{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DUW6GOKNYBJCQJFUYCHOFHSH3H","short_pith_number":"pith:DUW6GOKN","schema_version":"1.0","canonical_sha256":"1d2de3394dc0522824b4c08ee29e47d9ce05ea519448f139ac9be55ac4bc7a76","source":{"kind":"arxiv","id":"2506.06789","version":1},"attestation_state":"computed","paper":{"title":"Liquid and solid layers in a thermal deep learning machine","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cond-mat.dis-nn","authors_text":"Gang Huang, Ge Zhang, Hajime Yoshino, Lai Shun Chan, Yuliang Jin","submitted_at":"2025-06-07T13:11:09Z","abstract_excerpt":"Based on deep neural networks (DNNs), deep learning has been successfully applied to many problems, but its mechanism is still not well understood -- especially the reason why over-parametrized DNNs can generalize. A recent statistical mechanics theory on supervised learning by a prototypical multi-layer perceptron (MLP) on some artificial learning scenarios predicts that adjustable parameters of over-parametrized MLPs become strongly constrained by the training data close to the input/output boundaries, while the parameters in the center remain largely free, giving rise to a solid-liquid-soli"},"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":"2506.06789","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.dis-nn","submitted_at":"2025-06-07T13:11:09Z","cross_cats_sorted":[],"title_canon_sha256":"3a8488bcadb79bcde3c05e9720441d3cba9325e7e4f680e4d96ade11dba40c84","abstract_canon_sha256":"b30b9fc2b5edadaf5ec1693bd7cf599f51fae3d2ad8f0b4f4dc994910a2872ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:55.696637Z","signature_b64":"7Kk+yobxxcuY8CkkKO9pDWi1kt3z9l5dTNvYeS+ezCZbOsY+0fdgJyO6LOQhKLPUc7bHxcVDenSoxadNOPDyBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d2de3394dc0522824b4c08ee29e47d9ce05ea519448f139ac9be55ac4bc7a76","last_reissued_at":"2026-07-05T11:17:55.696192Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:55.696192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Liquid and solid layers in a thermal deep learning machine","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cond-mat.dis-nn","authors_text":"Gang Huang, Ge Zhang, Hajime Yoshino, Lai Shun Chan, Yuliang Jin","submitted_at":"2025-06-07T13:11:09Z","abstract_excerpt":"Based on deep neural networks (DNNs), deep learning has been successfully applied to many problems, but its mechanism is still not well understood -- especially the reason why over-parametrized DNNs can generalize. A recent statistical mechanics theory on supervised learning by a prototypical multi-layer perceptron (MLP) on some artificial learning scenarios predicts that adjustable parameters of over-parametrized MLPs become strongly constrained by the training data close to the input/output boundaries, while the parameters in the center remain largely free, giving rise to a solid-liquid-soli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06789","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/2506.06789/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":"2506.06789","created_at":"2026-07-05T11:17:55.696248+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.06789v1","created_at":"2026-07-05T11:17:55.696248+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06789","created_at":"2026-07-05T11:17:55.696248+00:00"},{"alias_kind":"pith_short_12","alias_value":"DUW6GOKNYBJC","created_at":"2026-07-05T11:17:55.696248+00:00"},{"alias_kind":"pith_short_16","alias_value":"DUW6GOKNYBJCQJFU","created_at":"2026-07-05T11:17:55.696248+00:00"},{"alias_kind":"pith_short_8","alias_value":"DUW6GOKN","created_at":"2026-07-05T11:17:55.696248+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/DUW6GOKNYBJCQJFUYCHOFHSH3H","json":"https://pith.science/pith/DUW6GOKNYBJCQJFUYCHOFHSH3H.json","graph_json":"https://pith.science/api/pith-number/DUW6GOKNYBJCQJFUYCHOFHSH3H/graph.json","events_json":"https://pith.science/api/pith-number/DUW6GOKNYBJCQJFUYCHOFHSH3H/events.json","paper":"https://pith.science/paper/DUW6GOKN"},"agent_actions":{"view_html":"https://pith.science/pith/DUW6GOKNYBJCQJFUYCHOFHSH3H","download_json":"https://pith.science/pith/DUW6GOKNYBJCQJFUYCHOFHSH3H.json","view_paper":"https://pith.science/paper/DUW6GOKN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.06789&json=true","fetch_graph":"https://pith.science/api/pith-number/DUW6GOKNYBJCQJFUYCHOFHSH3H/graph.json","fetch_events":"https://pith.science/api/pith-number/DUW6GOKNYBJCQJFUYCHOFHSH3H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DUW6GOKNYBJCQJFUYCHOFHSH3H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DUW6GOKNYBJCQJFUYCHOFHSH3H/action/storage_attestation","attest_author":"https://pith.science/pith/DUW6GOKNYBJCQJFUYCHOFHSH3H/action/author_attestation","sign_citation":"https://pith.science/pith/DUW6GOKNYBJCQJFUYCHOFHSH3H/action/citation_signature","submit_replication":"https://pith.science/pith/DUW6GOKNYBJCQJFUYCHOFHSH3H/action/replication_record"}},"created_at":"2026-07-05T11:17:55.696248+00:00","updated_at":"2026-07-05T11:17:55.696248+00:00"}