{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YFK4RKHN5MYNKQXVTIDP2TK7UC","short_pith_number":"pith:YFK4RKHN","schema_version":"1.0","canonical_sha256":"c155c8a8edeb30d542f59a06fd4d5fa0b86bf632de154eec78f861ff8834351d","source":{"kind":"arxiv","id":"2605.22940","version":1},"attestation_state":"computed","paper":{"title":"Human-Centered Learning Mechanics: A Dynamical Framework for Entropy-Regulated Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kim Phuc Tran","submitted_at":"2026-05-21T18:16:39Z","abstract_excerpt":"Deep learning is increasingly viewed as a dynamical process in parameter space, yet many existing theories still treat training as a closed optimization system. This view is limited for real-world AI, where models operate under uncertainty, resource constraints, distribution shift, downstream decision risks, and human feedback. We propose Human-Centered Learning Mechanics (HCLM), a dynamical and information-theoretic framework for open and controlled learning systems. The central idea is that entropy regularization is useful only when the chosen entropy surrogate generates a non-degenerate inf"},"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":"2605.22940","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T18:16:39Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"ce38d74af42164dbbe00cf0185e73ecf8a4db2b88e3efb49ec25896bdd1758d1","abstract_canon_sha256":"0804faea5b2d26e14b26594ea32785a70dd1737f808abcff5e1f5ea6ed67306b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:31.447902Z","signature_b64":"rM89Feg+Rpx7WVn8T3kWvy621ovsKYj/bM2n9lyPfQfpRVdpfjuTYjGlath96NG4Z7puvosZ5PJ5+yjN22YpBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c155c8a8edeb30d542f59a06fd4d5fa0b86bf632de154eec78f861ff8834351d","last_reissued_at":"2026-05-25T02:01:31.447166Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:31.447166Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Human-Centered Learning Mechanics: A Dynamical Framework for Entropy-Regulated Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kim Phuc Tran","submitted_at":"2026-05-21T18:16:39Z","abstract_excerpt":"Deep learning is increasingly viewed as a dynamical process in parameter space, yet many existing theories still treat training as a closed optimization system. This view is limited for real-world AI, where models operate under uncertainty, resource constraints, distribution shift, downstream decision risks, and human feedback. We propose Human-Centered Learning Mechanics (HCLM), a dynamical and information-theoretic framework for open and controlled learning systems. The central idea is that entropy regularization is useful only when the chosen entropy surrogate generates a non-degenerate inf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22940","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/2605.22940/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":"2605.22940","created_at":"2026-05-25T02:01:31.447259+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.22940v1","created_at":"2026-05-25T02:01:31.447259+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22940","created_at":"2026-05-25T02:01:31.447259+00:00"},{"alias_kind":"pith_short_12","alias_value":"YFK4RKHN5MYN","created_at":"2026-05-25T02:01:31.447259+00:00"},{"alias_kind":"pith_short_16","alias_value":"YFK4RKHN5MYNKQXV","created_at":"2026-05-25T02:01:31.447259+00:00"},{"alias_kind":"pith_short_8","alias_value":"YFK4RKHN","created_at":"2026-05-25T02:01:31.447259+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/YFK4RKHN5MYNKQXVTIDP2TK7UC","json":"https://pith.science/pith/YFK4RKHN5MYNKQXVTIDP2TK7UC.json","graph_json":"https://pith.science/api/pith-number/YFK4RKHN5MYNKQXVTIDP2TK7UC/graph.json","events_json":"https://pith.science/api/pith-number/YFK4RKHN5MYNKQXVTIDP2TK7UC/events.json","paper":"https://pith.science/paper/YFK4RKHN"},"agent_actions":{"view_html":"https://pith.science/pith/YFK4RKHN5MYNKQXVTIDP2TK7UC","download_json":"https://pith.science/pith/YFK4RKHN5MYNKQXVTIDP2TK7UC.json","view_paper":"https://pith.science/paper/YFK4RKHN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.22940&json=true","fetch_graph":"https://pith.science/api/pith-number/YFK4RKHN5MYNKQXVTIDP2TK7UC/graph.json","fetch_events":"https://pith.science/api/pith-number/YFK4RKHN5MYNKQXVTIDP2TK7UC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YFK4RKHN5MYNKQXVTIDP2TK7UC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YFK4RKHN5MYNKQXVTIDP2TK7UC/action/storage_attestation","attest_author":"https://pith.science/pith/YFK4RKHN5MYNKQXVTIDP2TK7UC/action/author_attestation","sign_citation":"https://pith.science/pith/YFK4RKHN5MYNKQXVTIDP2TK7UC/action/citation_signature","submit_replication":"https://pith.science/pith/YFK4RKHN5MYNKQXVTIDP2TK7UC/action/replication_record"}},"created_at":"2026-05-25T02:01:31.447259+00:00","updated_at":"2026-05-25T02:01:31.447259+00:00"}