{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OJ4PQGZCIWPR4RR7MBCLT5P5V4","short_pith_number":"pith:OJ4PQGZC","schema_version":"1.0","canonical_sha256":"7278f81b22459f1e463f6044b9f5fdaf0411f29e21e7ef480cd08a4eed8b9af7","source":{"kind":"arxiv","id":"2607.00926","version":1},"attestation_state":"computed","paper":{"title":"Human-Machine Collaboration on Generative Meta-Learning: Model and Algorithm","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Midhun Parakkal Unni, Samuel Kaski","submitted_at":"2026-07-01T13:29:54Z","abstract_excerpt":"Generalizing machine learning models to environments that differ from their training distribution remains a critical hurdle, particularly when data from the target domain is entirely or partially unavailable. We propose Generative Meta-Learning with Human Feedback (GMHF), a novel framework that bridges this domain gap by leveraging expert intuition to guide data synthesis. Grounded in a theoretical analysis of generalization error, we derive bounds demonstrating that aligning the distribution of generated data with human beliefs regarding the target physics significantly mitigates risk. GMHF o"},"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":"2607.00926","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-01T13:29:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e1507426b732ffd42fad2c697327f067446ffbf4fb00f8973ccaef85992a1084","abstract_canon_sha256":"afb551b85f2cf7797ee788d6fc560ac8bc78dcf3b4981a72b19d6ef6acee9524"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:18:23.744957Z","signature_b64":"rv7lQT5KzBdRW8kQuxFJI5dVPXT5mlYrN3jtpwzWNpDHItxOOLS8ALsTbbMjNGnUGTsaPF1NK/jBCZTgdNe4DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7278f81b22459f1e463f6044b9f5fdaf0411f29e21e7ef480cd08a4eed8b9af7","last_reissued_at":"2026-07-02T01:18:23.744571Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:18:23.744571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Human-Machine Collaboration on Generative Meta-Learning: Model and Algorithm","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Midhun Parakkal Unni, Samuel Kaski","submitted_at":"2026-07-01T13:29:54Z","abstract_excerpt":"Generalizing machine learning models to environments that differ from their training distribution remains a critical hurdle, particularly when data from the target domain is entirely or partially unavailable. We propose Generative Meta-Learning with Human Feedback (GMHF), a novel framework that bridges this domain gap by leveraging expert intuition to guide data synthesis. Grounded in a theoretical analysis of generalization error, we derive bounds demonstrating that aligning the distribution of generated data with human beliefs regarding the target physics significantly mitigates risk. GMHF o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00926","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/2607.00926/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":"2607.00926","created_at":"2026-07-02T01:18:23.744634+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.00926v1","created_at":"2026-07-02T01:18:23.744634+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00926","created_at":"2026-07-02T01:18:23.744634+00:00"},{"alias_kind":"pith_short_12","alias_value":"OJ4PQGZCIWPR","created_at":"2026-07-02T01:18:23.744634+00:00"},{"alias_kind":"pith_short_16","alias_value":"OJ4PQGZCIWPR4RR7","created_at":"2026-07-02T01:18:23.744634+00:00"},{"alias_kind":"pith_short_8","alias_value":"OJ4PQGZC","created_at":"2026-07-02T01:18:23.744634+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/OJ4PQGZCIWPR4RR7MBCLT5P5V4","json":"https://pith.science/pith/OJ4PQGZCIWPR4RR7MBCLT5P5V4.json","graph_json":"https://pith.science/api/pith-number/OJ4PQGZCIWPR4RR7MBCLT5P5V4/graph.json","events_json":"https://pith.science/api/pith-number/OJ4PQGZCIWPR4RR7MBCLT5P5V4/events.json","paper":"https://pith.science/paper/OJ4PQGZC"},"agent_actions":{"view_html":"https://pith.science/pith/OJ4PQGZCIWPR4RR7MBCLT5P5V4","download_json":"https://pith.science/pith/OJ4PQGZCIWPR4RR7MBCLT5P5V4.json","view_paper":"https://pith.science/paper/OJ4PQGZC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.00926&json=true","fetch_graph":"https://pith.science/api/pith-number/OJ4PQGZCIWPR4RR7MBCLT5P5V4/graph.json","fetch_events":"https://pith.science/api/pith-number/OJ4PQGZCIWPR4RR7MBCLT5P5V4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OJ4PQGZCIWPR4RR7MBCLT5P5V4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OJ4PQGZCIWPR4RR7MBCLT5P5V4/action/storage_attestation","attest_author":"https://pith.science/pith/OJ4PQGZCIWPR4RR7MBCLT5P5V4/action/author_attestation","sign_citation":"https://pith.science/pith/OJ4PQGZCIWPR4RR7MBCLT5P5V4/action/citation_signature","submit_replication":"https://pith.science/pith/OJ4PQGZCIWPR4RR7MBCLT5P5V4/action/replication_record"}},"created_at":"2026-07-02T01:18:23.744634+00:00","updated_at":"2026-07-02T01:18:23.744634+00:00"}