{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:R3JP2PWNBJIU3YDNBHT7CD2PQZ","short_pith_number":"pith:R3JP2PWN","schema_version":"1.0","canonical_sha256":"8ed2fd3ecd0a514de06d09e7f10f4f86487f56003124f26f8edd8609d35ffb78","source":{"kind":"arxiv","id":"1912.02178","version":1},"attestation_state":"computed","paper":{"title":"Fantastic Generalization Measures and Where to Find Them","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Behnam Neyshabur, Dilip Krishnan, Hossein Mobahi, Samy Bengio, Yiding Jiang","submitted_at":"2019-12-04T18:58:26Z","abstract_excerpt":"Generalization of deep networks has been of great interest in recent years, resulting in a number of theoretically and empirically motivated complexity measures. However, most papers proposing such measures study only a small set of models, leaving open the question of whether the conclusion drawn from those experiments would remain valid in other settings. We present the first large scale study of generalization in deep networks. We investigate more then 40 complexity measures taken from both theoretical bounds and empirical studies. We train over 10,000 convolutional networks by systematical"},"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":"1912.02178","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-04T18:58:26Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fd5da7879982581c65ef546f4d4f456ff65a04595b3e3610a3edf41b0f81040c","abstract_canon_sha256":"df4e2631425eb57cc1cdb2ee2329f0ed03bb2923536e827209651e8f21744148"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:23:57.485312Z","signature_b64":"4EL7ubmbr9tDsiHa07FAGshbEVF8vPPnxjkMKp/Gp5E2OxE4zAbthZ7HzGB8RhrfZWHnQLeEqOo9zObOuUZUBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ed2fd3ecd0a514de06d09e7f10f4f86487f56003124f26f8edd8609d35ffb78","last_reissued_at":"2026-07-05T00:23:57.484939Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:23:57.484939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fantastic Generalization Measures and Where to Find Them","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Behnam Neyshabur, Dilip Krishnan, Hossein Mobahi, Samy Bengio, Yiding Jiang","submitted_at":"2019-12-04T18:58:26Z","abstract_excerpt":"Generalization of deep networks has been of great interest in recent years, resulting in a number of theoretically and empirically motivated complexity measures. However, most papers proposing such measures study only a small set of models, leaving open the question of whether the conclusion drawn from those experiments would remain valid in other settings. We present the first large scale study of generalization in deep networks. We investigate more then 40 complexity measures taken from both theoretical bounds and empirical studies. We train over 10,000 convolutional networks by systematical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.02178","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/1912.02178/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":"1912.02178","created_at":"2026-07-05T00:23:57.484996+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.02178v1","created_at":"2026-07-05T00:23:57.484996+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.02178","created_at":"2026-07-05T00:23:57.484996+00:00"},{"alias_kind":"pith_short_12","alias_value":"R3JP2PWNBJIU","created_at":"2026-07-05T00:23:57.484996+00:00"},{"alias_kind":"pith_short_16","alias_value":"R3JP2PWNBJIU3YDN","created_at":"2026-07-05T00:23:57.484996+00:00"},{"alias_kind":"pith_short_8","alias_value":"R3JP2PWN","created_at":"2026-07-05T00:23:57.484996+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":18,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23641","citing_title":"Flatness Preserves Instruction Following in Vision-Language-Action Models","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22873","citing_title":"SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22873","citing_title":"SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24680","citing_title":"Trajectory-Based Difficulty Scoring for Reliable Learning on Tabular Data","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30226","citing_title":"Characterizing Optimizer-Dependent Training Dynamics Through Hessian Eigenvector Displacement and Localization","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29823","citing_title":"Quantifying and Optimizing Simplicity via Polynomial Representations","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15551","citing_title":"Characterizing Learning in Deep Neural Networks using Tractable Algorithmic Complexity Analysis","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17118","citing_title":"Differentiable Optimization Layers for Guaranteed Fairness in Deep Learning","ref_index":108,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18598","citing_title":"Pointwise Generalization in Deep Neural Networks","ref_index":102,"is_internal_anchor":false},{"citing_arxiv_id":"2510.23448","citing_title":"An Information-Theoretic Analysis of OOD Generalization in Meta-Reinforcement Learning","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2010.01412","citing_title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2602.08813","citing_title":"Robust Policy Optimization to Prevent Catastrophic Forgetting","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14297","citing_title":"Policy Optimization in Hybrid Discrete-Continuous Action Spaces via Mixed Gradients","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08870","citing_title":"TopoGeoScore: A Self-Supervised Source-Only Geometric Framework for OOD Checkpoint Selection","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2201.02177","citing_title":"Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01967","citing_title":"MER-DG: Modality-Entropy Regularization for Multimodal Domain Generalization","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07914","citing_title":"Flatness and Gradient Alignment Are Both Necessary: Spectral-Aware Gradient-Aligned Exploration for Multi-Distribution Learning","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19740","citing_title":"Generalization at the Edge of Stability","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R3JP2PWNBJIU3YDNBHT7CD2PQZ","json":"https://pith.science/pith/R3JP2PWNBJIU3YDNBHT7CD2PQZ.json","graph_json":"https://pith.science/api/pith-number/R3JP2PWNBJIU3YDNBHT7CD2PQZ/graph.json","events_json":"https://pith.science/api/pith-number/R3JP2PWNBJIU3YDNBHT7CD2PQZ/events.json","paper":"https://pith.science/paper/R3JP2PWN"},"agent_actions":{"view_html":"https://pith.science/pith/R3JP2PWNBJIU3YDNBHT7CD2PQZ","download_json":"https://pith.science/pith/R3JP2PWNBJIU3YDNBHT7CD2PQZ.json","view_paper":"https://pith.science/paper/R3JP2PWN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.02178&json=true","fetch_graph":"https://pith.science/api/pith-number/R3JP2PWNBJIU3YDNBHT7CD2PQZ/graph.json","fetch_events":"https://pith.science/api/pith-number/R3JP2PWNBJIU3YDNBHT7CD2PQZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R3JP2PWNBJIU3YDNBHT7CD2PQZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R3JP2PWNBJIU3YDNBHT7CD2PQZ/action/storage_attestation","attest_author":"https://pith.science/pith/R3JP2PWNBJIU3YDNBHT7CD2PQZ/action/author_attestation","sign_citation":"https://pith.science/pith/R3JP2PWNBJIU3YDNBHT7CD2PQZ/action/citation_signature","submit_replication":"https://pith.science/pith/R3JP2PWNBJIU3YDNBHT7CD2PQZ/action/replication_record"}},"created_at":"2026-07-05T00:23:57.484996+00:00","updated_at":"2026-07-05T00:23:57.484996+00:00"}