{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ART6OIEWGYNSIG22Y4NEWUYZSE","short_pith_number":"pith:ART6OIEW","schema_version":"1.0","canonical_sha256":"0467e72096361b241b5ac71a4b5319910ae604f911cba98eecdf09641325e7f4","source":{"kind":"arxiv","id":"2501.12391","version":1},"attestation_state":"computed","paper":{"title":"Physics of Skill Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","physics.data-an","stat.ML"],"primary_cat":"cs.LG","authors_text":"Eric J. Michaud, Jeff Gore, Max Tegmark, Yizhou Liu, Ziming Liu","submitted_at":"2025-01-21T18:59:49Z","abstract_excerpt":"We aim to understand physics of skill learning, i.e., how skills are learned in neural networks during training. We start by observing the Domino effect, i.e., skills are learned sequentially, and notably, some skills kick off learning right after others complete learning, similar to the sequential fall of domino cards. To understand the Domino effect and relevant behaviors of skill learning, we take physicists' approach of abstraction and simplification. We propose three models with varying complexities -- the Geometry model, the Resource model, and the Domino model, trading between reality a"},"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":"2501.12391","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-21T18:59:49Z","cross_cats_sorted":["cs.AI","physics.data-an","stat.ML"],"title_canon_sha256":"2ab716afd52d8cfe1ea2181bdd65c15fb09bb5ef228e46149c28642227db2f20","abstract_canon_sha256":"9d00f87d13668346afe30062bb3419ad937200e0ebf0df93d8ec4adc2500bff8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:03:35.600488Z","signature_b64":"lsb+xITeuTUiO8lO5bHv0W/qhz5qRf5IldGvKMv3HygD4iuWq8EVxbXcvU5Z7CfPeadl0soEwD89oGqycuL+Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0467e72096361b241b5ac71a4b5319910ae604f911cba98eecdf09641325e7f4","last_reissued_at":"2026-07-05T10:03:35.600026Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:03:35.600026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Physics of Skill Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","physics.data-an","stat.ML"],"primary_cat":"cs.LG","authors_text":"Eric J. Michaud, Jeff Gore, Max Tegmark, Yizhou Liu, Ziming Liu","submitted_at":"2025-01-21T18:59:49Z","abstract_excerpt":"We aim to understand physics of skill learning, i.e., how skills are learned in neural networks during training. We start by observing the Domino effect, i.e., skills are learned sequentially, and notably, some skills kick off learning right after others complete learning, similar to the sequential fall of domino cards. To understand the Domino effect and relevant behaviors of skill learning, we take physicists' approach of abstraction and simplification. We propose three models with varying complexities -- the Geometry model, the Resource model, and the Domino model, trading between reality a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12391","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/2501.12391/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":"2501.12391","created_at":"2026-07-05T10:03:35.600086+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.12391v1","created_at":"2026-07-05T10:03:35.600086+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12391","created_at":"2026-07-05T10:03:35.600086+00:00"},{"alias_kind":"pith_short_12","alias_value":"ART6OIEWGYNS","created_at":"2026-07-05T10:03:35.600086+00:00"},{"alias_kind":"pith_short_16","alias_value":"ART6OIEWGYNSIG22","created_at":"2026-07-05T10:03:35.600086+00:00"},{"alias_kind":"pith_short_8","alias_value":"ART6OIEW","created_at":"2026-07-05T10:03:35.600086+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25008","citing_title":"Neural Scaling Universality: If Exponents Are Fixed, Time to Understand Coefficients","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01647","citing_title":"AgenticDataBench: A Comprehensive Benchmark for Data Agents","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22951","citing_title":"The Power of Power Law: Asymmetry Enables Compositional Reasoning","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2505.10465","citing_title":"Superposition Yields Robust Neural Scaling","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ART6OIEWGYNSIG22Y4NEWUYZSE","json":"https://pith.science/pith/ART6OIEWGYNSIG22Y4NEWUYZSE.json","graph_json":"https://pith.science/api/pith-number/ART6OIEWGYNSIG22Y4NEWUYZSE/graph.json","events_json":"https://pith.science/api/pith-number/ART6OIEWGYNSIG22Y4NEWUYZSE/events.json","paper":"https://pith.science/paper/ART6OIEW"},"agent_actions":{"view_html":"https://pith.science/pith/ART6OIEWGYNSIG22Y4NEWUYZSE","download_json":"https://pith.science/pith/ART6OIEWGYNSIG22Y4NEWUYZSE.json","view_paper":"https://pith.science/paper/ART6OIEW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.12391&json=true","fetch_graph":"https://pith.science/api/pith-number/ART6OIEWGYNSIG22Y4NEWUYZSE/graph.json","fetch_events":"https://pith.science/api/pith-number/ART6OIEWGYNSIG22Y4NEWUYZSE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ART6OIEWGYNSIG22Y4NEWUYZSE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ART6OIEWGYNSIG22Y4NEWUYZSE/action/storage_attestation","attest_author":"https://pith.science/pith/ART6OIEWGYNSIG22Y4NEWUYZSE/action/author_attestation","sign_citation":"https://pith.science/pith/ART6OIEWGYNSIG22Y4NEWUYZSE/action/citation_signature","submit_replication":"https://pith.science/pith/ART6OIEWGYNSIG22Y4NEWUYZSE/action/replication_record"}},"created_at":"2026-07-05T10:03:35.600086+00:00","updated_at":"2026-07-05T10:03:35.600086+00:00"}