{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CFQAOTZZ2RCDK4VH5R2HDFIETB","short_pith_number":"pith:CFQAOTZZ","schema_version":"1.0","canonical_sha256":"1160074f39d4443572a7ec7471950498774362dad31997c094d287df581ae091","source":{"kind":"arxiv","id":"2203.16034","version":2},"attestation_state":"computed","paper":{"title":"Monitored Distillation for Positive Congruent Depth Completion","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alex Wong, Allison Chen, Byung-Woo Hong, Parth Agrawal, Tian Yu Liu","submitted_at":"2022-03-30T03:35:56Z","abstract_excerpt":"We propose a method to infer a dense depth map from a single image, its calibration, and the associated sparse point cloud. In order to leverage existing models (teachers) that produce putative depth maps, we propose an adaptive knowledge distillation approach that yields a positive congruent training process, wherein a student model avoids learning the error modes of the teachers. In the absence of ground truth for model selection and training, our method, termed Monitored Distillation, allows a student to exploit a blind ensemble of teachers by selectively learning from predictions that best"},"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":"2203.16034","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-30T03:35:56Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4519b086f142a23f8fa4acb7f9fab9042fde96357bb9507384550688fb65c53f","abstract_canon_sha256":"0c1283cee4d377bfc1605b42f4cba1d7172f4fc08350c3eea3b76cc4284b4c49"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:09:55.908412Z","signature_b64":"PqZhlAqu0qh5+qyTWt4Mgx+bc5f8Ek4RPACyUHPxg8lXuTcEu38WzjGQxuLHBtRk/T5xAE54bpHI64D+GBoVAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1160074f39d4443572a7ec7471950498774362dad31997c094d287df581ae091","last_reissued_at":"2026-07-05T05:09:55.907985Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:09:55.907985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Monitored Distillation for Positive Congruent Depth Completion","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alex Wong, Allison Chen, Byung-Woo Hong, Parth Agrawal, Tian Yu Liu","submitted_at":"2022-03-30T03:35:56Z","abstract_excerpt":"We propose a method to infer a dense depth map from a single image, its calibration, and the associated sparse point cloud. In order to leverage existing models (teachers) that produce putative depth maps, we propose an adaptive knowledge distillation approach that yields a positive congruent training process, wherein a student model avoids learning the error modes of the teachers. In the absence of ground truth for model selection and training, our method, termed Monitored Distillation, allows a student to exploit a blind ensemble of teachers by selectively learning from predictions that best"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.16034","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/2203.16034/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":"2203.16034","created_at":"2026-07-05T05:09:55.908039+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.16034v2","created_at":"2026-07-05T05:09:55.908039+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.16034","created_at":"2026-07-05T05:09:55.908039+00:00"},{"alias_kind":"pith_short_12","alias_value":"CFQAOTZZ2RCD","created_at":"2026-07-05T05:09:55.908039+00:00"},{"alias_kind":"pith_short_16","alias_value":"CFQAOTZZ2RCDK4VH","created_at":"2026-07-05T05:09:55.908039+00:00"},{"alias_kind":"pith_short_8","alias_value":"CFQAOTZZ","created_at":"2026-07-05T05:09:55.908039+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/CFQAOTZZ2RCDK4VH5R2HDFIETB","json":"https://pith.science/pith/CFQAOTZZ2RCDK4VH5R2HDFIETB.json","graph_json":"https://pith.science/api/pith-number/CFQAOTZZ2RCDK4VH5R2HDFIETB/graph.json","events_json":"https://pith.science/api/pith-number/CFQAOTZZ2RCDK4VH5R2HDFIETB/events.json","paper":"https://pith.science/paper/CFQAOTZZ"},"agent_actions":{"view_html":"https://pith.science/pith/CFQAOTZZ2RCDK4VH5R2HDFIETB","download_json":"https://pith.science/pith/CFQAOTZZ2RCDK4VH5R2HDFIETB.json","view_paper":"https://pith.science/paper/CFQAOTZZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.16034&json=true","fetch_graph":"https://pith.science/api/pith-number/CFQAOTZZ2RCDK4VH5R2HDFIETB/graph.json","fetch_events":"https://pith.science/api/pith-number/CFQAOTZZ2RCDK4VH5R2HDFIETB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CFQAOTZZ2RCDK4VH5R2HDFIETB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CFQAOTZZ2RCDK4VH5R2HDFIETB/action/storage_attestation","attest_author":"https://pith.science/pith/CFQAOTZZ2RCDK4VH5R2HDFIETB/action/author_attestation","sign_citation":"https://pith.science/pith/CFQAOTZZ2RCDK4VH5R2HDFIETB/action/citation_signature","submit_replication":"https://pith.science/pith/CFQAOTZZ2RCDK4VH5R2HDFIETB/action/replication_record"}},"created_at":"2026-07-05T05:09:55.908039+00:00","updated_at":"2026-07-05T05:09:55.908039+00:00"}