{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CCDOGMSDKMFMEVMAXMGUEE2QJY","short_pith_number":"pith:CCDOGMSD","schema_version":"1.0","canonical_sha256":"1086e33243530ac25580bb0d4213504e37de3982826e3535b4ce858b16016081","source":{"kind":"arxiv","id":"2508.05496","version":2},"attestation_state":"computed","paper":{"title":"InfiAlign: A Scalable and Sample-Efficient Framework for Aligning LLMs to Enhance Reasoning Capabilities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Congkai Xie, Hongxia Yang, Kejing Yang, Qi Zhou, Shuo Cai, Su Lu, Zhijie Sang","submitted_at":"2025-08-07T15:34:06Z","abstract_excerpt":"Large language models (LLMs) have exhibited impressive reasoning abilities on a wide range of complex tasks. However, enhancing these capabilities through post-training remains resource intensive, particularly in terms of data and computational cost. Although recent efforts have sought to improve sample efficiency through selective data curation, existing methods often rely on heuristic or task-specific strategies that hinder scalability. In this work, we introduce InfiAlign, a scalable and sample-efficient post-training framework that integrates supervised fine-tuning (SFT) with Direct Prefer"},"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":"2508.05496","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-07T15:34:06Z","cross_cats_sorted":[],"title_canon_sha256":"38eec3ede18df751ff7ad2e63f32b1d065542ff1cbe7108af8d42aa85e0b525f","abstract_canon_sha256":"f4eaaf01990c315ebd84e867f1c1fedbf8b5c601652261ee9394523ea8267f9c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:23.554796Z","signature_b64":"+QQWp5+MKolC1PkPBwkqJGBtOExhv7KFbX5QZhnm0wV+21j3hjiznXtoRctw4weZokcToJOFvO2kpENDkGpAAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1086e33243530ac25580bb0d4213504e37de3982826e3535b4ce858b16016081","last_reissued_at":"2026-07-05T11:52:23.554243Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:23.554243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InfiAlign: A Scalable and Sample-Efficient Framework for Aligning LLMs to Enhance Reasoning Capabilities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Congkai Xie, Hongxia Yang, Kejing Yang, Qi Zhou, Shuo Cai, Su Lu, Zhijie Sang","submitted_at":"2025-08-07T15:34:06Z","abstract_excerpt":"Large language models (LLMs) have exhibited impressive reasoning abilities on a wide range of complex tasks. However, enhancing these capabilities through post-training remains resource intensive, particularly in terms of data and computational cost. Although recent efforts have sought to improve sample efficiency through selective data curation, existing methods often rely on heuristic or task-specific strategies that hinder scalability. In this work, we introduce InfiAlign, a scalable and sample-efficient post-training framework that integrates supervised fine-tuning (SFT) with Direct Prefer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.05496","kind":"arxiv","version":2},"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/2508.05496/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":"2508.05496","created_at":"2026-07-05T11:52:23.554309+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.05496v2","created_at":"2026-07-05T11:52:23.554309+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.05496","created_at":"2026-07-05T11:52:23.554309+00:00"},{"alias_kind":"pith_short_12","alias_value":"CCDOGMSDKMFM","created_at":"2026-07-05T11:52:23.554309+00:00"},{"alias_kind":"pith_short_16","alias_value":"CCDOGMSDKMFMEVMA","created_at":"2026-07-05T11:52:23.554309+00:00"},{"alias_kind":"pith_short_8","alias_value":"CCDOGMSD","created_at":"2026-07-05T11:52:23.554309+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/CCDOGMSDKMFMEVMAXMGUEE2QJY","json":"https://pith.science/pith/CCDOGMSDKMFMEVMAXMGUEE2QJY.json","graph_json":"https://pith.science/api/pith-number/CCDOGMSDKMFMEVMAXMGUEE2QJY/graph.json","events_json":"https://pith.science/api/pith-number/CCDOGMSDKMFMEVMAXMGUEE2QJY/events.json","paper":"https://pith.science/paper/CCDOGMSD"},"agent_actions":{"view_html":"https://pith.science/pith/CCDOGMSDKMFMEVMAXMGUEE2QJY","download_json":"https://pith.science/pith/CCDOGMSDKMFMEVMAXMGUEE2QJY.json","view_paper":"https://pith.science/paper/CCDOGMSD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.05496&json=true","fetch_graph":"https://pith.science/api/pith-number/CCDOGMSDKMFMEVMAXMGUEE2QJY/graph.json","fetch_events":"https://pith.science/api/pith-number/CCDOGMSDKMFMEVMAXMGUEE2QJY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CCDOGMSDKMFMEVMAXMGUEE2QJY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CCDOGMSDKMFMEVMAXMGUEE2QJY/action/storage_attestation","attest_author":"https://pith.science/pith/CCDOGMSDKMFMEVMAXMGUEE2QJY/action/author_attestation","sign_citation":"https://pith.science/pith/CCDOGMSDKMFMEVMAXMGUEE2QJY/action/citation_signature","submit_replication":"https://pith.science/pith/CCDOGMSDKMFMEVMAXMGUEE2QJY/action/replication_record"}},"created_at":"2026-07-05T11:52:23.554309+00:00","updated_at":"2026-07-05T11:52:23.554309+00:00"}