{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LIY75RWV5ZSH4SXFKNJK4ENKWJ","short_pith_number":"pith:LIY75RWV","schema_version":"1.0","canonical_sha256":"5a31fec6d5ee647e4ae55352ae11aab26637b38d130d554badd2aeb2e19e60a4","source":{"kind":"arxiv","id":"2410.07185","version":1},"attestation_state":"computed","paper":{"title":"Margin-bounded Confidence Scores for Out-of-Distribution Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lakpa D. Tamang, Mohamed Reda Bouadjenek, Richard Dazeley, Sunil Aryal","submitted_at":"2024-09-22T05:40:25Z","abstract_excerpt":"In many critical Machine Learning applications, such as autonomous driving and medical image diagnosis, the detection of out-of-distribution (OOD) samples is as crucial as accurately classifying in-distribution (ID) inputs. Recently Outlier Exposure (OE) based methods have shown promising results in detecting OOD inputs via model fine-tuning with auxiliary outlier data. However, most of the previous OE-based approaches emphasize more on synthesizing extra outlier samples or introducing regularization to diversify OOD sample space, which is rather unquantifiable in practice. In this work, we pr"},"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":"2410.07185","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-22T05:40:25Z","cross_cats_sorted":[],"title_canon_sha256":"7b8e1fc3b3d9c6260b0c1a7f5b294576af03f07b2129dd32a83a9149db79c027","abstract_canon_sha256":"7d0c4f6d4cab5dc1c612d9ee1781f76a7629dafbacfaae14f3b93413e65d6f77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:12.152914Z","signature_b64":"5Tg6Hza57AHxoGNBJXQGSHINS/umU1XY2PKYADP4xAs75MvrpFTCELubygLY7vOUGHZvgJazZal2MW+ymgDWAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a31fec6d5ee647e4ae55352ae11aab26637b38d130d554badd2aeb2e19e60a4","last_reissued_at":"2026-07-05T09:18:12.152489Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:12.152489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Margin-bounded Confidence Scores for Out-of-Distribution Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lakpa D. Tamang, Mohamed Reda Bouadjenek, Richard Dazeley, Sunil Aryal","submitted_at":"2024-09-22T05:40:25Z","abstract_excerpt":"In many critical Machine Learning applications, such as autonomous driving and medical image diagnosis, the detection of out-of-distribution (OOD) samples is as crucial as accurately classifying in-distribution (ID) inputs. Recently Outlier Exposure (OE) based methods have shown promising results in detecting OOD inputs via model fine-tuning with auxiliary outlier data. However, most of the previous OE-based approaches emphasize more on synthesizing extra outlier samples or introducing regularization to diversify OOD sample space, which is rather unquantifiable in practice. In this work, we pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07185","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/2410.07185/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":"2410.07185","created_at":"2026-07-05T09:18:12.152545+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.07185v1","created_at":"2026-07-05T09:18:12.152545+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07185","created_at":"2026-07-05T09:18:12.152545+00:00"},{"alias_kind":"pith_short_12","alias_value":"LIY75RWV5ZSH","created_at":"2026-07-05T09:18:12.152545+00:00"},{"alias_kind":"pith_short_16","alias_value":"LIY75RWV5ZSH4SXF","created_at":"2026-07-05T09:18:12.152545+00:00"},{"alias_kind":"pith_short_8","alias_value":"LIY75RWV","created_at":"2026-07-05T09:18:12.152545+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/LIY75RWV5ZSH4SXFKNJK4ENKWJ","json":"https://pith.science/pith/LIY75RWV5ZSH4SXFKNJK4ENKWJ.json","graph_json":"https://pith.science/api/pith-number/LIY75RWV5ZSH4SXFKNJK4ENKWJ/graph.json","events_json":"https://pith.science/api/pith-number/LIY75RWV5ZSH4SXFKNJK4ENKWJ/events.json","paper":"https://pith.science/paper/LIY75RWV"},"agent_actions":{"view_html":"https://pith.science/pith/LIY75RWV5ZSH4SXFKNJK4ENKWJ","download_json":"https://pith.science/pith/LIY75RWV5ZSH4SXFKNJK4ENKWJ.json","view_paper":"https://pith.science/paper/LIY75RWV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.07185&json=true","fetch_graph":"https://pith.science/api/pith-number/LIY75RWV5ZSH4SXFKNJK4ENKWJ/graph.json","fetch_events":"https://pith.science/api/pith-number/LIY75RWV5ZSH4SXFKNJK4ENKWJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LIY75RWV5ZSH4SXFKNJK4ENKWJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LIY75RWV5ZSH4SXFKNJK4ENKWJ/action/storage_attestation","attest_author":"https://pith.science/pith/LIY75RWV5ZSH4SXFKNJK4ENKWJ/action/author_attestation","sign_citation":"https://pith.science/pith/LIY75RWV5ZSH4SXFKNJK4ENKWJ/action/citation_signature","submit_replication":"https://pith.science/pith/LIY75RWV5ZSH4SXFKNJK4ENKWJ/action/replication_record"}},"created_at":"2026-07-05T09:18:12.152545+00:00","updated_at":"2026-07-05T09:18:12.152545+00:00"}