{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EXLVOXRBMLSIT5GYHAEISBOMIF","short_pith_number":"pith:EXLVOXRB","schema_version":"1.0","canonical_sha256":"25d7575e2162e489f4d838088905cc41559ebe3d62504317f3e84ad6c1a71fa0","source":{"kind":"arxiv","id":"2503.07325","version":2},"attestation_state":"computed","paper":{"title":"Non-vacuous Generalization Bounds for Deep Neural Networks without any modification to the trained models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dat Phan, Khoat Than","submitted_at":"2025-03-10T13:40:10Z","abstract_excerpt":"Understanding and certifying the behavior of modern deep neural networks remains a fundamental challenge in reliable machine learning. We introduce a new class of data-dependent generalization bounds that apply directly to trained models, without any modification. In particular, we present an exactly computable bound that is non-vacuous across all evaluated networks, including ImageNet-scale models with 600M parameters. This this is the first work showing that meaningful generalization guarantees are achievable even for large, unaltered deep networks.\n  Our approach reveals that generalization"},"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":"2503.07325","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-10T13:40:10Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"90d30e984b72d51d2c5299bd0dfa56bc6876c118ff6090d9790f31adc54f58f7","abstract_canon_sha256":"fec798db7d67c9da669178863d2600710a9d661aabd8a37d8953ffbfe60d8faf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:05.360371Z","signature_b64":"e48Fmd7px2zFEvWGzpMwpRQHARkzAMJpycwNWs8pZDVeKEmCxrXqNJ6x6zmlyAenWSyJqz0HYHVbWc+hvDflBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25d7575e2162e489f4d838088905cc41559ebe3d62504317f3e84ad6c1a71fa0","last_reissued_at":"2026-06-02T02:04:05.359809Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:05.359809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Non-vacuous Generalization Bounds for Deep Neural Networks without any modification to the trained models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dat Phan, Khoat Than","submitted_at":"2025-03-10T13:40:10Z","abstract_excerpt":"Understanding and certifying the behavior of modern deep neural networks remains a fundamental challenge in reliable machine learning. We introduce a new class of data-dependent generalization bounds that apply directly to trained models, without any modification. In particular, we present an exactly computable bound that is non-vacuous across all evaluated networks, including ImageNet-scale models with 600M parameters. This this is the first work showing that meaningful generalization guarantees are achievable even for large, unaltered deep networks.\n  Our approach reveals that generalization"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.07325","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/2503.07325/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":"2503.07325","created_at":"2026-06-02T02:04:05.359866+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.07325v2","created_at":"2026-06-02T02:04:05.359866+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.07325","created_at":"2026-06-02T02:04:05.359866+00:00"},{"alias_kind":"pith_short_12","alias_value":"EXLVOXRBMLSI","created_at":"2026-06-02T02:04:05.359866+00:00"},{"alias_kind":"pith_short_16","alias_value":"EXLVOXRBMLSIT5GY","created_at":"2026-06-02T02:04:05.359866+00:00"},{"alias_kind":"pith_short_8","alias_value":"EXLVOXRB","created_at":"2026-06-02T02:04:05.359866+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/EXLVOXRBMLSIT5GYHAEISBOMIF","json":"https://pith.science/pith/EXLVOXRBMLSIT5GYHAEISBOMIF.json","graph_json":"https://pith.science/api/pith-number/EXLVOXRBMLSIT5GYHAEISBOMIF/graph.json","events_json":"https://pith.science/api/pith-number/EXLVOXRBMLSIT5GYHAEISBOMIF/events.json","paper":"https://pith.science/paper/EXLVOXRB"},"agent_actions":{"view_html":"https://pith.science/pith/EXLVOXRBMLSIT5GYHAEISBOMIF","download_json":"https://pith.science/pith/EXLVOXRBMLSIT5GYHAEISBOMIF.json","view_paper":"https://pith.science/paper/EXLVOXRB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.07325&json=true","fetch_graph":"https://pith.science/api/pith-number/EXLVOXRBMLSIT5GYHAEISBOMIF/graph.json","fetch_events":"https://pith.science/api/pith-number/EXLVOXRBMLSIT5GYHAEISBOMIF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EXLVOXRBMLSIT5GYHAEISBOMIF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EXLVOXRBMLSIT5GYHAEISBOMIF/action/storage_attestation","attest_author":"https://pith.science/pith/EXLVOXRBMLSIT5GYHAEISBOMIF/action/author_attestation","sign_citation":"https://pith.science/pith/EXLVOXRBMLSIT5GYHAEISBOMIF/action/citation_signature","submit_replication":"https://pith.science/pith/EXLVOXRBMLSIT5GYHAEISBOMIF/action/replication_record"}},"created_at":"2026-06-02T02:04:05.359866+00:00","updated_at":"2026-06-02T02:04:05.359866+00:00"}