{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3R3VNOZVED6IOUIF2CALJ73H4O","short_pith_number":"pith:3R3VNOZV","schema_version":"1.0","canonical_sha256":"dc7756bb3520fc875105d080b4ff67e388ee7120ab1aead0318cd20973bb92a2","source":{"kind":"arxiv","id":"2503.02113","version":2},"attestation_state":"computed","paper":{"title":"Deep Learning is Not So Mysterious or Different","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew Gordon Wilson","submitted_at":"2025-03-03T22:56:04Z","abstract_excerpt":"Deep neural networks are often seen as different from other model classes by defying conventional notions of generalization. Popular examples of anomalous generalization behaviour include benign overfitting, double descent, and the success of overparametrization. We argue that these phenomena are not distinct to neural networks, or particularly mysterious. Moreover, this generalization behaviour can be intuitively understood, and rigorously characterized, using long-standing generalization frameworks such as PAC-Bayes and countable hypothesis bounds. We present soft inductive biases as a key u"},"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":"2503.02113","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-03T22:56:04Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ca1fa1ac67a73a1c1115795367774f868be58b58e293ff87b220ce79246e3268","abstract_canon_sha256":"4258961b5da509ad44881369e2cf15ca0770a6e0cb56277907e2186ebfe0d2c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:48.029255Z","signature_b64":"0tFMs3Ec5bm4xVeKmxS5m9tvrl3LN1qEZ+JPKA+kjaPoZ+oRMq9WfRmIw09U5TubW2CbLRoQhiMfPPESNj+CAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc7756bb3520fc875105d080b4ff67e388ee7120ab1aead0318cd20973bb92a2","last_reissued_at":"2026-07-05T11:34:48.028760Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:48.028760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Learning is Not So Mysterious or Different","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew Gordon Wilson","submitted_at":"2025-03-03T22:56:04Z","abstract_excerpt":"Deep neural networks are often seen as different from other model classes by defying conventional notions of generalization. Popular examples of anomalous generalization behaviour include benign overfitting, double descent, and the success of overparametrization. We argue that these phenomena are not distinct to neural networks, or particularly mysterious. Moreover, this generalization behaviour can be intuitively understood, and rigorously characterized, using long-standing generalization frameworks such as PAC-Bayes and countable hypothesis bounds. We present soft inductive biases as a key u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.02113","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/2503.02113/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":"2503.02113","created_at":"2026-07-05T11:34:48.028820+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.02113v2","created_at":"2026-07-05T11:34:48.028820+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.02113","created_at":"2026-07-05T11:34:48.028820+00:00"},{"alias_kind":"pith_short_12","alias_value":"3R3VNOZVED6I","created_at":"2026-07-05T11:34:48.028820+00:00"},{"alias_kind":"pith_short_16","alias_value":"3R3VNOZVED6IOUIF","created_at":"2026-07-05T11:34:48.028820+00:00"},{"alias_kind":"pith_short_8","alias_value":"3R3VNOZV","created_at":"2026-07-05T11:34:48.028820+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06675","citing_title":"Spectral Born machines: classically trainable quantum generative models for discrete data","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2606.20299","citing_title":"Statistical Properties of Training & Generalization","ref_index":161,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19329","citing_title":"The Chandra-Gaia Catalog of Counterparts: Resolving ambiguous Gaia matches to X-ray sources in the Chandra Source Catalog using Machine Learning","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20299","citing_title":"Statistical Properties of Training & Generalization","ref_index":161,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22850","citing_title":"To select or not to select: predictively consistent priors instead of model selection","ref_index":92,"is_internal_anchor":false},{"citing_arxiv_id":"2506.00182","citing_title":"Overfitting has a limitation: a model-independent generalization gap bound based on R\\'enyi entropy","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18598","citing_title":"Pointwise Generalization in Deep Neural Networks","ref_index":171,"is_internal_anchor":false},{"citing_arxiv_id":"2603.24654","citing_title":"Spectral methods: crucial for machine learning, natural for quantum computers?","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05436","citing_title":"Estimating Implicit Regularization in Deep Learning","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17166","citing_title":"The Virtue of Sparsity in Complexity","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3R3VNOZVED6IOUIF2CALJ73H4O","json":"https://pith.science/pith/3R3VNOZVED6IOUIF2CALJ73H4O.json","graph_json":"https://pith.science/api/pith-number/3R3VNOZVED6IOUIF2CALJ73H4O/graph.json","events_json":"https://pith.science/api/pith-number/3R3VNOZVED6IOUIF2CALJ73H4O/events.json","paper":"https://pith.science/paper/3R3VNOZV"},"agent_actions":{"view_html":"https://pith.science/pith/3R3VNOZVED6IOUIF2CALJ73H4O","download_json":"https://pith.science/pith/3R3VNOZVED6IOUIF2CALJ73H4O.json","view_paper":"https://pith.science/paper/3R3VNOZV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.02113&json=true","fetch_graph":"https://pith.science/api/pith-number/3R3VNOZVED6IOUIF2CALJ73H4O/graph.json","fetch_events":"https://pith.science/api/pith-number/3R3VNOZVED6IOUIF2CALJ73H4O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3R3VNOZVED6IOUIF2CALJ73H4O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3R3VNOZVED6IOUIF2CALJ73H4O/action/storage_attestation","attest_author":"https://pith.science/pith/3R3VNOZVED6IOUIF2CALJ73H4O/action/author_attestation","sign_citation":"https://pith.science/pith/3R3VNOZVED6IOUIF2CALJ73H4O/action/citation_signature","submit_replication":"https://pith.science/pith/3R3VNOZVED6IOUIF2CALJ73H4O/action/replication_record"}},"created_at":"2026-07-05T11:34:48.028820+00:00","updated_at":"2026-07-05T11:34:48.028820+00:00"}