{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PE5RKEQM5YCPMKJK2RUWMW6KOK","short_pith_number":"pith:PE5RKEQM","schema_version":"1.0","canonical_sha256":"793b15120cee04f6292ad469665bca7288830f2cd354aeede581dc9ad1f6d0a4","source":{"kind":"arxiv","id":"2302.07011","version":2},"attestation_state":"computed","paper":{"title":"A Modern Look at the Relationship between Sharpness and Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Francesco Croce, Maksym Andriushchenko, Matthias Hein, Maximilian M\\\"uller, Nicolas Flammarion","submitted_at":"2023-02-14T12:38:12Z","abstract_excerpt":"Sharpness of minima is a promising quantity that can correlate with generalization in deep networks and, when optimized during training, can improve generalization. However, standard sharpness is not invariant under reparametrizations of neural networks, and, to fix this, reparametrization-invariant sharpness definitions have been proposed, most prominently adaptive sharpness (Kwon et al., 2021). But does it really capture generalization in modern practical settings? We comprehensively explore this question in a detailed study of various definitions of adaptive sharpness in settings ranging fr"},"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":"2302.07011","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-14T12:38:12Z","cross_cats_sorted":[],"title_canon_sha256":"a698b97234eac20dd7405bda85e9a813cc6796f99d06be905cd60092c109e174","abstract_canon_sha256":"fa4e1a6a3c5357eb047eed71a4c7b1916965d814b2d365aa4fdc2686ee6ac069"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:18:20.436449Z","signature_b64":"De2EgJjys4B9x+KeCWgaPlZx61IeJl/hy55kDSF70/XJMP/0marJjnRivwYSprr8iR1dOKa+DlqDFopTzWriAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"793b15120cee04f6292ad469665bca7288830f2cd354aeede581dc9ad1f6d0a4","last_reissued_at":"2026-07-05T06:18:20.435993Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:18:20.435993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Modern Look at the Relationship between Sharpness and Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Francesco Croce, Maksym Andriushchenko, Matthias Hein, Maximilian M\\\"uller, Nicolas Flammarion","submitted_at":"2023-02-14T12:38:12Z","abstract_excerpt":"Sharpness of minima is a promising quantity that can correlate with generalization in deep networks and, when optimized during training, can improve generalization. However, standard sharpness is not invariant under reparametrizations of neural networks, and, to fix this, reparametrization-invariant sharpness definitions have been proposed, most prominently adaptive sharpness (Kwon et al., 2021). But does it really capture generalization in modern practical settings? We comprehensively explore this question in a detailed study of various definitions of adaptive sharpness in settings ranging fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.07011","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/2302.07011/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":"2302.07011","created_at":"2026-07-05T06:18:20.436051+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.07011v2","created_at":"2026-07-05T06:18:20.436051+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.07011","created_at":"2026-07-05T06:18:20.436051+00:00"},{"alias_kind":"pith_short_12","alias_value":"PE5RKEQM5YCP","created_at":"2026-07-05T06:18:20.436051+00:00"},{"alias_kind":"pith_short_16","alias_value":"PE5RKEQM5YCPMKJK","created_at":"2026-07-05T06:18:20.436051+00:00"},{"alias_kind":"pith_short_8","alias_value":"PE5RKEQM","created_at":"2026-07-05T06:18:20.436051+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04662","citing_title":"Why Muon Outperforms Adam: A Curvature Perspective","ref_index":123,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04754","citing_title":"Beyond Structural Symmetries: Linear Mode Connectivity via Neuron Identifiability","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13652","citing_title":"Beyond Perplexity: A Geometric and Spectral Study of Low-Rank Pre-Training","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18598","citing_title":"Pointwise Generalization in Deep Neural Networks","ref_index":109,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13652","citing_title":"Beyond Perplexity: A Geometric and Spectral Study of Low-Rank Pre-Training","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08192","citing_title":"Inside-Out: Measuring Generalization in Vision Transformers Through Inner Workings","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PE5RKEQM5YCPMKJK2RUWMW6KOK","json":"https://pith.science/pith/PE5RKEQM5YCPMKJK2RUWMW6KOK.json","graph_json":"https://pith.science/api/pith-number/PE5RKEQM5YCPMKJK2RUWMW6KOK/graph.json","events_json":"https://pith.science/api/pith-number/PE5RKEQM5YCPMKJK2RUWMW6KOK/events.json","paper":"https://pith.science/paper/PE5RKEQM"},"agent_actions":{"view_html":"https://pith.science/pith/PE5RKEQM5YCPMKJK2RUWMW6KOK","download_json":"https://pith.science/pith/PE5RKEQM5YCPMKJK2RUWMW6KOK.json","view_paper":"https://pith.science/paper/PE5RKEQM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.07011&json=true","fetch_graph":"https://pith.science/api/pith-number/PE5RKEQM5YCPMKJK2RUWMW6KOK/graph.json","fetch_events":"https://pith.science/api/pith-number/PE5RKEQM5YCPMKJK2RUWMW6KOK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PE5RKEQM5YCPMKJK2RUWMW6KOK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PE5RKEQM5YCPMKJK2RUWMW6KOK/action/storage_attestation","attest_author":"https://pith.science/pith/PE5RKEQM5YCPMKJK2RUWMW6KOK/action/author_attestation","sign_citation":"https://pith.science/pith/PE5RKEQM5YCPMKJK2RUWMW6KOK/action/citation_signature","submit_replication":"https://pith.science/pith/PE5RKEQM5YCPMKJK2RUWMW6KOK/action/replication_record"}},"created_at":"2026-07-05T06:18:20.436051+00:00","updated_at":"2026-07-05T06:18:20.436051+00:00"}