{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UJAGU4JMFE4IMYVG6PXL5YDBJK","short_pith_number":"pith:UJAGU4JM","schema_version":"1.0","canonical_sha256":"a2406a712c29388662a6f3eebee0614aaa156b59cf15fae6696d0ec256daf879","source":{"kind":"arxiv","id":"2501.04393","version":1},"attestation_state":"computed","paper":{"title":"SEO: Stochastic Experience Optimization for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Conghui Zhu, Hongyun Zhou, Jin Huang, Jitao Xu, Lei Shen, Yitao Duan","submitted_at":"2025-01-08T10:10:29Z","abstract_excerpt":"Large Language Models (LLMs) can benefit from useful experiences to improve their performance on specific tasks. However, finding helpful experiences for different LLMs is not obvious, since it is unclear what experiences suit specific LLMs. Previous studies intended to automatically find useful experiences using LLMs, while it is difficult to ensure the effectiveness of the obtained experience. In this paper, we propose Stochastic Experience Optimization (SEO), an iterative approach that finds optimized model-specific experience without modifying model parameters through experience update in "},"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":"2501.04393","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-08T10:10:29Z","cross_cats_sorted":[],"title_canon_sha256":"1b1415f1001eea0ed0661b5666e79fd34907f690d1d0ff671ade52b0f89e001a","abstract_canon_sha256":"479c57f55ec43397ca5f7d0b97f21b03796f4d4bad7b6bbbdbd9f160cf9ce070"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:34.458435Z","signature_b64":"RVH+s8soN6Ep9XTS4Y+tmPltJgtCRRwmklPO5sVa7XKChIGGWvejGYFTwSsLjMiwj+zxmYr7BDFeWBxKpTEHBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2406a712c29388662a6f3eebee0614aaa156b59cf15fae6696d0ec256daf879","last_reissued_at":"2026-07-05T09:58:34.457938Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:34.457938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SEO: Stochastic Experience Optimization for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Conghui Zhu, Hongyun Zhou, Jin Huang, Jitao Xu, Lei Shen, Yitao Duan","submitted_at":"2025-01-08T10:10:29Z","abstract_excerpt":"Large Language Models (LLMs) can benefit from useful experiences to improve their performance on specific tasks. However, finding helpful experiences for different LLMs is not obvious, since it is unclear what experiences suit specific LLMs. Previous studies intended to automatically find useful experiences using LLMs, while it is difficult to ensure the effectiveness of the obtained experience. In this paper, we propose Stochastic Experience Optimization (SEO), an iterative approach that finds optimized model-specific experience without modifying model parameters through experience update in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04393","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/2501.04393/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":"2501.04393","created_at":"2026-07-05T09:58:34.458007+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.04393v1","created_at":"2026-07-05T09:58:34.458007+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04393","created_at":"2026-07-05T09:58:34.458007+00:00"},{"alias_kind":"pith_short_12","alias_value":"UJAGU4JMFE4I","created_at":"2026-07-05T09:58:34.458007+00:00"},{"alias_kind":"pith_short_16","alias_value":"UJAGU4JMFE4IMYVG","created_at":"2026-07-05T09:58:34.458007+00:00"},{"alias_kind":"pith_short_8","alias_value":"UJAGU4JM","created_at":"2026-07-05T09:58:34.458007+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/UJAGU4JMFE4IMYVG6PXL5YDBJK","json":"https://pith.science/pith/UJAGU4JMFE4IMYVG6PXL5YDBJK.json","graph_json":"https://pith.science/api/pith-number/UJAGU4JMFE4IMYVG6PXL5YDBJK/graph.json","events_json":"https://pith.science/api/pith-number/UJAGU4JMFE4IMYVG6PXL5YDBJK/events.json","paper":"https://pith.science/paper/UJAGU4JM"},"agent_actions":{"view_html":"https://pith.science/pith/UJAGU4JMFE4IMYVG6PXL5YDBJK","download_json":"https://pith.science/pith/UJAGU4JMFE4IMYVG6PXL5YDBJK.json","view_paper":"https://pith.science/paper/UJAGU4JM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.04393&json=true","fetch_graph":"https://pith.science/api/pith-number/UJAGU4JMFE4IMYVG6PXL5YDBJK/graph.json","fetch_events":"https://pith.science/api/pith-number/UJAGU4JMFE4IMYVG6PXL5YDBJK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UJAGU4JMFE4IMYVG6PXL5YDBJK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UJAGU4JMFE4IMYVG6PXL5YDBJK/action/storage_attestation","attest_author":"https://pith.science/pith/UJAGU4JMFE4IMYVG6PXL5YDBJK/action/author_attestation","sign_citation":"https://pith.science/pith/UJAGU4JMFE4IMYVG6PXL5YDBJK/action/citation_signature","submit_replication":"https://pith.science/pith/UJAGU4JMFE4IMYVG6PXL5YDBJK/action/replication_record"}},"created_at":"2026-07-05T09:58:34.458007+00:00","updated_at":"2026-07-05T09:58:34.458007+00:00"}