{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UZSKYMBVUXO7OVNQCTLLI56DCK","short_pith_number":"pith:UZSKYMBV","schema_version":"1.0","canonical_sha256":"a664ac3035a5ddf755b014d6b477c3128b8d4a6f0c2a4b6faf67aebd3175b1e9","source":{"kind":"arxiv","id":"2409.17085","version":1},"attestation_state":"computed","paper":{"title":"Parameter-efficient Bayesian Neural Networks for Uncertainty-aware Depth Estimation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CV","authors_text":"Alessio Quercia, Hanno Scharr, Katharina N\\\"oh, Richard D. Paul, Vincent Fortuin","submitted_at":"2024-09-25T16:49:25Z","abstract_excerpt":"State-of-the-art computer vision tasks, like monocular depth estimation (MDE), rely heavily on large, modern Transformer-based architectures. However, their application in safety-critical domains demands reliable predictive performance and uncertainty quantification. While Bayesian neural networks provide a conceptually simple approach to serve those requirements, they suffer from the high dimensionality of the parameter space. Parameter-efficient fine-tuning (PEFT) methods, in particular low-rank adaptations (LoRA), have emerged as a popular strategy for adapting large-scale models to down-st"},"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":"2409.17085","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-25T16:49:25Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8f3cc549225fc73fcf24ea6eaaa2475655355bfdd28b413fa78722e407b093c6","abstract_canon_sha256":"49edabd7a57c2fa11b5ec747819b1f9c6786a9343ee01e74a154fbb30eb9021f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:11:43.608828Z","signature_b64":"PY6sdN12YVyjnTw3MACHSg2vCBFzzKfMomzy2lCiX7wXvbPVInPlNawDfqwCy31w+2s11bJqHztUn+ZkqNgDBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a664ac3035a5ddf755b014d6b477c3128b8d4a6f0c2a4b6faf67aebd3175b1e9","last_reissued_at":"2026-07-05T09:11:43.608346Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:11:43.608346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Parameter-efficient Bayesian Neural Networks for Uncertainty-aware Depth Estimation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CV","authors_text":"Alessio Quercia, Hanno Scharr, Katharina N\\\"oh, Richard D. Paul, Vincent Fortuin","submitted_at":"2024-09-25T16:49:25Z","abstract_excerpt":"State-of-the-art computer vision tasks, like monocular depth estimation (MDE), rely heavily on large, modern Transformer-based architectures. However, their application in safety-critical domains demands reliable predictive performance and uncertainty quantification. While Bayesian neural networks provide a conceptually simple approach to serve those requirements, they suffer from the high dimensionality of the parameter space. Parameter-efficient fine-tuning (PEFT) methods, in particular low-rank adaptations (LoRA), have emerged as a popular strategy for adapting large-scale models to down-st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.17085","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/2409.17085/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":"2409.17085","created_at":"2026-07-05T09:11:43.608406+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.17085v1","created_at":"2026-07-05T09:11:43.608406+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.17085","created_at":"2026-07-05T09:11:43.608406+00:00"},{"alias_kind":"pith_short_12","alias_value":"UZSKYMBVUXO7","created_at":"2026-07-05T09:11:43.608406+00:00"},{"alias_kind":"pith_short_16","alias_value":"UZSKYMBVUXO7OVNQ","created_at":"2026-07-05T09:11:43.608406+00:00"},{"alias_kind":"pith_short_8","alias_value":"UZSKYMBV","created_at":"2026-07-05T09:11:43.608406+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.05049","citing_title":"UncertainSAM: Fast and Efficient Uncertainty Quantification of the Segment Anything Model","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UZSKYMBVUXO7OVNQCTLLI56DCK","json":"https://pith.science/pith/UZSKYMBVUXO7OVNQCTLLI56DCK.json","graph_json":"https://pith.science/api/pith-number/UZSKYMBVUXO7OVNQCTLLI56DCK/graph.json","events_json":"https://pith.science/api/pith-number/UZSKYMBVUXO7OVNQCTLLI56DCK/events.json","paper":"https://pith.science/paper/UZSKYMBV"},"agent_actions":{"view_html":"https://pith.science/pith/UZSKYMBVUXO7OVNQCTLLI56DCK","download_json":"https://pith.science/pith/UZSKYMBVUXO7OVNQCTLLI56DCK.json","view_paper":"https://pith.science/paper/UZSKYMBV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.17085&json=true","fetch_graph":"https://pith.science/api/pith-number/UZSKYMBVUXO7OVNQCTLLI56DCK/graph.json","fetch_events":"https://pith.science/api/pith-number/UZSKYMBVUXO7OVNQCTLLI56DCK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UZSKYMBVUXO7OVNQCTLLI56DCK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UZSKYMBVUXO7OVNQCTLLI56DCK/action/storage_attestation","attest_author":"https://pith.science/pith/UZSKYMBVUXO7OVNQCTLLI56DCK/action/author_attestation","sign_citation":"https://pith.science/pith/UZSKYMBVUXO7OVNQCTLLI56DCK/action/citation_signature","submit_replication":"https://pith.science/pith/UZSKYMBVUXO7OVNQCTLLI56DCK/action/replication_record"}},"created_at":"2026-07-05T09:11:43.608406+00:00","updated_at":"2026-07-05T09:11:43.608406+00:00"}