{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PVUK3DSPRJ2OJFDEUHP7M66Q7Z","short_pith_number":"pith:PVUK3DSP","schema_version":"1.0","canonical_sha256":"7d68ad8e4f8a74e49464a1dff67bd0fe6148735d7eeaaf8c614ab0bfbb8ed047","source":{"kind":"arxiv","id":"2505.20282","version":4},"attestation_state":"computed","paper":{"title":"One-shot Entropy Minimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bryan Dai, Haoming Luo, Joey Zhou, Lynx Chen, Zitian Gao","submitted_at":"2025-05-26T17:58:30Z","abstract_excerpt":"We trained 13,440 large language models and found that entropy minimization requires only a single unlabeled data and 10 steps optimization to achieve performance improvements comparable to or even greater than those obtained using thousands of data and carefully designed rewards in rule-based reinforcement learning. This striking result may prompt a rethinking of post-training paradigms for large language models. Our code is avaliable at https://github.com/zitian-gao/one-shot-em."},"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":"2505.20282","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T17:58:30Z","cross_cats_sorted":[],"title_canon_sha256":"87abec6c8c68c0c6bfdfab6686e16eb55fdd7d6c4e3732b600cd554e9d76507d","abstract_canon_sha256":"a1ce249dce302dab7bf1bcb1e1b6ddf8275887d06920b6247be62c57a76b4b62"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:57.529339Z","signature_b64":"4aFgVuphaNcPcGo202j+ILac++08ZW54Znx4nkZ8QzfwQDJuqySuuWVLIFwuwjSUwn37c+HKee9VxBxvLl8hCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d68ad8e4f8a74e49464a1dff67bd0fe6148735d7eeaaf8c614ab0bfbb8ed047","last_reissued_at":"2026-07-05T11:56:57.528631Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:57.528631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One-shot Entropy Minimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bryan Dai, Haoming Luo, Joey Zhou, Lynx Chen, Zitian Gao","submitted_at":"2025-05-26T17:58:30Z","abstract_excerpt":"We trained 13,440 large language models and found that entropy minimization requires only a single unlabeled data and 10 steps optimization to achieve performance improvements comparable to or even greater than those obtained using thousands of data and carefully designed rewards in rule-based reinforcement learning. This striking result may prompt a rethinking of post-training paradigms for large language models. Our code is avaliable at https://github.com/zitian-gao/one-shot-em."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20282","kind":"arxiv","version":4},"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/2505.20282/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":"2505.20282","created_at":"2026-07-05T11:56:57.528708+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20282v4","created_at":"2026-07-05T11:56:57.528708+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20282","created_at":"2026-07-05T11:56:57.528708+00:00"},{"alias_kind":"pith_short_12","alias_value":"PVUK3DSPRJ2O","created_at":"2026-07-05T11:56:57.528708+00:00"},{"alias_kind":"pith_short_16","alias_value":"PVUK3DSPRJ2OJFDE","created_at":"2026-07-05T11:56:57.528708+00:00"},{"alias_kind":"pith_short_8","alias_value":"PVUK3DSP","created_at":"2026-07-05T11:56:57.528708+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22570","citing_title":"What are Key Factors for Updates in RL for LLM Reasoning?","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01249","citing_title":"Trust Region On-Policy Distillation","ref_index":240,"is_internal_anchor":false},{"citing_arxiv_id":"2509.14234","citing_title":"Compute as Teacher: Turning Inference Compute Into Reference-Free Supervision","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08186","citing_title":"Rethinking Entropy Minimization in Test-Time Adaptation for Autoregressive Models","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19295","citing_title":"TEMPO: Scaling Test-time Training for Large Reasoning Models","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12736","citing_title":"Token-Level Policy Optimization: Linking Group-Level Rewards to Token-Level Aggregation via Sequence-Level Likelihood","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07244","citing_title":"Experience Sharing in Mutual Reinforcement Learning for Heterogeneous Language Models","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18003","citing_title":"SELF-EMO: Emotional Self-Evolution from Recognition to Consistent Expression","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17928","citing_title":"HEALing Entropy Collapse: Enhancing Exploration in Few-Shot RLVR via Hybrid-Domain Entropy Dynamics Alignment","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PVUK3DSPRJ2OJFDEUHP7M66Q7Z","json":"https://pith.science/pith/PVUK3DSPRJ2OJFDEUHP7M66Q7Z.json","graph_json":"https://pith.science/api/pith-number/PVUK3DSPRJ2OJFDEUHP7M66Q7Z/graph.json","events_json":"https://pith.science/api/pith-number/PVUK3DSPRJ2OJFDEUHP7M66Q7Z/events.json","paper":"https://pith.science/paper/PVUK3DSP"},"agent_actions":{"view_html":"https://pith.science/pith/PVUK3DSPRJ2OJFDEUHP7M66Q7Z","download_json":"https://pith.science/pith/PVUK3DSPRJ2OJFDEUHP7M66Q7Z.json","view_paper":"https://pith.science/paper/PVUK3DSP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20282&json=true","fetch_graph":"https://pith.science/api/pith-number/PVUK3DSPRJ2OJFDEUHP7M66Q7Z/graph.json","fetch_events":"https://pith.science/api/pith-number/PVUK3DSPRJ2OJFDEUHP7M66Q7Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PVUK3DSPRJ2OJFDEUHP7M66Q7Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PVUK3DSPRJ2OJFDEUHP7M66Q7Z/action/storage_attestation","attest_author":"https://pith.science/pith/PVUK3DSPRJ2OJFDEUHP7M66Q7Z/action/author_attestation","sign_citation":"https://pith.science/pith/PVUK3DSPRJ2OJFDEUHP7M66Q7Z/action/citation_signature","submit_replication":"https://pith.science/pith/PVUK3DSPRJ2OJFDEUHP7M66Q7Z/action/replication_record"}},"created_at":"2026-07-05T11:56:57.528708+00:00","updated_at":"2026-07-05T11:56:57.528708+00:00"}