{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:NQGPC56TZU2UFP3Z7ZKQPPNN43","short_pith_number":"pith:NQGPC56T","schema_version":"1.0","canonical_sha256":"6c0cf177d3cd3542bf79fe5507bdade6e7c4a43304be232de4eaf46f1183947d","source":{"kind":"arxiv","id":"2006.15416","version":3},"attestation_state":"computed","paper":{"title":"Thermodynamic Machine Learning through Maximum Work Production","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.DS","nlin.AO","stat.ML"],"primary_cat":"cond-mat.stat-mech","authors_text":"A. B. Boyd, J. P. Crutchfield, M. Gu","submitted_at":"2020-06-27T17:57:24Z","abstract_excerpt":"Adaptive systems -- such as a biological organism gaining survival advantage, an autonomous robot executing a functional task, or a motor protein transporting intracellular nutrients -- must model the regularities and stochasticity in their environments to take full advantage of thermodynamic resources. Analogously, but in a purely computational realm, machine learning algorithms estimate models to capture predictable structure and identify irrelevant noise in training data. This happens through optimization of performance metrics, such as model likelihood. If physically implemented, is there "},"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":"2006.15416","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.stat-mech","submitted_at":"2020-06-27T17:57:24Z","cross_cats_sorted":["cs.LG","math.DS","nlin.AO","stat.ML"],"title_canon_sha256":"855c093d69ffd00a3126f0bf5541638dfb36be3dfd576804a70a8275ed875718","abstract_canon_sha256":"9c2a33f276530760627f71007e842b77a1b561137a48b5fb277c8c6d0a6cd79d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:30:58.455468Z","signature_b64":"bk0YoIymVaUAkKvPBZbjlNMfP5scpTAeWgE8xh68ToeghQhzmyhax3PF6Yo68FBHBrDoRg0uuvYZN6NrvmE8BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c0cf177d3cd3542bf79fe5507bdade6e7c4a43304be232de4eaf46f1183947d","last_reissued_at":"2026-07-05T02:30:58.454930Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:30:58.454930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Thermodynamic Machine Learning through Maximum Work Production","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.DS","nlin.AO","stat.ML"],"primary_cat":"cond-mat.stat-mech","authors_text":"A. B. Boyd, J. P. Crutchfield, M. Gu","submitted_at":"2020-06-27T17:57:24Z","abstract_excerpt":"Adaptive systems -- such as a biological organism gaining survival advantage, an autonomous robot executing a functional task, or a motor protein transporting intracellular nutrients -- must model the regularities and stochasticity in their environments to take full advantage of thermodynamic resources. Analogously, but in a purely computational realm, machine learning algorithms estimate models to capture predictable structure and identify irrelevant noise in training data. This happens through optimization of performance metrics, such as model likelihood. If physically implemented, is there "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.15416","kind":"arxiv","version":3},"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/2006.15416/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":"2006.15416","created_at":"2026-07-05T02:30:58.454986+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.15416v3","created_at":"2026-07-05T02:30:58.454986+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.15416","created_at":"2026-07-05T02:30:58.454986+00:00"},{"alias_kind":"pith_short_12","alias_value":"NQGPC56TZU2U","created_at":"2026-07-05T02:30:58.454986+00:00"},{"alias_kind":"pith_short_16","alias_value":"NQGPC56TZU2UFP3Z","created_at":"2026-07-05T02:30:58.454986+00:00"},{"alias_kind":"pith_short_8","alias_value":"NQGPC56T","created_at":"2026-07-05T02:30:58.454986+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/NQGPC56TZU2UFP3Z7ZKQPPNN43","json":"https://pith.science/pith/NQGPC56TZU2UFP3Z7ZKQPPNN43.json","graph_json":"https://pith.science/api/pith-number/NQGPC56TZU2UFP3Z7ZKQPPNN43/graph.json","events_json":"https://pith.science/api/pith-number/NQGPC56TZU2UFP3Z7ZKQPPNN43/events.json","paper":"https://pith.science/paper/NQGPC56T"},"agent_actions":{"view_html":"https://pith.science/pith/NQGPC56TZU2UFP3Z7ZKQPPNN43","download_json":"https://pith.science/pith/NQGPC56TZU2UFP3Z7ZKQPPNN43.json","view_paper":"https://pith.science/paper/NQGPC56T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.15416&json=true","fetch_graph":"https://pith.science/api/pith-number/NQGPC56TZU2UFP3Z7ZKQPPNN43/graph.json","fetch_events":"https://pith.science/api/pith-number/NQGPC56TZU2UFP3Z7ZKQPPNN43/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NQGPC56TZU2UFP3Z7ZKQPPNN43/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NQGPC56TZU2UFP3Z7ZKQPPNN43/action/storage_attestation","attest_author":"https://pith.science/pith/NQGPC56TZU2UFP3Z7ZKQPPNN43/action/author_attestation","sign_citation":"https://pith.science/pith/NQGPC56TZU2UFP3Z7ZKQPPNN43/action/citation_signature","submit_replication":"https://pith.science/pith/NQGPC56TZU2UFP3Z7ZKQPPNN43/action/replication_record"}},"created_at":"2026-07-05T02:30:58.454986+00:00","updated_at":"2026-07-05T02:30:58.454986+00:00"}