{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:54CNCODKGEQTGWA4QBDSLL62IW","short_pith_number":"pith:54CNCODK","schema_version":"1.0","canonical_sha256":"ef04d1386a312133581c804725afda45bb375212de545705191b5fa651b67e6c","source":{"kind":"arxiv","id":"2103.02200","version":2},"attestation_state":"computed","paper":{"title":"Formalizing Generalization and Robustness of Neural Networks to Weight Perturbations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chia-Mu Yu, Chia-Yi Hsu, Pin-Yu Chen, Yu-Lin Tsai","submitted_at":"2021-03-03T06:17:03Z","abstract_excerpt":"Studying the sensitivity of weight perturbation in neural networks and its impacts on model performance, including generalization and robustness, is an active research topic due to its implications on a wide range of machine learning tasks such as model compression, generalization gap assessment, and adversarial attacks. In this paper, we provide the first integral study and analysis for feed-forward neural networks in terms of the robustness in pairwise class margin and its generalization behavior under weight perturbation. We further design a new theory-driven loss function for training gene"},"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":"2103.02200","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-03T06:17:03Z","cross_cats_sorted":[],"title_canon_sha256":"9075904c62b5ba27bdf820073d180a0665d1c4500fc8a4c394b1b51a610882e7","abstract_canon_sha256":"d1425c06c0bd99f8bcd6ecb6dba6b765cb9f720eec12478bdd7656632d79fdaf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:41:38.524757Z","signature_b64":"5BQji7XP1AK4I5EzzWBpnE+gQeTWnEhkDqGBbRmHMjTFbZ4InyKSwF2mGoyPuarXxOmuM5z4Ow6PhRJHgY4RAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef04d1386a312133581c804725afda45bb375212de545705191b5fa651b67e6c","last_reissued_at":"2026-07-05T03:41:38.524271Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:41:38.524271Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Formalizing Generalization and Robustness of Neural Networks to Weight Perturbations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chia-Mu Yu, Chia-Yi Hsu, Pin-Yu Chen, Yu-Lin Tsai","submitted_at":"2021-03-03T06:17:03Z","abstract_excerpt":"Studying the sensitivity of weight perturbation in neural networks and its impacts on model performance, including generalization and robustness, is an active research topic due to its implications on a wide range of machine learning tasks such as model compression, generalization gap assessment, and adversarial attacks. In this paper, we provide the first integral study and analysis for feed-forward neural networks in terms of the robustness in pairwise class margin and its generalization behavior under weight perturbation. We further design a new theory-driven loss function for training gene"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.02200","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/2103.02200/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":"2103.02200","created_at":"2026-07-05T03:41:38.524347+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.02200v2","created_at":"2026-07-05T03:41:38.524347+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.02200","created_at":"2026-07-05T03:41:38.524347+00:00"},{"alias_kind":"pith_short_12","alias_value":"54CNCODKGEQT","created_at":"2026-07-05T03:41:38.524347+00:00"},{"alias_kind":"pith_short_16","alias_value":"54CNCODKGEQTGWA4","created_at":"2026-07-05T03:41:38.524347+00:00"},{"alias_kind":"pith_short_8","alias_value":"54CNCODK","created_at":"2026-07-05T03:41:38.524347+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/54CNCODKGEQTGWA4QBDSLL62IW","json":"https://pith.science/pith/54CNCODKGEQTGWA4QBDSLL62IW.json","graph_json":"https://pith.science/api/pith-number/54CNCODKGEQTGWA4QBDSLL62IW/graph.json","events_json":"https://pith.science/api/pith-number/54CNCODKGEQTGWA4QBDSLL62IW/events.json","paper":"https://pith.science/paper/54CNCODK"},"agent_actions":{"view_html":"https://pith.science/pith/54CNCODKGEQTGWA4QBDSLL62IW","download_json":"https://pith.science/pith/54CNCODKGEQTGWA4QBDSLL62IW.json","view_paper":"https://pith.science/paper/54CNCODK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.02200&json=true","fetch_graph":"https://pith.science/api/pith-number/54CNCODKGEQTGWA4QBDSLL62IW/graph.json","fetch_events":"https://pith.science/api/pith-number/54CNCODKGEQTGWA4QBDSLL62IW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/54CNCODKGEQTGWA4QBDSLL62IW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/54CNCODKGEQTGWA4QBDSLL62IW/action/storage_attestation","attest_author":"https://pith.science/pith/54CNCODKGEQTGWA4QBDSLL62IW/action/author_attestation","sign_citation":"https://pith.science/pith/54CNCODKGEQTGWA4QBDSLL62IW/action/citation_signature","submit_replication":"https://pith.science/pith/54CNCODKGEQTGWA4QBDSLL62IW/action/replication_record"}},"created_at":"2026-07-05T03:41:38.524347+00:00","updated_at":"2026-07-05T03:41:38.524347+00:00"}