{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CNGYA4L55TUN3WEIF7ZXFWUS52","short_pith_number":"pith:CNGYA4L5","schema_version":"1.0","canonical_sha256":"134d80717dece8ddd8882ff372da92ee89540cee7644962c2669d1a941d6ebc7","source":{"kind":"arxiv","id":"2603.06008","version":2},"attestation_state":"computed","paper":{"title":"Dynamical scaling method improved by a deep learning approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A neural network estimates scaling parameters from full dynamical datasets at lower cost than Gaussian process regression.","cross_cats":[],"primary_cat":"cond-mat.stat-mech","authors_text":"Yukiyasu Ozeki, Yusuke Terasawa","submitted_at":"2026-03-06T08:05:46Z","abstract_excerpt":"We propose a dynamical scaling analysis improved by a deep learning approach. While Gaussian process regression has been widely employed for estimating scaling parameters, its computational cost for parameter optimization becomes a limitation in dynamical scaling analysis, where large datasets are involved. In contrast, the present method employs a neural network, which significantly reduces the computational cost and enables the use of the entire dataset that was inaccessible with Gaussian process regression. We applied the method to the 2D Ising model and the 2D 3-state Potts model, achievin"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2603.06008","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.stat-mech","submitted_at":"2026-03-06T08:05:46Z","cross_cats_sorted":[],"title_canon_sha256":"a75b7057952a98121df58fb8155a407026e04b9d68bfb32db4c829fc7980ed94","abstract_canon_sha256":"f8ecac6795d16ce56bbb0ca8f162a1f1feb5ca6ab180700078ec2a77c52527c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:35.794087Z","signature_b64":"XKhTqlUdu52uXV4sR579QFpeeIpUD6maBqCQXjvW7zXzJ5e3aHWP8lxhw/C6hv4bJFDj6wXUb8ZNdVDUVARvCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"134d80717dece8ddd8882ff372da92ee89540cee7644962c2669d1a941d6ebc7","last_reissued_at":"2026-05-20T00:00:35.793350Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:35.793350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamical scaling method improved by a deep learning approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A neural network estimates scaling parameters from full dynamical datasets at lower cost than Gaussian process regression.","cross_cats":[],"primary_cat":"cond-mat.stat-mech","authors_text":"Yukiyasu Ozeki, Yusuke Terasawa","submitted_at":"2026-03-06T08:05:46Z","abstract_excerpt":"We propose a dynamical scaling analysis improved by a deep learning approach. While Gaussian process regression has been widely employed for estimating scaling parameters, its computational cost for parameter optimization becomes a limitation in dynamical scaling analysis, where large datasets are involved. In contrast, the present method employs a neural network, which significantly reduces the computational cost and enables the use of the entire dataset that was inaccessible with Gaussian process regression. We applied the method to the 2D Ising model and the 2D 3-state Potts model, achievin"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The neural network method significantly reduces the computational cost and enables the use of the entire dataset, achieving higher accuracy and computational efficiency than conventional Gaussian process regression approaches for dynamical scaling analysis in the 2D Ising and 3-state Potts models.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That a neural network can be trained to estimate scaling parameters from large dynamical scaling datasets with sufficient accuracy and without introducing systematic biases that would offset the claimed gains in efficiency and precision.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A neural network replaces Gaussian process regression in dynamical scaling analysis, cutting computational cost while improving accuracy on 2D Ising and Potts models.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A neural network estimates scaling parameters from full dynamical datasets at lower cost than Gaussian process regression.