{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BLCB6A2QARV5EM7D3JZHXTRD2U","short_pith_number":"pith:BLCB6A2Q","schema_version":"1.0","canonical_sha256":"0ac41f0350046bd233e3da727bce23d51cf1c1365f81cabbbfe053512c3424d9","source":{"kind":"arxiv","id":"2407.07168","version":1},"attestation_state":"computed","paper":{"title":"Statistical mechanics of transfer learning in fully-connected networks in the proportional limit","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.stat-mech"],"primary_cat":"cond-mat.dis-nn","authors_text":"Alessandro Ingrosso, Federica Gerace, Pietro Rotondo, Rosalba Pacelli","submitted_at":"2024-07-09T18:14:18Z","abstract_excerpt":"Transfer learning (TL) is a well-established machine learning technique to boost the generalization performance on a specific (target) task using information gained from a related (source) task, and it crucially depends on the ability of a network to learn useful features. Leveraging recent analytical progress in the proportional regime of deep learning theory (i.e. the limit where the size of the training set $P$ and the size of the hidden layers $N$ are taken to infinity keeping their ratio $\\alpha = P/N$ finite), in this work we develop a novel single-instance Franz-Parisi formalism that yi"},"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":"2407.07168","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.dis-nn","submitted_at":"2024-07-09T18:14:18Z","cross_cats_sorted":["cond-mat.stat-mech"],"title_canon_sha256":"10f6068f4a874c81dfdbbb86a83344b4bb92189e16d5d6400ee8ab6139ab0c54","abstract_canon_sha256":"e222ddea69a72c89f17ac027b9760a5370bc1f3af1e176208b140bec84386ef1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:07.085865Z","signature_b64":"WrBhxUFP+aEAD7OpT1Pxy3BKJ5N/D0xu0BMcAlWVi/pvRrpHuRg4elX0iKeXFg90DfLBQtzuVPcDFy/uk9U+Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ac41f0350046bd233e3da727bce23d51cf1c1365f81cabbbfe053512c3424d9","last_reissued_at":"2026-07-05T08:42:07.085456Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:07.085456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Statistical mechanics of transfer learning in fully-connected networks in the proportional limit","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.stat-mech"],"primary_cat":"cond-mat.dis-nn","authors_text":"Alessandro Ingrosso, Federica Gerace, Pietro Rotondo, Rosalba Pacelli","submitted_at":"2024-07-09T18:14:18Z","abstract_excerpt":"Transfer learning (TL) is a well-established machine learning technique to boost the generalization performance on a specific (target) task using information gained from a related (source) task, and it crucially depends on the ability of a network to learn useful features. Leveraging recent analytical progress in the proportional regime of deep learning theory (i.e. the limit where the size of the training set $P$ and the size of the hidden layers $N$ are taken to infinity keeping their ratio $\\alpha = P/N$ finite), in this work we develop a novel single-instance Franz-Parisi formalism that yi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07168","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/2407.07168/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":"2407.07168","created_at":"2026-07-05T08:42:07.085514+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.07168v1","created_at":"2026-07-05T08:42:07.085514+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07168","created_at":"2026-07-05T08:42:07.085514+00:00"},{"alias_kind":"pith_short_12","alias_value":"BLCB6A2QARV5","created_at":"2026-07-05T08:42:07.085514+00:00"},{"alias_kind":"pith_short_16","alias_value":"BLCB6A2QARV5EM7D","created_at":"2026-07-05T08:42:07.085514+00:00"},{"alias_kind":"pith_short_8","alias_value":"BLCB6A2Q","created_at":"2026-07-05T08:42:07.085514+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.15911","citing_title":"Kernel shape renormalization explains output-output correlations in finite Bayesian one-hidden-layer networks","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BLCB6A2QARV5EM7D3JZHXTRD2U","json":"https://pith.science/pith/BLCB6A2QARV5EM7D3JZHXTRD2U.json","graph_json":"https://pith.science/api/pith-number/BLCB6A2QARV5EM7D3JZHXTRD2U/graph.json","events_json":"https://pith.science/api/pith-number/BLCB6A2QARV5EM7D3JZHXTRD2U/events.json","paper":"https://pith.science/paper/BLCB6A2Q"},"agent_actions":{"view_html":"https://pith.science/pith/BLCB6A2QARV5EM7D3JZHXTRD2U","download_json":"https://pith.science/pith/BLCB6A2QARV5EM7D3JZHXTRD2U.json","view_paper":"https://pith.science/paper/BLCB6A2Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.07168&json=true","fetch_graph":"https://pith.science/api/pith-number/BLCB6A2QARV5EM7D3JZHXTRD2U/graph.json","fetch_events":"https://pith.science/api/pith-number/BLCB6A2QARV5EM7D3JZHXTRD2U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BLCB6A2QARV5EM7D3JZHXTRD2U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BLCB6A2QARV5EM7D3JZHXTRD2U/action/storage_attestation","attest_author":"https://pith.science/pith/BLCB6A2QARV5EM7D3JZHXTRD2U/action/author_attestation","sign_citation":"https://pith.science/pith/BLCB6A2QARV5EM7D3JZHXTRD2U/action/citation_signature","submit_replication":"https://pith.science/pith/BLCB6A2QARV5EM7D3JZHXTRD2U/action/replication_record"}},"created_at":"2026-07-05T08:42:07.085514+00:00","updated_at":"2026-07-05T08:42:07.085514+00:00"}