{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FIB6NIWI7AHFPXOXFQOZJWNEIO","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"319555a63e1f119b9034a9c39eb74946f5f52f43f4bfc46936d59189673705dc","cross_cats_sorted":["cond-mat.stat-mech","math.FA","math.PR","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T16:09:06Z","title_canon_sha256":"3fa8f1024a573e031fc307b776bf80fa170d7682a7b2614a31d8f657812ca7eb"},"schema_version":"1.0","source":{"id":"2605.18598","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18598","created_at":"2026-05-20T00:06:10Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18598v1","created_at":"2026-05-20T00:06:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18598","created_at":"2026-05-20T00:06:10Z"},{"alias_kind":"pith_short_12","alias_value":"FIB6NIWI7AHF","created_at":"2026-05-20T00:06:10Z"},{"alias_kind":"pith_short_16","alias_value":"FIB6NIWI7AHFPXOX","created_at":"2026-05-20T00:06:10Z"},{"alias_kind":"pith_short_8","alias_value":"FIB6NIWI","created_at":"2026-05-20T00:06:10Z"}],"graph_snapshots":[{"event_id":"sha256:969aa406e44bc9c27f0c1b2ded6820e38e23b749efb13b63e74d67d81b25bbc0","target":"graph","created_at":"2026-05-20T00:06:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T00:01:59.260932Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.18598/integrity.json","findings":[],"snapshot_sha256":"852ed4524fd50d1b24b89fbbb889310a67eed07166d16073485efa7a4087b369","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Shaojie Li, Yunbei Xu","cross_cats":["cond-mat.stat-mech","math.FA","math.PR","math.ST","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T16:09:06Z","title":"Pointwise Generalization in Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18598","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b5e52e4f8cfe079168a907954049feb324f695246f41ae185056325e06bde623","target":"record","created_at":"2026-05-20T00:06:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"319555a63e1f119b9034a9c39eb74946f5f52f43f4bfc46936d59189673705dc","cross_cats_sorted":["cond-mat.stat-mech","math.FA","math.PR","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T16:09:06Z","title_canon_sha256":"3fa8f1024a573e031fc307b776bf80fa170d7682a7b2614a31d8f657812ca7eb"},"schema_version":"1.0","source":{"id":"2605.18598","kind":"arxiv","version":1}},"canonical_sha256":"2a03e6a2c8f80e57ddd72c1d94d9a443bcb1bd670191ccfbe66feed5a7ab15fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a03e6a2c8f80e57ddd72c1d94d9a443bcb1bd670191ccfbe66feed5a7ab15fa","first_computed_at":"2026-05-20T00:06:10.097909Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:06:10.097909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bhBWxhl54+vr62uE/1FDrDsczfRwxU5vu1nyQf4hZ8U9gbqQjxg3msZZIwuY7MHiQlYeJ0StUgC7JzP6oLv3Aw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:06:10.098755Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.18598","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5e52e4f8cfe079168a907954049feb324f695246f41ae185056325e06bde623","sha256:969aa406e44bc9c27f0c1b2ded6820e38e23b749efb13b63e74d67d81b25bbc0"],"state_sha256":"a704dddecad11e7adf2efe51e9b1b7722b5d542c14c55a16b6b5db8182ca2fe3"}