{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2FZLUUASHLL3EMKY3TKCOJD7ZF","short_pith_number":"pith:2FZLUUAS","schema_version":"1.0","canonical_sha256":"d172ba50123ad7b23158dcd427247fc95e7e61ed6e3cac0eae19b54ad46a7116","source":{"kind":"arxiv","id":"2304.04858","version":1},"attestation_state":"computed","paper":{"title":"Simulated Annealing in Early Layers Leads to Better Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"AmirMohammad Sarfi, Eugene Belilovsky, Mirco Ravanelli, Muawiz Chaudhary, Nasir M. Khalid, Sudhir Mudur, Zahra Karimpour","submitted_at":"2023-04-10T20:41:40Z","abstract_excerpt":"Recently, a number of iterative learning methods have been introduced to improve generalization. These typically rely on training for longer periods of time in exchange for improved generalization. LLF (later-layer-forgetting) is a state-of-the-art method in this category. It strengthens learning in early layers by periodically re-initializing the last few layers of the network. Our principal innovation in this work is to use Simulated annealing in EArly Layers (SEAL) of the network in place of re-initialization of later layers. Essentially, later layers go through the normal gradient descent "},"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":"2304.04858","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-10T20:41:40Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"186dbd1ce3545051270800b97da5d6908cf81dad8b562aca2f8e124e028fb11b","abstract_canon_sha256":"6b74fe0ee3e0992936723633f372115d36d4283a12137da948553dafe3a6fd2a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:59:52.523493Z","signature_b64":"Qfgk7JG3Nft/t5Jgur3hCavixVsdGupmFbLxiXmHMm7zXkZR1ICn+O7ZKCnRx1ES5ONoPI+BoAW9FBPOy306Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d172ba50123ad7b23158dcd427247fc95e7e61ed6e3cac0eae19b54ad46a7116","last_reissued_at":"2026-07-05T05:59:52.523081Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:59:52.523081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simulated Annealing in Early Layers Leads to Better Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"AmirMohammad Sarfi, Eugene Belilovsky, Mirco Ravanelli, Muawiz Chaudhary, Nasir M. Khalid, Sudhir Mudur, Zahra Karimpour","submitted_at":"2023-04-10T20:41:40Z","abstract_excerpt":"Recently, a number of iterative learning methods have been introduced to improve generalization. These typically rely on training for longer periods of time in exchange for improved generalization. LLF (later-layer-forgetting) is a state-of-the-art method in this category. It strengthens learning in early layers by periodically re-initializing the last few layers of the network. Our principal innovation in this work is to use Simulated annealing in EArly Layers (SEAL) of the network in place of re-initialization of later layers. Essentially, later layers go through the normal gradient descent "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.04858","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/2304.04858/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":"2304.04858","created_at":"2026-07-05T05:59:52.523137+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.04858v1","created_at":"2026-07-05T05:59:52.523137+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.04858","created_at":"2026-07-05T05:59:52.523137+00:00"},{"alias_kind":"pith_short_12","alias_value":"2FZLUUASHLL3","created_at":"2026-07-05T05:59:52.523137+00:00"},{"alias_kind":"pith_short_16","alias_value":"2FZLUUASHLL3EMKY","created_at":"2026-07-05T05:59:52.523137+00:00"},{"alias_kind":"pith_short_8","alias_value":"2FZLUUAS","created_at":"2026-07-05T05:59:52.523137+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/2FZLUUASHLL3EMKY3TKCOJD7ZF","json":"https://pith.science/pith/2FZLUUASHLL3EMKY3TKCOJD7ZF.json","graph_json":"https://pith.science/api/pith-number/2FZLUUASHLL3EMKY3TKCOJD7ZF/graph.json","events_json":"https://pith.science/api/pith-number/2FZLUUASHLL3EMKY3TKCOJD7ZF/events.json","paper":"https://pith.science/paper/2FZLUUAS"},"agent_actions":{"view_html":"https://pith.science/pith/2FZLUUASHLL3EMKY3TKCOJD7ZF","download_json":"https://pith.science/pith/2FZLUUASHLL3EMKY3TKCOJD7ZF.json","view_paper":"https://pith.science/paper/2FZLUUAS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.04858&json=true","fetch_graph":"https://pith.science/api/pith-number/2FZLUUASHLL3EMKY3TKCOJD7ZF/graph.json","fetch_events":"https://pith.science/api/pith-number/2FZLUUASHLL3EMKY3TKCOJD7ZF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2FZLUUASHLL3EMKY3TKCOJD7ZF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2FZLUUASHLL3EMKY3TKCOJD7ZF/action/storage_attestation","attest_author":"https://pith.science/pith/2FZLUUASHLL3EMKY3TKCOJD7ZF/action/author_attestation","sign_citation":"https://pith.science/pith/2FZLUUASHLL3EMKY3TKCOJD7ZF/action/citation_signature","submit_replication":"https://pith.science/pith/2FZLUUASHLL3EMKY3TKCOJD7ZF/action/replication_record"}},"created_at":"2026-07-05T05:59:52.523137+00:00","updated_at":"2026-07-05T05:59:52.523137+00:00"}