{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:K3FQWGND7CO5P54RK2JTBTOC7J","short_pith_number":"pith:K3FQWGND","schema_version":"1.0","canonical_sha256":"56cb0b19a3f89dd7f791569330cdc2fa7f936e1823da6e5ad98b8c8aa6349418","source":{"kind":"arxiv","id":"2302.06359","version":4},"attestation_state":"computed","paper":{"title":"Fixing Overconfidence in Dynamic Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrea Pilzer, Arno Solin, Lassi Meronen, Le Yang, Martin Trapp","submitted_at":"2023-02-13T13:45:50Z","abstract_excerpt":"Dynamic neural networks are a recent technique that promises a remedy for the increasing size of modern deep learning models by dynamically adapting their computational cost to the difficulty of the inputs. In this way, the model can adjust to a limited computational budget. However, the poor quality of uncertainty estimates in deep learning models makes it difficult to distinguish between hard and easy samples. To address this challenge, we present a computationally efficient approach for post-hoc uncertainty quantification in dynamic neural networks. We show that adequately quantifying and a"},"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":"2302.06359","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-13T13:45:50Z","cross_cats_sorted":[],"title_canon_sha256":"6609798eacd7413e63ff1aa455c750e448aa293979dcf8824d6cc11ab015cda8","abstract_canon_sha256":"7f81c062570598c4c15e267418af2310e4a382982117722ef48cc56c5c1a00c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:21:40.762276Z","signature_b64":"ILAsujzNpu8SOnTcJ5tVy9qR7M/FK8NcBg0gK6Tyep8v2zLKSWea7FCQX3sexVH+qZIbY1QG+rlfWJUx5i/hBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56cb0b19a3f89dd7f791569330cdc2fa7f936e1823da6e5ad98b8c8aa6349418","last_reissued_at":"2026-07-05T07:21:40.761788Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:21:40.761788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fixing Overconfidence in Dynamic Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrea Pilzer, Arno Solin, Lassi Meronen, Le Yang, Martin Trapp","submitted_at":"2023-02-13T13:45:50Z","abstract_excerpt":"Dynamic neural networks are a recent technique that promises a remedy for the increasing size of modern deep learning models by dynamically adapting their computational cost to the difficulty of the inputs. In this way, the model can adjust to a limited computational budget. However, the poor quality of uncertainty estimates in deep learning models makes it difficult to distinguish between hard and easy samples. To address this challenge, we present a computationally efficient approach for post-hoc uncertainty quantification in dynamic neural networks. We show that adequately quantifying and a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.06359","kind":"arxiv","version":4},"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/2302.06359/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":"2302.06359","created_at":"2026-07-05T07:21:40.761849+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.06359v4","created_at":"2026-07-05T07:21:40.761849+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.06359","created_at":"2026-07-05T07:21:40.761849+00:00"},{"alias_kind":"pith_short_12","alias_value":"K3FQWGND7CO5","created_at":"2026-07-05T07:21:40.761849+00:00"},{"alias_kind":"pith_short_16","alias_value":"K3FQWGND7CO5P54R","created_at":"2026-07-05T07:21:40.761849+00:00"},{"alias_kind":"pith_short_8","alias_value":"K3FQWGND","created_at":"2026-07-05T07:21:40.761849+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/K3FQWGND7CO5P54RK2JTBTOC7J","json":"https://pith.science/pith/K3FQWGND7CO5P54RK2JTBTOC7J.json","graph_json":"https://pith.science/api/pith-number/K3FQWGND7CO5P54RK2JTBTOC7J/graph.json","events_json":"https://pith.science/api/pith-number/K3FQWGND7CO5P54RK2JTBTOC7J/events.json","paper":"https://pith.science/paper/K3FQWGND"},"agent_actions":{"view_html":"https://pith.science/pith/K3FQWGND7CO5P54RK2JTBTOC7J","download_json":"https://pith.science/pith/K3FQWGND7CO5P54RK2JTBTOC7J.json","view_paper":"https://pith.science/paper/K3FQWGND","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.06359&json=true","fetch_graph":"https://pith.science/api/pith-number/K3FQWGND7CO5P54RK2JTBTOC7J/graph.json","fetch_events":"https://pith.science/api/pith-number/K3FQWGND7CO5P54RK2JTBTOC7J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K3FQWGND7CO5P54RK2JTBTOC7J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K3FQWGND7CO5P54RK2JTBTOC7J/action/storage_attestation","attest_author":"https://pith.science/pith/K3FQWGND7CO5P54RK2JTBTOC7J/action/author_attestation","sign_citation":"https://pith.science/pith/K3FQWGND7CO5P54RK2JTBTOC7J/action/citation_signature","submit_replication":"https://pith.science/pith/K3FQWGND7CO5P54RK2JTBTOC7J/action/replication_record"}},"created_at":"2026-07-05T07:21:40.761849+00:00","updated_at":"2026-07-05T07:21:40.761849+00:00"}