{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AGQEQQ2VW4YVYB5BFYR7MX7MDS","short_pith_number":"pith:AGQEQQ2V","schema_version":"1.0","canonical_sha256":"01a0484355b7315c07a12e23f65fec1c92e303733238922ba20649bd481646b2","source":{"kind":"arxiv","id":"2602.04548","version":2},"attestation_state":"computed","paper":{"title":"Gradient Flow Through Diagram Expansions: Learning Regimes and Explicit Solutions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dmitry Yarotsky, Eugene Golikov, Yaroslav Gusev","submitted_at":"2026-02-04T13:38:57Z","abstract_excerpt":"We develop a general mathematical framework to analyze scaling regimes and derive explicit analytic solutions for gradient flow (GF) in large learning problems. Our key innovation is a formal power series expansion of the loss evolution, with coefficients encoded by diagrams akin to Feynman diagrams. We show that this expansion has a well-defined large-size limit that can be used to reveal different learning phases and, in some cases, to obtain explicit solutions of the nonlinear GF. We focus on learning Canonical Polyadic (CP) decompositions of high-order tensors, and show that this model has"},"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":"2602.04548","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-04T13:38:57Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0df326fc22736ffc85d441806f2803b8c6d7e39d016740b717563c58e26b20a8","abstract_canon_sha256":"3b128f9182ae37eb32d5c43ddd9255d8ddfaedb7fd1726c4e20b42ede53bb56b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:13:53.962118Z","signature_b64":"ZCsjKfBrVur1QufoDrPys45wxUCkKAaCnIGxve39reGNX4Hkzc2fz3CXBbj+Gwz+b/YkQeqg/ik9gIRzYsL8CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01a0484355b7315c07a12e23f65fec1c92e303733238922ba20649bd481646b2","last_reissued_at":"2026-06-23T03:13:53.961670Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:13:53.961670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gradient Flow Through Diagram Expansions: Learning Regimes and Explicit Solutions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dmitry Yarotsky, Eugene Golikov, Yaroslav Gusev","submitted_at":"2026-02-04T13:38:57Z","abstract_excerpt":"We develop a general mathematical framework to analyze scaling regimes and derive explicit analytic solutions for gradient flow (GF) in large learning problems. Our key innovation is a formal power series expansion of the loss evolution, with coefficients encoded by diagrams akin to Feynman diagrams. We show that this expansion has a well-defined large-size limit that can be used to reveal different learning phases and, in some cases, to obtain explicit solutions of the nonlinear GF. We focus on learning Canonical Polyadic (CP) decompositions of high-order tensors, and show that this model has"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.04548","kind":"arxiv","version":2},"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/2602.04548/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":"2602.04548","created_at":"2026-06-23T03:13:53.961728+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.04548v2","created_at":"2026-06-23T03:13:53.961728+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.04548","created_at":"2026-06-23T03:13:53.961728+00:00"},{"alias_kind":"pith_short_12","alias_value":"AGQEQQ2VW4YV","created_at":"2026-06-23T03:13:53.961728+00:00"},{"alias_kind":"pith_short_16","alias_value":"AGQEQQ2VW4YVYB5B","created_at":"2026-06-23T03:13:53.961728+00:00"},{"alias_kind":"pith_short_8","alias_value":"AGQEQQ2V","created_at":"2026-06-23T03:13:53.961728+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/AGQEQQ2VW4YVYB5BFYR7MX7MDS","json":"https://pith.science/pith/AGQEQQ2VW4YVYB5BFYR7MX7MDS.json","graph_json":"https://pith.science/api/pith-number/AGQEQQ2VW4YVYB5BFYR7MX7MDS/graph.json","events_json":"https://pith.science/api/pith-number/AGQEQQ2VW4YVYB5BFYR7MX7MDS/events.json","paper":"https://pith.science/paper/AGQEQQ2V"},"agent_actions":{"view_html":"https://pith.science/pith/AGQEQQ2VW4YVYB5BFYR7MX7MDS","download_json":"https://pith.science/pith/AGQEQQ2VW4YVYB5BFYR7MX7MDS.json","view_paper":"https://pith.science/paper/AGQEQQ2V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.04548&json=true","fetch_graph":"https://pith.science/api/pith-number/AGQEQQ2VW4YVYB5BFYR7MX7MDS/graph.json","fetch_events":"https://pith.science/api/pith-number/AGQEQQ2VW4YVYB5BFYR7MX7MDS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AGQEQQ2VW4YVYB5BFYR7MX7MDS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AGQEQQ2VW4YVYB5BFYR7MX7MDS/action/storage_attestation","attest_author":"https://pith.science/pith/AGQEQQ2VW4YVYB5BFYR7MX7MDS/action/author_attestation","sign_citation":"https://pith.science/pith/AGQEQQ2VW4YVYB5BFYR7MX7MDS/action/citation_signature","submit_replication":"https://pith.science/pith/AGQEQQ2VW4YVYB5BFYR7MX7MDS/action/replication_record"}},"created_at":"2026-06-23T03:13:53.961728+00:00","updated_at":"2026-06-23T03:13:53.961728+00:00"}