{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RWEF4AWN4Q2M5IR4JBBI32UDHL","short_pith_number":"pith:RWEF4AWN","schema_version":"1.0","canonical_sha256":"8d885e02cde434cea23c48428dea833ace054df0e1154e7261b114c5c2745810","source":{"kind":"arxiv","id":"2502.18553","version":3},"attestation_state":"computed","paper":{"title":"Applications of Statistical Field Theory in Deep Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.dis-nn","cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Edo Mor, Inbar Seroussi, Moritz Helias, Noa Rubin, Zohar Ringel","submitted_at":"2025-02-25T18:19:06Z","abstract_excerpt":"Deep learning algorithms have made incredible strides in the past decade, yet due to their complexity, the science of deep learning remains in its early stages. Being an experimentally driven field, it is natural to seek a theory of deep learning within the physics paradigm. As deep learning is largely about learning functions and distributions over functions, statistical field theory, a rich and versatile toolbox for tackling complex distributions over functions (fields) is an obvious choice of formalism. Research efforts carried out in the past few years have demonstrated the ability of fiel"},"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":"2502.18553","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-02-25T18:19:06Z","cross_cats_sorted":["cond-mat.dis-nn","cs.AI","cs.LG"],"title_canon_sha256":"9d5f2babb6a67822ce3dc9f3f0b5348aab8f11ce586e0f96ded3d2f0a3184521","abstract_canon_sha256":"eee1d864f0227bc06f7eac974510c0709dc4b2c997c9598d87e4c73b07f62700"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:11.994458Z","signature_b64":"5a/sI6XiOFSts7gNCL5S97wzfxJuh9z+K5Gdum6Vleu+k7suMnYJK/TurMMZ9FdjNJ3Z+A0kimRNjZ0JUGfZCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d885e02cde434cea23c48428dea833ace054df0e1154e7261b114c5c2745810","last_reissued_at":"2026-07-05T10:50:11.993956Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:11.993956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Applications of Statistical Field Theory in Deep Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.dis-nn","cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Edo Mor, Inbar Seroussi, Moritz Helias, Noa Rubin, Zohar Ringel","submitted_at":"2025-02-25T18:19:06Z","abstract_excerpt":"Deep learning algorithms have made incredible strides in the past decade, yet due to their complexity, the science of deep learning remains in its early stages. Being an experimentally driven field, it is natural to seek a theory of deep learning within the physics paradigm. As deep learning is largely about learning functions and distributions over functions, statistical field theory, a rich and versatile toolbox for tackling complex distributions over functions (fields) is an obvious choice of formalism. Research efforts carried out in the past few years have demonstrated the ability of fiel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.18553","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/2502.18553/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":"2502.18553","created_at":"2026-07-05T10:50:11.994022+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.18553v3","created_at":"2026-07-05T10:50:11.994022+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.18553","created_at":"2026-07-05T10:50:11.994022+00:00"},{"alias_kind":"pith_short_12","alias_value":"RWEF4AWN4Q2M","created_at":"2026-07-05T10:50:11.994022+00:00"},{"alias_kind":"pith_short_16","alias_value":"RWEF4AWN4Q2M5IR4","created_at":"2026-07-05T10:50:11.994022+00:00"},{"alias_kind":"pith_short_8","alias_value":"RWEF4AWN","created_at":"2026-07-05T10:50:11.994022+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12058","citing_title":"Phase Transitions in Attention: A Bayesian Theory of Copy Head Emergence","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20299","citing_title":"Statistical Properties of Training & Generalization","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04426","citing_title":"Discrete signaling mediates chaotic regularization in recurrent neural networks","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20299","citing_title":"Statistical Properties of Training & Generalization","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05294","citing_title":"Competing nonlinearities, criticality, and order-to-chaos transition in deep networks","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21691","citing_title":"There Will Be a Scientific Theory of Deep Learning","ref_index":278,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RWEF4AWN4Q2M5IR4JBBI32UDHL","json":"https://pith.science/pith/RWEF4AWN4Q2M5IR4JBBI32UDHL.json","graph_json":"https://pith.science/api/pith-number/RWEF4AWN4Q2M5IR4JBBI32UDHL/graph.json","events_json":"https://pith.science/api/pith-number/RWEF4AWN4Q2M5IR4JBBI32UDHL/events.json","paper":"https://pith.science/paper/RWEF4AWN"},"agent_actions":{"view_html":"https://pith.science/pith/RWEF4AWN4Q2M5IR4JBBI32UDHL","download_json":"https://pith.science/pith/RWEF4AWN4Q2M5IR4JBBI32UDHL.json","view_paper":"https://pith.science/paper/RWEF4AWN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.18553&json=true","fetch_graph":"https://pith.science/api/pith-number/RWEF4AWN4Q2M5IR4JBBI32UDHL/graph.json","fetch_events":"https://pith.science/api/pith-number/RWEF4AWN4Q2M5IR4JBBI32UDHL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RWEF4AWN4Q2M5IR4JBBI32UDHL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RWEF4AWN4Q2M5IR4JBBI32UDHL/action/storage_attestation","attest_author":"https://pith.science/pith/RWEF4AWN4Q2M5IR4JBBI32UDHL/action/author_attestation","sign_citation":"https://pith.science/pith/RWEF4AWN4Q2M5IR4JBBI32UDHL/action/citation_signature","submit_replication":"https://pith.science/pith/RWEF4AWN4Q2M5IR4JBBI32UDHL/action/replication_record"}},"created_at":"2026-07-05T10:50:11.994022+00:00","updated_at":"2026-07-05T10:50:11.994022+00:00"}