{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:52DSWRQJ5UAPN3GP4CMDN7N5VF","short_pith_number":"pith:52DSWRQJ","schema_version":"1.0","canonical_sha256":"ee872b4609ed00f6eccfe09836fdbda94c2ec340cdda4bcc5f55fbcca6deeaa9","source":{"kind":"arxiv","id":"2303.10449","version":2},"attestation_state":"computed","paper":{"title":"Uncertainty-Aware Optimal Transport for Semantically Coherent Out-of-Distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fan Lu, Kai Zhu, Kecheng Zheng, Wei Zhai, Yang Cao","submitted_at":"2023-03-18T16:22:59Z","abstract_excerpt":"Semantically coherent out-of-distribution (SCOOD) detection aims to discern outliers from the intended data distribution with access to unlabeled extra set. The coexistence of in-distribution and out-of-distribution samples will exacerbate the model overfitting when no distinction is made. To address this problem, we propose a novel uncertainty-aware optimal transport scheme. Our scheme consists of an energy-based transport (ET) mechanism that estimates the fluctuating cost of uncertainty to promote the assignment of semantic-agnostic representation, and an inter-cluster extension strategy tha"},"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":"2303.10449","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-18T16:22:59Z","cross_cats_sorted":[],"title_canon_sha256":"41a48cfe8ce8c5f9c2df7f8de9325a86fbd21c514b30dfe6ceabc61b56ad6eb2","abstract_canon_sha256":"24aabfcbe55bdf66eb7dff9dcac9a24dc87e29a03aad61adb369393f6579f94b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:53:16.616003Z","signature_b64":"KKN0uuw8dvM8RoWZ+JHxhkE4yrU2h+SBMgMwD5KwOgkDpTn8lAC1HddryBzjup3qYYzjohnZjgE517PwYNztBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee872b4609ed00f6eccfe09836fdbda94c2ec340cdda4bcc5f55fbcca6deeaa9","last_reissued_at":"2026-07-05T05:53:16.615497Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:53:16.615497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uncertainty-Aware Optimal Transport for Semantically Coherent Out-of-Distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fan Lu, Kai Zhu, Kecheng Zheng, Wei Zhai, Yang Cao","submitted_at":"2023-03-18T16:22:59Z","abstract_excerpt":"Semantically coherent out-of-distribution (SCOOD) detection aims to discern outliers from the intended data distribution with access to unlabeled extra set. The coexistence of in-distribution and out-of-distribution samples will exacerbate the model overfitting when no distinction is made. To address this problem, we propose a novel uncertainty-aware optimal transport scheme. Our scheme consists of an energy-based transport (ET) mechanism that estimates the fluctuating cost of uncertainty to promote the assignment of semantic-agnostic representation, and an inter-cluster extension strategy tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.10449","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/2303.10449/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":"2303.10449","created_at":"2026-07-05T05:53:16.615567+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.10449v2","created_at":"2026-07-05T05:53:16.615567+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.10449","created_at":"2026-07-05T05:53:16.615567+00:00"},{"alias_kind":"pith_short_12","alias_value":"52DSWRQJ5UAP","created_at":"2026-07-05T05:53:16.615567+00:00"},{"alias_kind":"pith_short_16","alias_value":"52DSWRQJ5UAPN3GP","created_at":"2026-07-05T05:53:16.615567+00:00"},{"alias_kind":"pith_short_8","alias_value":"52DSWRQJ","created_at":"2026-07-05T05:53:16.615567+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.16850","citing_title":"Toward a Real-Time Framework for Accurate Monocular 3D Human Pose Estimation with Geometric Priors","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/52DSWRQJ5UAPN3GP4CMDN7N5VF","json":"https://pith.science/pith/52DSWRQJ5UAPN3GP4CMDN7N5VF.json","graph_json":"https://pith.science/api/pith-number/52DSWRQJ5UAPN3GP4CMDN7N5VF/graph.json","events_json":"https://pith.science/api/pith-number/52DSWRQJ5UAPN3GP4CMDN7N5VF/events.json","paper":"https://pith.science/paper/52DSWRQJ"},"agent_actions":{"view_html":"https://pith.science/pith/52DSWRQJ5UAPN3GP4CMDN7N5VF","download_json":"https://pith.science/pith/52DSWRQJ5UAPN3GP4CMDN7N5VF.json","view_paper":"https://pith.science/paper/52DSWRQJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.10449&json=true","fetch_graph":"https://pith.science/api/pith-number/52DSWRQJ5UAPN3GP4CMDN7N5VF/graph.json","fetch_events":"https://pith.science/api/pith-number/52DSWRQJ5UAPN3GP4CMDN7N5VF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/52DSWRQJ5UAPN3GP4CMDN7N5VF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/52DSWRQJ5UAPN3GP4CMDN7N5VF/action/storage_attestation","attest_author":"https://pith.science/pith/52DSWRQJ5UAPN3GP4CMDN7N5VF/action/author_attestation","sign_citation":"https://pith.science/pith/52DSWRQJ5UAPN3GP4CMDN7N5VF/action/citation_signature","submit_replication":"https://pith.science/pith/52DSWRQJ5UAPN3GP4CMDN7N5VF/action/replication_record"}},"created_at":"2026-07-05T05:53:16.615567+00:00","updated_at":"2026-07-05T05:53:16.615567+00:00"}