{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FVQQFGMSOHGAHQTRTOVZRUAXES","short_pith_number":"pith:FVQQFGMS","schema_version":"1.0","canonical_sha256":"2d6102999271cc03c2719bab98d017249be94d2293ab7507b1b1462e7cc4900c","source":{"kind":"arxiv","id":"2209.15208","version":1},"attestation_state":"computed","paper":{"title":"Scale-invariant Bayesian Neural Networks with Connectivity Tangent Kernel","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Eunho Yang, Kyungsu Kim, Sihwan Park, Sungyub Kim","submitted_at":"2022-09-30T03:31:13Z","abstract_excerpt":"Explaining generalizations and preventing over-confident predictions are central goals of studies on the loss landscape of neural networks. Flatness, defined as loss invariability on perturbations of a pre-trained solution, is widely accepted as a predictor of generalization in this context. However, the problem that flatness and generalization bounds can be changed arbitrarily according to the scale of a parameter was pointed out, and previous studies partially solved the problem with restrictions: Counter-intuitively, their generalization bounds were still variant for the function-preserving"},"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":"2209.15208","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-30T03:31:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a7fdf6b0990d9eb8f72bcd3c6839d6e1ebeabf11f2d11094ee11bb2137c11f61","abstract_canon_sha256":"b40a2b99a9b6fdf1f4d4b866ebdc303700b2529dbc1371d128b4773e892303eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:02:17.613037Z","signature_b64":"Ggj0gvShY3t3EXBTpGRZck85ocfCEpt95orxnTbqh+rNzmQPxu/duLiec4H6Xubz1QCxD/dKKmfjgQFWY4hICQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d6102999271cc03c2719bab98d017249be94d2293ab7507b1b1462e7cc4900c","last_reissued_at":"2026-07-05T05:02:17.612600Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:02:17.612600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scale-invariant Bayesian Neural Networks with Connectivity Tangent Kernel","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Eunho Yang, Kyungsu Kim, Sihwan Park, Sungyub Kim","submitted_at":"2022-09-30T03:31:13Z","abstract_excerpt":"Explaining generalizations and preventing over-confident predictions are central goals of studies on the loss landscape of neural networks. Flatness, defined as loss invariability on perturbations of a pre-trained solution, is widely accepted as a predictor of generalization in this context. However, the problem that flatness and generalization bounds can be changed arbitrarily according to the scale of a parameter was pointed out, and previous studies partially solved the problem with restrictions: Counter-intuitively, their generalization bounds were still variant for the function-preserving"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.15208","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/2209.15208/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":"2209.15208","created_at":"2026-07-05T05:02:17.612657+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.15208v1","created_at":"2026-07-05T05:02:17.612657+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.15208","created_at":"2026-07-05T05:02:17.612657+00:00"},{"alias_kind":"pith_short_12","alias_value":"FVQQFGMSOHGA","created_at":"2026-07-05T05:02:17.612657+00:00"},{"alias_kind":"pith_short_16","alias_value":"FVQQFGMSOHGAHQTR","created_at":"2026-07-05T05:02:17.612657+00:00"},{"alias_kind":"pith_short_8","alias_value":"FVQQFGMS","created_at":"2026-07-05T05:02:17.612657+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/FVQQFGMSOHGAHQTRTOVZRUAXES","json":"https://pith.science/pith/FVQQFGMSOHGAHQTRTOVZRUAXES.json","graph_json":"https://pith.science/api/pith-number/FVQQFGMSOHGAHQTRTOVZRUAXES/graph.json","events_json":"https://pith.science/api/pith-number/FVQQFGMSOHGAHQTRTOVZRUAXES/events.json","paper":"https://pith.science/paper/FVQQFGMS"},"agent_actions":{"view_html":"https://pith.science/pith/FVQQFGMSOHGAHQTRTOVZRUAXES","download_json":"https://pith.science/pith/FVQQFGMSOHGAHQTRTOVZRUAXES.json","view_paper":"https://pith.science/paper/FVQQFGMS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.15208&json=true","fetch_graph":"https://pith.science/api/pith-number/FVQQFGMSOHGAHQTRTOVZRUAXES/graph.json","fetch_events":"https://pith.science/api/pith-number/FVQQFGMSOHGAHQTRTOVZRUAXES/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FVQQFGMSOHGAHQTRTOVZRUAXES/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FVQQFGMSOHGAHQTRTOVZRUAXES/action/storage_attestation","attest_author":"https://pith.science/pith/FVQQFGMSOHGAHQTRTOVZRUAXES/action/author_attestation","sign_citation":"https://pith.science/pith/FVQQFGMSOHGAHQTRTOVZRUAXES/action/citation_signature","submit_replication":"https://pith.science/pith/FVQQFGMSOHGAHQTRTOVZRUAXES/action/replication_record"}},"created_at":"2026-07-05T05:02:17.612657+00:00","updated_at":"2026-07-05T05:02:17.612657+00:00"}