{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LNNQP7PBT45GX23DNAMD2N4J7M","short_pith_number":"pith:LNNQP7PB","schema_version":"1.0","canonical_sha256":"5b5b07fde19f3a6beb6368183d3789fb195e7fbcf7fd2858aa7f902d31cca770","source":{"kind":"arxiv","id":"2306.14306","version":2},"attestation_state":"computed","paper":{"title":"Adaptive Sharpness-Aware Pruning for Robust Sparse Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Anna Bair, Hongxu Yin, Jose Alvarez, Maying Shen, Pavlo Molchanov","submitted_at":"2023-06-25T18:29:29Z","abstract_excerpt":"Robustness and compactness are two essential attributes of deep learning models that are deployed in the real world. The goals of robustness and compactness may seem to be at odds, since robustness requires generalization across domains, while the process of compression exploits specificity in one domain. We introduce Adaptive Sharpness-Aware Pruning (AdaSAP), which unifies these goals through the lens of network sharpness. The AdaSAP method produces sparse networks that are robust to input variations which are unseen at training time. We achieve this by strategically incorporating weight pert"},"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":"2306.14306","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-25T18:29:29Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"551498d983fa4acecdacc0704ba9dcc67c4bc7f6967eb4178a214d183c429290","abstract_canon_sha256":"df12cc0ffaaa1e9f2f5197fb21a289bf0e812c74acc20c56595b57791d731fe4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:55:22.645820Z","signature_b64":"HWcZwhaLfYrGXTVHa3esgDdgCJAEap4UbzO99Vc+CxISB9FXNmh5Oijo9ZrktoENtoh6CCfmEWeCj9eXpUDlCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b5b07fde19f3a6beb6368183d3789fb195e7fbcf7fd2858aa7f902d31cca770","last_reissued_at":"2026-07-05T07:55:22.645335Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:55:22.645335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Sharpness-Aware Pruning for Robust Sparse Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Anna Bair, Hongxu Yin, Jose Alvarez, Maying Shen, Pavlo Molchanov","submitted_at":"2023-06-25T18:29:29Z","abstract_excerpt":"Robustness and compactness are two essential attributes of deep learning models that are deployed in the real world. The goals of robustness and compactness may seem to be at odds, since robustness requires generalization across domains, while the process of compression exploits specificity in one domain. We introduce Adaptive Sharpness-Aware Pruning (AdaSAP), which unifies these goals through the lens of network sharpness. The AdaSAP method produces sparse networks that are robust to input variations which are unseen at training time. We achieve this by strategically incorporating weight pert"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.14306","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/2306.14306/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":"2306.14306","created_at":"2026-07-05T07:55:22.645394+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.14306v2","created_at":"2026-07-05T07:55:22.645394+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.14306","created_at":"2026-07-05T07:55:22.645394+00:00"},{"alias_kind":"pith_short_12","alias_value":"LNNQP7PBT45G","created_at":"2026-07-05T07:55:22.645394+00:00"},{"alias_kind":"pith_short_16","alias_value":"LNNQP7PBT45GX23D","created_at":"2026-07-05T07:55:22.645394+00:00"},{"alias_kind":"pith_short_8","alias_value":"LNNQP7PB","created_at":"2026-07-05T07:55:22.645394+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/LNNQP7PBT45GX23DNAMD2N4J7M","json":"https://pith.science/pith/LNNQP7PBT45GX23DNAMD2N4J7M.json","graph_json":"https://pith.science/api/pith-number/LNNQP7PBT45GX23DNAMD2N4J7M/graph.json","events_json":"https://pith.science/api/pith-number/LNNQP7PBT45GX23DNAMD2N4J7M/events.json","paper":"https://pith.science/paper/LNNQP7PB"},"agent_actions":{"view_html":"https://pith.science/pith/LNNQP7PBT45GX23DNAMD2N4J7M","download_json":"https://pith.science/pith/LNNQP7PBT45GX23DNAMD2N4J7M.json","view_paper":"https://pith.science/paper/LNNQP7PB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.14306&json=true","fetch_graph":"https://pith.science/api/pith-number/LNNQP7PBT45GX23DNAMD2N4J7M/graph.json","fetch_events":"https://pith.science/api/pith-number/LNNQP7PBT45GX23DNAMD2N4J7M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LNNQP7PBT45GX23DNAMD2N4J7M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LNNQP7PBT45GX23DNAMD2N4J7M/action/storage_attestation","attest_author":"https://pith.science/pith/LNNQP7PBT45GX23DNAMD2N4J7M/action/author_attestation","sign_citation":"https://pith.science/pith/LNNQP7PBT45GX23DNAMD2N4J7M/action/citation_signature","submit_replication":"https://pith.science/pith/LNNQP7PBT45GX23DNAMD2N4J7M/action/replication_record"}},"created_at":"2026-07-05T07:55:22.645394+00:00","updated_at":"2026-07-05T07:55:22.645394+00:00"}