{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:24DSEF2TOXLEHEXTKNVQBFRZG5","short_pith_number":"pith:24DSEF2T","schema_version":"1.0","canonical_sha256":"d70722175375d64392f3536b0096393750c9aefec60b178a2150695da6873d2e","source":{"kind":"arxiv","id":"2501.12204","version":1},"attestation_state":"computed","paper":{"title":"Score Combining for Contrastive OOD Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Edward T. Reehorst, Philip Schniter","submitted_at":"2025-01-21T15:20:22Z","abstract_excerpt":"In out-of-distribution (OOD) detection, one is asked to classify whether a test sample comes from a known inlier distribution or not. We focus on the case where the inlier distribution is defined by a training dataset and there exists no additional knowledge about the novelties that one is likely to encounter. This problem is also referred to as novelty detection, one-class classification, and unsupervised anomaly detection. The current literature suggests that contrastive learning techniques are state-of-the-art for OOD detection. We aim to improve on those techniques by combining/ensembling "},"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":"2501.12204","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-21T15:20:22Z","cross_cats_sorted":[],"title_canon_sha256":"f037156be72f689795c8f6f1d0d6d26a32230f339c5ca7d6a5e1fd6e5e42ba63","abstract_canon_sha256":"66ba339e907227e54eacd349bcc886d0d70a496334cffbb5b4f4469db306585a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:03:32.879019Z","signature_b64":"t5fL5+kYB4L+X7lo3gVVNY4wnDdsgHgQep5zM/10UXLjNmBRcNUYw+5RBPMPhXJi22WUUMw0PWEnShALvd+7BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d70722175375d64392f3536b0096393750c9aefec60b178a2150695da6873d2e","last_reissued_at":"2026-07-05T10:03:32.878667Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:03:32.878667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Score Combining for Contrastive OOD Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Edward T. Reehorst, Philip Schniter","submitted_at":"2025-01-21T15:20:22Z","abstract_excerpt":"In out-of-distribution (OOD) detection, one is asked to classify whether a test sample comes from a known inlier distribution or not. We focus on the case where the inlier distribution is defined by a training dataset and there exists no additional knowledge about the novelties that one is likely to encounter. This problem is also referred to as novelty detection, one-class classification, and unsupervised anomaly detection. The current literature suggests that contrastive learning techniques are state-of-the-art for OOD detection. We aim to improve on those techniques by combining/ensembling "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12204","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/2501.12204/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":"2501.12204","created_at":"2026-07-05T10:03:32.878729+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.12204v1","created_at":"2026-07-05T10:03:32.878729+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12204","created_at":"2026-07-05T10:03:32.878729+00:00"},{"alias_kind":"pith_short_12","alias_value":"24DSEF2TOXLE","created_at":"2026-07-05T10:03:32.878729+00:00"},{"alias_kind":"pith_short_16","alias_value":"24DSEF2TOXLEHEXT","created_at":"2026-07-05T10:03:32.878729+00:00"},{"alias_kind":"pith_short_8","alias_value":"24DSEF2T","created_at":"2026-07-05T10:03:32.878729+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/24DSEF2TOXLEHEXTKNVQBFRZG5","json":"https://pith.science/pith/24DSEF2TOXLEHEXTKNVQBFRZG5.json","graph_json":"https://pith.science/api/pith-number/24DSEF2TOXLEHEXTKNVQBFRZG5/graph.json","events_json":"https://pith.science/api/pith-number/24DSEF2TOXLEHEXTKNVQBFRZG5/events.json","paper":"https://pith.science/paper/24DSEF2T"},"agent_actions":{"view_html":"https://pith.science/pith/24DSEF2TOXLEHEXTKNVQBFRZG5","download_json":"https://pith.science/pith/24DSEF2TOXLEHEXTKNVQBFRZG5.json","view_paper":"https://pith.science/paper/24DSEF2T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.12204&json=true","fetch_graph":"https://pith.science/api/pith-number/24DSEF2TOXLEHEXTKNVQBFRZG5/graph.json","fetch_events":"https://pith.science/api/pith-number/24DSEF2TOXLEHEXTKNVQBFRZG5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/24DSEF2TOXLEHEXTKNVQBFRZG5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/24DSEF2TOXLEHEXTKNVQBFRZG5/action/storage_attestation","attest_author":"https://pith.science/pith/24DSEF2TOXLEHEXTKNVQBFRZG5/action/author_attestation","sign_citation":"https://pith.science/pith/24DSEF2TOXLEHEXTKNVQBFRZG5/action/citation_signature","submit_replication":"https://pith.science/pith/24DSEF2TOXLEHEXTKNVQBFRZG5/action/replication_record"}},"created_at":"2026-07-05T10:03:32.878729+00:00","updated_at":"2026-07-05T10:03:32.878729+00:00"}