{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KN2YQQKWFF4GMGLQZDBARF2ZHP","short_pith_number":"pith:KN2YQQKW","schema_version":"1.0","canonical_sha256":"53758841562978661970c8c20897593bf72dbba4218ee13d0ca2c108b7649bad","source":{"kind":"arxiv","id":"2508.19733","version":2},"attestation_state":"computed","paper":{"title":"Tune My Adam, Please!","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Frank Hutter, Samuel M\\\"uller, Steven Adriaensen, Theodoros Athanasiadis","submitted_at":"2025-08-27T09:57:45Z","abstract_excerpt":"The Adam optimizer remains one of the most widely used optimizers in deep learning, and effectively tuning its hyperparameters is key to optimizing performance. However, tuning can be tedious and costly. Freeze-thaw Bayesian Optimization (BO) is a recent promising approach for low-budget hyperparameter tuning, but is limited by generic surrogates without prior knowledge of how hyperparameters affect learning. We propose Adam-PFN, a new surrogate model for Freeze-thaw BO of Adam's hyperparameters, pre-trained on learning curves from TaskSet, together with a new learning curve augmentation metho"},"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":"2508.19733","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-27T09:57:45Z","cross_cats_sorted":[],"title_canon_sha256":"c2af710d07342abb7868f96b569eca06379de7ffd18d3065edff7e79ee504dd5","abstract_canon_sha256":"c2dc83dd77e5a3381661c0e262f2a4462e66ec610d0ab28876b2e1d18b020986"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:52.429577Z","signature_b64":"fLSYLQMMA5RjOQG0cblKqsulyqo/GPqBKzVip2VrgNYp7+C5gZT/P/jz4j2cNElqKUEr2Y1sfU6HCiiyNNUyAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53758841562978661970c8c20897593bf72dbba4218ee13d0ca2c108b7649bad","last_reissued_at":"2026-07-05T12:00:52.429041Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:52.429041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tune My Adam, Please!","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Frank Hutter, Samuel M\\\"uller, Steven Adriaensen, Theodoros Athanasiadis","submitted_at":"2025-08-27T09:57:45Z","abstract_excerpt":"The Adam optimizer remains one of the most widely used optimizers in deep learning, and effectively tuning its hyperparameters is key to optimizing performance. However, tuning can be tedious and costly. Freeze-thaw Bayesian Optimization (BO) is a recent promising approach for low-budget hyperparameter tuning, but is limited by generic surrogates without prior knowledge of how hyperparameters affect learning. We propose Adam-PFN, a new surrogate model for Freeze-thaw BO of Adam's hyperparameters, pre-trained on learning curves from TaskSet, together with a new learning curve augmentation metho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.19733","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/2508.19733/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":"2508.19733","created_at":"2026-07-05T12:00:52.429107+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.19733v2","created_at":"2026-07-05T12:00:52.429107+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.19733","created_at":"2026-07-05T12:00:52.429107+00:00"},{"alias_kind":"pith_short_12","alias_value":"KN2YQQKWFF4G","created_at":"2026-07-05T12:00:52.429107+00:00"},{"alias_kind":"pith_short_16","alias_value":"KN2YQQKWFF4GMGLQ","created_at":"2026-07-05T12:00:52.429107+00:00"},{"alias_kind":"pith_short_8","alias_value":"KN2YQQKW","created_at":"2026-07-05T12:00:52.429107+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29158","citing_title":"On the Nonlinearity of Learning Rate Scaling for LLM Training","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KN2YQQKWFF4GMGLQZDBARF2ZHP","json":"https://pith.science/pith/KN2YQQKWFF4GMGLQZDBARF2ZHP.json","graph_json":"https://pith.science/api/pith-number/KN2YQQKWFF4GMGLQZDBARF2ZHP/graph.json","events_json":"https://pith.science/api/pith-number/KN2YQQKWFF4GMGLQZDBARF2ZHP/events.json","paper":"https://pith.science/paper/KN2YQQKW"},"agent_actions":{"view_html":"https://pith.science/pith/KN2YQQKWFF4GMGLQZDBARF2ZHP","download_json":"https://pith.science/pith/KN2YQQKWFF4GMGLQZDBARF2ZHP.json","view_paper":"https://pith.science/paper/KN2YQQKW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.19733&json=true","fetch_graph":"https://pith.science/api/pith-number/KN2YQQKWFF4GMGLQZDBARF2ZHP/graph.json","fetch_events":"https://pith.science/api/pith-number/KN2YQQKWFF4GMGLQZDBARF2ZHP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KN2YQQKWFF4GMGLQZDBARF2ZHP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KN2YQQKWFF4GMGLQZDBARF2ZHP/action/storage_attestation","attest_author":"https://pith.science/pith/KN2YQQKWFF4GMGLQZDBARF2ZHP/action/author_attestation","sign_citation":"https://pith.science/pith/KN2YQQKWFF4GMGLQZDBARF2ZHP/action/citation_signature","submit_replication":"https://pith.science/pith/KN2YQQKWFF4GMGLQZDBARF2ZHP/action/replication_record"}},"created_at":"2026-07-05T12:00:52.429107+00:00","updated_at":"2026-07-05T12:00:52.429107+00:00"}