{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FIB6NIWI7AHFPXOXFQOZJWNEIO","short_pith_number":"pith:FIB6NIWI","schema_version":"1.0","canonical_sha256":"2a03e6a2c8f80e57ddd72c1d94d9a443bcb1bd670191ccfbe66feed5a7ab15fa","source":{"kind":"arxiv","id":"2605.18598","version":1},"attestation_state":"computed","paper":{"title":"Pointwise Generalization in Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.stat-mech","math.FA","math.PR","math.ST","stat.TH"],"primary_cat":"cs.LG","authors_text":"Shaojie Li, Yunbei Xu","submitted_at":"2026-05-18T16:09:06Z","abstract_excerpt":"We address the fundamental question of why deep neural networks generalize by establishing a pointwise generalization theory for fully connected networks. This framework resolves long-standing barriers to characterizing the rich nonlinear feature-learning regime and builds a new statistical foundation for representation learning. For each trained model, we characterize the hypothesis via a pointwise Riemannian Dimension, derived from the eigenvalues of the learned feature representations across layers. This establishes a principled framework for deriving hypothesis-dependent, representation-aw"},"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":"2605.18598","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T16:09:06Z","cross_cats_sorted":["cond-mat.stat-mech","math.FA","math.PR","math.ST","stat.TH"],"title_canon_sha256":"3fa8f1024a573e031fc307b776bf80fa170d7682a7b2614a31d8f657812ca7eb","abstract_canon_sha256":"319555a63e1f119b9034a9c39eb74946f5f52f43f4bfc46936d59189673705dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:10.098755Z","signature_b64":"bhBWxhl54+vr62uE/1FDrDsczfRwxU5vu1nyQf4hZ8U9gbqQjxg3msZZIwuY7MHiQlYeJ0StUgC7JzP6oLv3Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a03e6a2c8f80e57ddd72c1d94d9a443bcb1bd670191ccfbe66feed5a7ab15fa","last_reissued_at":"2026-05-20T00:06:10.097909Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:10.097909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pointwise Generalization in Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.stat-mech","math.FA","math.PR","math.ST","stat.TH"],"primary_cat":"cs.LG","authors_text":"Shaojie Li, Yunbei Xu","submitted_at":"2026-05-18T16:09:06Z","abstract_excerpt":"We address the fundamental question of why deep neural networks generalize by establishing a pointwise generalization theory for fully connected networks. This framework resolves long-standing barriers to characterizing the rich nonlinear feature-learning regime and builds a new statistical foundation for representation learning. For each trained model, we characterize the hypothesis via a pointwise Riemannian Dimension, derived from the eigenvalues of the learned feature representations across layers. This establishes a principled framework for deriving hypothesis-dependent, representation-aw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18598","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/2605.18598/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T00:01:59.260932Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"852ed4524fd50d1b24b89fbbb889310a67eed07166d16073485efa7a4087b369"},"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":"2605.18598","created_at":"2026-05-20T00:06:10.098032+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18598v1","created_at":"2026-05-20T00:06:10.098032+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18598","created_at":"2026-05-20T00:06:10.098032+00:00"},{"alias_kind":"pith_short_12","alias_value":"FIB6NIWI7AHF","created_at":"2026-05-20T00:06:10.098032+00:00"},{"alias_kind":"pith_short_16","alias_value":"FIB6NIWI7AHFPXOX","created_at":"2026-05-20T00:06:10.098032+00:00"},{"alias_kind":"pith_short_8","alias_value":"FIB6NIWI","created_at":"2026-05-20T00:06:10.098032+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/FIB6NIWI7AHFPXOXFQOZJWNEIO","json":"https://pith.science/pith/FIB6NIWI7AHFPXOXFQOZJWNEIO.json","graph_json":"https://pith.science/api/pith-number/FIB6NIWI7AHFPXOXFQOZJWNEIO/graph.json","events_json":"https://pith.science/api/pith-number/FIB6NIWI7AHFPXOXFQOZJWNEIO/events.json","paper":"https://pith.science/paper/FIB6NIWI"},"agent_actions":{"view_html":"https://pith.science/pith/FIB6NIWI7AHFPXOXFQOZJWNEIO","download_json":"https://pith.science/pith/FIB6NIWI7AHFPXOXFQOZJWNEIO.json","view_paper":"https://pith.science/paper/FIB6NIWI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18598&json=true","fetch_graph":"https://pith.science/api/pith-number/FIB6NIWI7AHFPXOXFQOZJWNEIO/graph.json","fetch_events":"https://pith.science/api/pith-number/FIB6NIWI7AHFPXOXFQOZJWNEIO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FIB6NIWI7AHFPXOXFQOZJWNEIO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FIB6NIWI7AHFPXOXFQOZJWNEIO/action/storage_attestation","attest_author":"https://pith.science/pith/FIB6NIWI7AHFPXOXFQOZJWNEIO/action/author_attestation","sign_citation":"https://pith.science/pith/FIB6NIWI7AHFPXOXFQOZJWNEIO/action/citation_signature","submit_replication":"https://pith.science/pith/FIB6NIWI7AHFPXOXFQOZJWNEIO/action/replication_record"}},"created_at":"2026-05-20T00:06:10.098032+00:00","updated_at":"2026-05-20T00:06:10.098032+00:00"}