{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AJFMWHRAYDZTBIVUEWZPL3VJXZ","short_pith_number":"pith:AJFMWHRA","schema_version":"1.0","canonical_sha256":"024acb1e20c0f330a2b425b2f5eea9be4b86f1cbe27ba3dc45cdedbfd795f256","source":{"kind":"arxiv","id":"2506.00324","version":1},"attestation_state":"computed","paper":{"title":"Improving Optical Flow and Stereo Depth Estimation by Leveraging Uncertainty-Based Learning Difficulties","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fatih Porikli, Hong Cai, Jamie Menjay Lin, Jisoo Jeong","submitted_at":"2025-05-31T00:37:12Z","abstract_excerpt":"Conventional training for optical flow and stereo depth models typically employs a uniform loss function across all pixels. However, this one-size-fits-all approach often overlooks the significant variations in learning difficulty among individual pixels and contextual regions. This paper investigates the uncertainty-based confidence maps which capture these spatially varying learning difficulties and introduces tailored solutions to address them. We first present the Difficulty Balancing (DB) loss, which utilizes an error-based confidence measure to encourage the network to focus more on chal"},"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":"2506.00324","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-31T00:37:12Z","cross_cats_sorted":[],"title_canon_sha256":"852dba596dc68456fd7642107a80297582564f5f3af65066dba9cafd9af2e9c4","abstract_canon_sha256":"6295f5f6a53f7be78be4dea7d8496a7b26d8364e02b1cfa5de335df3e6a9745b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:32.561286Z","signature_b64":"bG6AeMIIM85YoNXTwpel1pl95mKuoq9k7azxWhOOSKo0Qwsl33SO7GHgVIScXLjV5JV7plbZtNVq8BPGVn+IAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"024acb1e20c0f330a2b425b2f5eea9be4b86f1cbe27ba3dc45cdedbfd795f256","last_reissued_at":"2026-07-05T11:13:32.560765Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:32.560765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Optical Flow and Stereo Depth Estimation by Leveraging Uncertainty-Based Learning Difficulties","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fatih Porikli, Hong Cai, Jamie Menjay Lin, Jisoo Jeong","submitted_at":"2025-05-31T00:37:12Z","abstract_excerpt":"Conventional training for optical flow and stereo depth models typically employs a uniform loss function across all pixels. However, this one-size-fits-all approach often overlooks the significant variations in learning difficulty among individual pixels and contextual regions. This paper investigates the uncertainty-based confidence maps which capture these spatially varying learning difficulties and introduces tailored solutions to address them. We first present the Difficulty Balancing (DB) loss, which utilizes an error-based confidence measure to encourage the network to focus more on chal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00324","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/2506.00324/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":"2506.00324","created_at":"2026-07-05T11:13:32.560846+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.00324v1","created_at":"2026-07-05T11:13:32.560846+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00324","created_at":"2026-07-05T11:13:32.560846+00:00"},{"alias_kind":"pith_short_12","alias_value":"AJFMWHRAYDZT","created_at":"2026-07-05T11:13:32.560846+00:00"},{"alias_kind":"pith_short_16","alias_value":"AJFMWHRAYDZTBIVU","created_at":"2026-07-05T11:13:32.560846+00:00"},{"alias_kind":"pith_short_8","alias_value":"AJFMWHRA","created_at":"2026-07-05T11:13:32.560846+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/AJFMWHRAYDZTBIVUEWZPL3VJXZ","json":"https://pith.science/pith/AJFMWHRAYDZTBIVUEWZPL3VJXZ.json","graph_json":"https://pith.science/api/pith-number/AJFMWHRAYDZTBIVUEWZPL3VJXZ/graph.json","events_json":"https://pith.science/api/pith-number/AJFMWHRAYDZTBIVUEWZPL3VJXZ/events.json","paper":"https://pith.science/paper/AJFMWHRA"},"agent_actions":{"view_html":"https://pith.science/pith/AJFMWHRAYDZTBIVUEWZPL3VJXZ","download_json":"https://pith.science/pith/AJFMWHRAYDZTBIVUEWZPL3VJXZ.json","view_paper":"https://pith.science/paper/AJFMWHRA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.00324&json=true","fetch_graph":"https://pith.science/api/pith-number/AJFMWHRAYDZTBIVUEWZPL3VJXZ/graph.json","fetch_events":"https://pith.science/api/pith-number/AJFMWHRAYDZTBIVUEWZPL3VJXZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AJFMWHRAYDZTBIVUEWZPL3VJXZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AJFMWHRAYDZTBIVUEWZPL3VJXZ/action/storage_attestation","attest_author":"https://pith.science/pith/AJFMWHRAYDZTBIVUEWZPL3VJXZ/action/author_attestation","sign_citation":"https://pith.science/pith/AJFMWHRAYDZTBIVUEWZPL3VJXZ/action/citation_signature","submit_replication":"https://pith.science/pith/AJFMWHRAYDZTBIVUEWZPL3VJXZ/action/replication_record"}},"created_at":"2026-07-05T11:13:32.560846+00:00","updated_at":"2026-07-05T11:13:32.560846+00:00"}