{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4Y7W7FXJDUXAUSCYZGFNSP3YS3","short_pith_number":"pith:4Y7W7FXJ","schema_version":"1.0","canonical_sha256":"e63f6f96e91d2e0a4858c98ad93f7896d0bd01633defab7eb140391d7222cc5d","source":{"kind":"arxiv","id":"2411.12352","version":1},"attestation_state":"computed","paper":{"title":"Perfecting Imperfect Physical Neural Networks with Transferable Robustness using Sharpness-Aware Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.ET","cs.LG"],"primary_cat":"physics.optics","authors_text":"Benshan Wang, Chaoran Huang, Dongliang Wang, Li Fan, Qiarong Xiao, Shaojie Liu, Tengji Xu, Zeyu Luo","submitted_at":"2024-11-19T09:15:08Z","abstract_excerpt":"AI models are essential in science and engineering, but recent advances are pushing the limits of traditional digital hardware. To address these limitations, physical neural networks (PNNs), which use physical substrates for computation, have gained increasing attention. However, developing effective training methods for PNNs remains a significant challenge. Current approaches, regardless of offline and online training, suffer from significant accuracy loss. Offline training is hindered by imprecise modeling, while online training yields device-specific models that can't be transferred to othe"},"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":"2411.12352","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.optics","submitted_at":"2024-11-19T09:15:08Z","cross_cats_sorted":["cs.ET","cs.LG"],"title_canon_sha256":"87c5e9bb9a3499ece8e45207191af851d9af410edf34b98ea6377a75cfab29bf","abstract_canon_sha256":"cf2b4b958e8d4976d15fd816c3a3a9893409e9058d58ca83b4826beade31333f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:37:20.068500Z","signature_b64":"A5ySpsogwyR5CaP4kwQlCmc4WVsXqpWIGDUeEoXlpwrlDLYY9tEvaLaOsAxvgUo9mnQQYJz+bEGQZIWaLlbPAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e63f6f96e91d2e0a4858c98ad93f7896d0bd01633defab7eb140391d7222cc5d","last_reissued_at":"2026-07-05T09:37:20.068085Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:37:20.068085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Perfecting Imperfect Physical Neural Networks with Transferable Robustness using Sharpness-Aware Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.ET","cs.LG"],"primary_cat":"physics.optics","authors_text":"Benshan Wang, Chaoran Huang, Dongliang Wang, Li Fan, Qiarong Xiao, Shaojie Liu, Tengji Xu, Zeyu Luo","submitted_at":"2024-11-19T09:15:08Z","abstract_excerpt":"AI models are essential in science and engineering, but recent advances are pushing the limits of traditional digital hardware. To address these limitations, physical neural networks (PNNs), which use physical substrates for computation, have gained increasing attention. However, developing effective training methods for PNNs remains a significant challenge. Current approaches, regardless of offline and online training, suffer from significant accuracy loss. Offline training is hindered by imprecise modeling, while online training yields device-specific models that can't be transferred to othe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.12352","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/2411.12352/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":"2411.12352","created_at":"2026-07-05T09:37:20.068137+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.12352v1","created_at":"2026-07-05T09:37:20.068137+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.12352","created_at":"2026-07-05T09:37:20.068137+00:00"},{"alias_kind":"pith_short_12","alias_value":"4Y7W7FXJDUXA","created_at":"2026-07-05T09:37:20.068137+00:00"},{"alias_kind":"pith_short_16","alias_value":"4Y7W7FXJDUXAUSCY","created_at":"2026-07-05T09:37:20.068137+00:00"},{"alias_kind":"pith_short_8","alias_value":"4Y7W7FXJ","created_at":"2026-07-05T09:37:20.068137+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.23866","citing_title":"Towards Understanding The Calibration Benefits of Sharpness-Aware Minimization","ref_index":77,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4Y7W7FXJDUXAUSCYZGFNSP3YS3","json":"https://pith.science/pith/4Y7W7FXJDUXAUSCYZGFNSP3YS3.json","graph_json":"https://pith.science/api/pith-number/4Y7W7FXJDUXAUSCYZGFNSP3YS3/graph.json","events_json":"https://pith.science/api/pith-number/4Y7W7FXJDUXAUSCYZGFNSP3YS3/events.json","paper":"https://pith.science/paper/4Y7W7FXJ"},"agent_actions":{"view_html":"https://pith.science/pith/4Y7W7FXJDUXAUSCYZGFNSP3YS3","download_json":"https://pith.science/pith/4Y7W7FXJDUXAUSCYZGFNSP3YS3.json","view_paper":"https://pith.science/paper/4Y7W7FXJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.12352&json=true","fetch_graph":"https://pith.science/api/pith-number/4Y7W7FXJDUXAUSCYZGFNSP3YS3/graph.json","fetch_events":"https://pith.science/api/pith-number/4Y7W7FXJDUXAUSCYZGFNSP3YS3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4Y7W7FXJDUXAUSCYZGFNSP3YS3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4Y7W7FXJDUXAUSCYZGFNSP3YS3/action/storage_attestation","attest_author":"https://pith.science/pith/4Y7W7FXJDUXAUSCYZGFNSP3YS3/action/author_attestation","sign_citation":"https://pith.science/pith/4Y7W7FXJDUXAUSCYZGFNSP3YS3/action/citation_signature","submit_replication":"https://pith.science/pith/4Y7W7FXJDUXAUSCYZGFNSP3YS3/action/replication_record"}},"created_at":"2026-07-05T09:37:20.068137+00:00","updated_at":"2026-07-05T09:37:20.068137+00:00"}