{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:B7D5GI6OEXSGHXGTLI23YLWXHB","short_pith_number":"pith:B7D5GI6O","schema_version":"1.0","canonical_sha256":"0fc7d323ce25e463dcd35a35bc2ed7385348f1007bb4f00c87e96c32000173c0","source":{"kind":"arxiv","id":"2605.29829","version":1},"attestation_state":"computed","paper":{"title":"OptSkills: Learning Generalizable Optimization Skills from Problem Archetypes via Cluster-Based Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Haochen Yang, Hong Qian, Ke Zhao, Mengyuan Ma, Xiangfeng Wang, Xingyu Lu","submitted_at":"2026-05-28T12:07:28Z","abstract_excerpt":"Leveraging Large Language Models (LLMs) to automatically formulate and solve optimization problems from natural language has emerged as an efficient paradigm for automated optimization. However, existing methods still exhibit limited generalization: they are sensitive to superficial narrative variations, reuse experience mainly at the case level, and struggle to adapt to shifted or emerging problem types. We propose OptSkills, an archetype-centric skill learning and reasoning agent system for optimization modeling and solving. To improve robust generalization, our system clusters problems by t"},"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":"2605.29829","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T12:07:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0ff6ddfdc1a97676e0a41c639aaa4f2abeeaf79ecd8bf0cb08e901179ce48f81","abstract_canon_sha256":"9626bf55297b7dc92aa2517d108e0e08742418dea9b24c6bc56677f083b1e12e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:05:55.041486Z","signature_b64":"dANSqho03P/V+ddOVPiy2VDAMiQqz++g6wxbCNLjz8a+RIseVuDANeL42L0Olvcz9qV0Zr5MpERVyydas4IuAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0fc7d323ce25e463dcd35a35bc2ed7385348f1007bb4f00c87e96c32000173c0","last_reissued_at":"2026-05-29T02:05:55.040831Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:05:55.040831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OptSkills: Learning Generalizable Optimization Skills from Problem Archetypes via Cluster-Based Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Haochen Yang, Hong Qian, Ke Zhao, Mengyuan Ma, Xiangfeng Wang, Xingyu Lu","submitted_at":"2026-05-28T12:07:28Z","abstract_excerpt":"Leveraging Large Language Models (LLMs) to automatically formulate and solve optimization problems from natural language has emerged as an efficient paradigm for automated optimization. However, existing methods still exhibit limited generalization: they are sensitive to superficial narrative variations, reuse experience mainly at the case level, and struggle to adapt to shifted or emerging problem types. We propose OptSkills, an archetype-centric skill learning and reasoning agent system for optimization modeling and solving. To improve robust generalization, our system clusters problems by t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29829","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/2605.29829/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":"2605.29829","created_at":"2026-05-29T02:05:55.040942+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29829v1","created_at":"2026-05-29T02:05:55.040942+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29829","created_at":"2026-05-29T02:05:55.040942+00:00"},{"alias_kind":"pith_short_12","alias_value":"B7D5GI6OEXSG","created_at":"2026-05-29T02:05:55.040942+00:00"},{"alias_kind":"pith_short_16","alias_value":"B7D5GI6OEXSGHXGT","created_at":"2026-05-29T02:05:55.040942+00:00"},{"alias_kind":"pith_short_8","alias_value":"B7D5GI6O","created_at":"2026-05-29T02:05:55.040942+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/B7D5GI6OEXSGHXGTLI23YLWXHB","json":"https://pith.science/pith/B7D5GI6OEXSGHXGTLI23YLWXHB.json","graph_json":"https://pith.science/api/pith-number/B7D5GI6OEXSGHXGTLI23YLWXHB/graph.json","events_json":"https://pith.science/api/pith-number/B7D5GI6OEXSGHXGTLI23YLWXHB/events.json","paper":"https://pith.science/paper/B7D5GI6O"},"agent_actions":{"view_html":"https://pith.science/pith/B7D5GI6OEXSGHXGTLI23YLWXHB","download_json":"https://pith.science/pith/B7D5GI6OEXSGHXGTLI23YLWXHB.json","view_paper":"https://pith.science/paper/B7D5GI6O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29829&json=true","fetch_graph":"https://pith.science/api/pith-number/B7D5GI6OEXSGHXGTLI23YLWXHB/graph.json","fetch_events":"https://pith.science/api/pith-number/B7D5GI6OEXSGHXGTLI23YLWXHB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B7D5GI6OEXSGHXGTLI23YLWXHB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B7D5GI6OEXSGHXGTLI23YLWXHB/action/storage_attestation","attest_author":"https://pith.science/pith/B7D5GI6OEXSGHXGTLI23YLWXHB/action/author_attestation","sign_citation":"https://pith.science/pith/B7D5GI6OEXSGHXGTLI23YLWXHB/action/citation_signature","submit_replication":"https://pith.science/pith/B7D5GI6OEXSGHXGTLI23YLWXHB/action/replication_record"}},"created_at":"2026-05-29T02:05:55.040942+00:00","updated_at":"2026-05-29T02:05:55.040942+00:00"}