{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KYH36PTQDXQTIQORKRNCRUGVR6","short_pith_number":"pith:KYH36PTQ","schema_version":"1.0","canonical_sha256":"560fbf3e701de13441d1545a28d0d58f9d6904321049b51239174c14871faa72","source":{"kind":"arxiv","id":"2506.14194","version":1},"attestation_state":"computed","paper":{"title":"A Variational Information Theoretic Approach to Out-of-Distribution Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ganesh Sundaramoorthi, Sudeepta Mondal, Zhuolin Jiang","submitted_at":"2025-06-17T05:17:36Z","abstract_excerpt":"We present a theory for the construction of out-of-distribution (OOD) detection features for neural networks. We introduce random features for OOD through a novel information-theoretic loss functional consisting of two terms, the first based on the KL divergence separates resulting in-distribution (ID) and OOD feature distributions and the second term is the Information Bottleneck, which favors compressed features that retain the OOD information. We formulate a variational procedure to optimize the loss and obtain OOD features. Based on assumptions on OOD distributions, one can recover propert"},"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":"2506.14194","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-17T05:17:36Z","cross_cats_sorted":[],"title_canon_sha256":"29c9ac1afc70fb664a1c6469c6248a666d72feb1d94f26d44d4041bd08874df5","abstract_canon_sha256":"81a70b1d0a635ed12e607a2523d6d20ff68ff719233f95999f9bfd4f2585799f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:50.597362Z","signature_b64":"xIvuVMFYRasTq8npeCtkVjYq1NPh/5NYgLNnMnNeKbqJyObbdpUdHC/C7u00qZufw7AuKHV2+eX3NgRdqZuvDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"560fbf3e701de13441d1545a28d0d58f9d6904321049b51239174c14871faa72","last_reissued_at":"2026-07-05T11:22:50.596907Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:50.596907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Variational Information Theoretic Approach to Out-of-Distribution Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ganesh Sundaramoorthi, Sudeepta Mondal, Zhuolin Jiang","submitted_at":"2025-06-17T05:17:36Z","abstract_excerpt":"We present a theory for the construction of out-of-distribution (OOD) detection features for neural networks. We introduce random features for OOD through a novel information-theoretic loss functional consisting of two terms, the first based on the KL divergence separates resulting in-distribution (ID) and OOD feature distributions and the second term is the Information Bottleneck, which favors compressed features that retain the OOD information. We formulate a variational procedure to optimize the loss and obtain OOD features. Based on assumptions on OOD distributions, one can recover propert"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14194","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/2506.14194/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":"2506.14194","created_at":"2026-07-05T11:22:50.596960+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.14194v1","created_at":"2026-07-05T11:22:50.596960+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14194","created_at":"2026-07-05T11:22:50.596960+00:00"},{"alias_kind":"pith_short_12","alias_value":"KYH36PTQDXQT","created_at":"2026-07-05T11:22:50.596960+00:00"},{"alias_kind":"pith_short_16","alias_value":"KYH36PTQDXQTIQOR","created_at":"2026-07-05T11:22:50.596960+00:00"},{"alias_kind":"pith_short_8","alias_value":"KYH36PTQ","created_at":"2026-07-05T11:22:50.596960+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12718","citing_title":"Out-of-Distribution (OOD) Detectors for Open-Set RF Fingerprinting","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KYH36PTQDXQTIQORKRNCRUGVR6","json":"https://pith.science/pith/KYH36PTQDXQTIQORKRNCRUGVR6.json","graph_json":"https://pith.science/api/pith-number/KYH36PTQDXQTIQORKRNCRUGVR6/graph.json","events_json":"https://pith.science/api/pith-number/KYH36PTQDXQTIQORKRNCRUGVR6/events.json","paper":"https://pith.science/paper/KYH36PTQ"},"agent_actions":{"view_html":"https://pith.science/pith/KYH36PTQDXQTIQORKRNCRUGVR6","download_json":"https://pith.science/pith/KYH36PTQDXQTIQORKRNCRUGVR6.json","view_paper":"https://pith.science/paper/KYH36PTQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.14194&json=true","fetch_graph":"https://pith.science/api/pith-number/KYH36PTQDXQTIQORKRNCRUGVR6/graph.json","fetch_events":"https://pith.science/api/pith-number/KYH36PTQDXQTIQORKRNCRUGVR6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KYH36PTQDXQTIQORKRNCRUGVR6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KYH36PTQDXQTIQORKRNCRUGVR6/action/storage_attestation","attest_author":"https://pith.science/pith/KYH36PTQDXQTIQORKRNCRUGVR6/action/author_attestation","sign_citation":"https://pith.science/pith/KYH36PTQDXQTIQORKRNCRUGVR6/action/citation_signature","submit_replication":"https://pith.science/pith/KYH36PTQDXQTIQORKRNCRUGVR6/action/replication_record"}},"created_at":"2026-07-05T11:22:50.596960+00:00","updated_at":"2026-07-05T11:22:50.596960+00:00"}