://pith.science/pith/FWUQPLDDNI5LTLC5XKC7JD6XJZ.json","graph_json":"https://pith.science/api/pith-number/FWUQPLDDNI5LTLC5XKC7JD6XJZ/graph.json","events_json":"https://pith.science/api/pith-number/FWUQPLDDNI5LTLC5XKC7JD6XJZ/events.json","paper":"https://pith.science/paper/FWUQPLDD"},"agent_actions":{"view_html":"https://pith.science/pith/FWUQPLDDNI5LTLC5XKC7JD6XJZ","download_json":"https://pith.science/pith/FWUQPLDDNI5LTLC5XKC7JD6XJZ.json","view_paper":"https://pith.science/paper/FWUQPLDD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.27273&json=true","fetch_graph":"https://pith.science/api/pith-number/FWUQPLDDNI5LTLC5XKC7JD6XJZ/graph.json","fetch_events":"https://pith.science/api/pith-number/FWUQPLDDNI5LTLC5XKC7JD6XJZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FWUQPLDDNI5LTLC5XKC7JD6XJZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FWUQPLDDNI5LTLC5XKC7JD6XJZ/action/storage_attestation","attest_author":"https://pith.science/pith/FWUQPLDDNI5LTLC5XKC7JD6XJZ/action/author_attestation","sign_citation":"https://pith.science/pith/FWUQPLDDNI5LTLC5XKC7JD6XJZ/action/citation_signature","submit_replication":"https://pith.science/pith/FWUQPLDDNI5LTLC5XKC7JD6XJZ/action/replication_record"}},"created_at":"2026-07-31T00:10:28.503091+00:00","updated_at":"2026-07-31T00:10:28.503091+00:00"}