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"76c53d67b6889c4f43a3452f3df01865aa37713f6fcd567093afc6c40eddabb4"},"source":{"id":"2603.06008","kind":"arxiv","version":2},"verdict":{"id":"bd3fa88f-5877-4693-8159-bd0a34a6c39f","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T15:38:59.646652Z","strongest_claim":"The neural network method significantly reduces the computational cost and enables the use of the entire dataset, achieving higher accuracy and computational efficiency than conventional Gaussian process regression approaches for dynamical scaling analysis in the 2D Ising and 3-state Potts models.","one_line_summary":"A neural network replaces Gaussian process regression in dynamical scaling analysis, cutting computational cost while improving accuracy on 2D Ising and Potts models.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That a neural network can be trained to estimate scaling parameters from large dynamical scaling datasets with sufficient accuracy and without introducing systematic biases that would offset the claimed gains in efficiency and precision.","pith_extraction_headline":"A neural network estimates scaling parameters from full dynamical datasets at lower cost than Gaussian process regression."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.06008/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":28,"sample":[{"doi":"","year":null,"title":"In this approach, we construct the scal- ing function Φ(·), as expressed in Eq","work_id":"d06bbcf2-2a8c-47de-a872-821dfc2b7404","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2000,"title":"In the dynamical scaling analy- sis of second-order transitions, the relaxation timeτ(T) exhibits a characteristic critical behavior, and the data must be transformed accordingly","work_id":"3a8005b7-b2d5-4da4-861d-b148abab7286","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1988,"title":"Cardy:Finite-size Scaling(Current physics","work_id":"c14f7563-bade-4abf-be06-03a2e3f7e04f","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2007,"title":"Y. Ozeki and N. Ito: J. Phys. A: Math. Theor.40(2007) R149","work_id":"f43cdad0-f076-4482-b65f-ed3b85ae8660","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2014,"title":"Y. Ozeki, S. Yotsuyanagi, T. Sakai, and Y. Echinaka: Phys. Rev. E89(2014) 022122","work_id":"cf71eca1-f553-4929-b6d1-f6c29ebe59ec","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":28,"snapshot_sha256":"573b5184ca874c97e3fba8244d662c8446b52e062030e2fb6d05b012df45cb1f","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"ff0deefe941e9ff265849ddb3a6c0a9bf285055dde4f240fa6ec1b313f213b27"},"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":"2603.06008","created_at":"2026-05-20T00:00:35.793453+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.06008v2","created_at":"2026-05-20T00:00:35.793453+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.06008","created_at":"2026-05-20T00:00:35.793453+00:00"},{"alias_kind":"pith_short_12","alias_value":"CNGYA4L55TUN","created_at":"2026-05-20T00:00:35.793453+00:00"},{"alias_kind":"pith_short_16","alias_value":"CNGYA4L55TUN3WEI","created_at":"2026-05-20T00:00:35.793453+00:00"},{"alias_kind":"pith_short_8","alias_value":"CNGYA4L5","created_at":"2026-05-20T00:00:35.793453+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CNGYA4L55TUN3WEIF7ZXFWUS52","json":"https://pith.science/pith/CNGYA4L55TUN3WEIF7ZXFWUS52.json","graph_json":"https://pith.science/api/pith-number/CNGYA4L55TUN3WEIF7ZXFWUS52/graph.json","events_json":"https://pith.science/api/pith-number/CNGYA4L55TUN3WEIF7ZXFWUS52/events.json","paper":"https://pith.science/paper/CNGYA4L5"},"agent_actions":{"view_html":"https://pith.science/pith/CNGYA4L55TUN3WEIF7ZXFWUS52","download_json":"https://pith.science/pith/CNGYA4L55TUN3WEIF7ZXFWUS52.json","view_paper":"https://pith.science/paper/CNGYA4L5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.06008&json=true","fetch_graph":"https://pith.science/api/pith-number/CNGYA4L55TUN3WEIF7ZXFWUS52/graph.json","fetch_events":"https://pith.science/api/pith-number/CNGYA4L55TUN3WEIF7ZXFWUS52/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CNGYA4L55TUN3WEIF7ZXFWUS52/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CNGYA4L55TUN3WEIF7ZXFWUS52/action/storage_attestation","attest_author":"https://pith.science/pith/CNGYA4L55TUN3WEIF7ZXFWUS52/action/author_attestation","sign_citation":"https://pith.science/pith/CNGYA4L55TUN3WEIF7ZXFWUS52/action/citation_signature","submit_replication":"https://pith.science/pith/CNGYA4L55TUN3WEIF7ZXFWUS52/action/replication_record"}},"created_at":"2026-05-20T00:00:35.793453+00:00","updated_at":"2026-05-20T00:00:35.793453+00:00"}