{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:LK2WHCGJFIYYNQ3MRF3EA3RVHM","short_pith_number":"pith:LK2WHCGJ","schema_version":"1.0","canonical_sha256":"5ab56388c92a3186c36c8976406e353b16f2ce8ecff9b880ebbb757229c78f80","source":{"kind":"arxiv","id":"2104.06957","version":2},"attestation_state":"computed","paper":{"title":"ComBiNet: Compact Convolutional Bayesian Neural Network for Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Divyansh Manocha, Hongxiang Fan, Martin Ferianc, Miguel Rodrigues","submitted_at":"2021-04-14T16:33:48Z","abstract_excerpt":"Fully convolutional U-shaped neural networks have largely been the dominant approach for pixel-wise image segmentation. In this work, we tackle two defects that hinder their deployment in real-world applications: 1) Predictions lack uncertainty quantification that may be crucial to many decision-making systems; 2) Large memory storage and computational consumption demanding extensive hardware resources. To address these issues and improve their practicality we demonstrate a few-parameter compact Bayesian convolutional architecture, that achieves a marginal improvement in accuracy in comparison"},"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":"2104.06957","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-14T16:33:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5352bcf002b030ccc3f9984aaecae1d33c39527eea51c80fe899c7353c8b06af","abstract_canon_sha256":"0bb16906a35ce56dec3b3691d72a7ea0c10254049b25c35f6050a27b49953a5a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:52:28.349307Z","signature_b64":"dNb8nPq57TCi+YX/glquowsTnc+dwWljCIVqn13eUOmWEqh60oazwzdqg7aq+WZDCktQh2VGjp5lTcsyJkv+DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ab56388c92a3186c36c8976406e353b16f2ce8ecff9b880ebbb757229c78f80","last_reissued_at":"2026-07-05T02:52:28.348874Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:52:28.348874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ComBiNet: Compact Convolutional Bayesian Neural Network for Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Divyansh Manocha, Hongxiang Fan, Martin Ferianc, Miguel Rodrigues","submitted_at":"2021-04-14T16:33:48Z","abstract_excerpt":"Fully convolutional U-shaped neural networks have largely been the dominant approach for pixel-wise image segmentation. In this work, we tackle two defects that hinder their deployment in real-world applications: 1) Predictions lack uncertainty quantification that may be crucial to many decision-making systems; 2) Large memory storage and computational consumption demanding extensive hardware resources. To address these issues and improve their practicality we demonstrate a few-parameter compact Bayesian convolutional architecture, that achieves a marginal improvement in accuracy in comparison"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.06957","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/2104.06957/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":"2104.06957","created_at":"2026-07-05T02:52:28.348928+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.06957v2","created_at":"2026-07-05T02:52:28.348928+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.06957","created_at":"2026-07-05T02:52:28.348928+00:00"},{"alias_kind":"pith_short_12","alias_value":"LK2WHCGJFIYY","created_at":"2026-07-05T02:52:28.348928+00:00"},{"alias_kind":"pith_short_16","alias_value":"LK2WHCGJFIYYNQ3M","created_at":"2026-07-05T02:52:28.348928+00:00"},{"alias_kind":"pith_short_8","alias_value":"LK2WHCGJ","created_at":"2026-07-05T02:52:28.348928+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/LK2WHCGJFIYYNQ3MRF3EA3RVHM","json":"https://pith.science/pith/LK2WHCGJFIYYNQ3MRF3EA3RVHM.json","graph_json":"https://pith.science/api/pith-number/LK2WHCGJFIYYNQ3MRF3EA3RVHM/graph.json","events_json":"https://pith.science/api/pith-number/LK2WHCGJFIYYNQ3MRF3EA3RVHM/events.json","paper":"https://pith.science/paper/LK2WHCGJ"},"agent_actions":{"view_html":"https://pith.science/pith/LK2WHCGJFIYYNQ3MRF3EA3RVHM","download_json":"https://pith.science/pith/LK2WHCGJFIYYNQ3MRF3EA3RVHM.json","view_paper":"https://pith.science/paper/LK2WHCGJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.06957&json=true","fetch_graph":"https://pith.science/api/pith-number/LK2WHCGJFIYYNQ3MRF3EA3RVHM/graph.json","fetch_events":"https://pith.science/api/pith-number/LK2WHCGJFIYYNQ3MRF3EA3RVHM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LK2WHCGJFIYYNQ3MRF3EA3RVHM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LK2WHCGJFIYYNQ3MRF3EA3RVHM/action/storage_attestation","attest_author":"https://pith.science/pith/LK2WHCGJFIYYNQ3MRF3EA3RVHM/action/author_attestation","sign_citation":"https://pith.science/pith/LK2WHCGJFIYYNQ3MRF3EA3RVHM/action/citation_signature","submit_replication":"https://pith.science/pith/LK2WHCGJFIYYNQ3MRF3EA3RVHM/action/replication_record"}},"created_at":"2026-07-05T02:52:28.348928+00:00","updated_at":"2026-07-05T02:52:28.348928+00:00"}