{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BUEMZUD6YPEZF447RHBHWP6HCD","short_pith_number":"pith:BUEMZUD6","schema_version":"1.0","canonical_sha256":"0d08ccd07ec3c992f39f89c27b3fc710e369f579a9e3139fd424d5bb766a1b78","source":{"kind":"arxiv","id":"2303.14531","version":1},"attestation_state":"computed","paper":{"title":"SIO: Synthetic In-Distribution Data Benefits Out-of-Distribution Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hai Li, Jingyang Zhang, Nathan Inkawhich, Randolph Linderman, Ryan Luley, Yiran Chen","submitted_at":"2023-03-25T18:34:34Z","abstract_excerpt":"Building up reliable Out-of-Distribution (OOD) detectors is challenging, often requiring the use of OOD data during training. In this work, we develop a data-driven approach which is distinct and complementary to existing works: Instead of using external OOD data, we fully exploit the internal in-distribution (ID) training set by utilizing generative models to produce additional synthetic ID images. The classifier is then trained using a novel objective that computes weighted loss on real and synthetic ID samples together. Our training framework, which is termed SIO, serves as a \"plug-and-play"},"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":"2303.14531","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-25T18:34:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"839dfbfb6e2ef95d626c0bd3042d4845be13e2cc48cffa5a34d9377ebfb5f32e","abstract_canon_sha256":"d3f7069551207b9c00f929c05a24d299788c2f11a78c568f118de28a1bc23432"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:43.052228Z","signature_b64":"peOK/DaCUuEZ65nrGxPQR/GssytL5j3G7YdjaVxVtOJjB77uJ6QX2reySKqzZkS3FUEL8R7Mz0NesZFvr9MICg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d08ccd07ec3c992f39f89c27b3fc710e369f579a9e3139fd424d5bb766a1b78","last_reissued_at":"2026-07-05T05:54:43.051893Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:43.051893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SIO: Synthetic In-Distribution Data Benefits Out-of-Distribution Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hai Li, Jingyang Zhang, Nathan Inkawhich, Randolph Linderman, Ryan Luley, Yiran Chen","submitted_at":"2023-03-25T18:34:34Z","abstract_excerpt":"Building up reliable Out-of-Distribution (OOD) detectors is challenging, often requiring the use of OOD data during training. In this work, we develop a data-driven approach which is distinct and complementary to existing works: Instead of using external OOD data, we fully exploit the internal in-distribution (ID) training set by utilizing generative models to produce additional synthetic ID images. The classifier is then trained using a novel objective that computes weighted loss on real and synthetic ID samples together. Our training framework, which is termed SIO, serves as a \"plug-and-play"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.14531","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/2303.14531/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":"2303.14531","created_at":"2026-07-05T05:54:43.051947+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.14531v1","created_at":"2026-07-05T05:54:43.051947+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.14531","created_at":"2026-07-05T05:54:43.051947+00:00"},{"alias_kind":"pith_short_12","alias_value":"BUEMZUD6YPEZ","created_at":"2026-07-05T05:54:43.051947+00:00"},{"alias_kind":"pith_short_16","alias_value":"BUEMZUD6YPEZF447","created_at":"2026-07-05T05:54:43.051947+00:00"},{"alias_kind":"pith_short_8","alias_value":"BUEMZUD6","created_at":"2026-07-05T05:54:43.051947+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/BUEMZUD6YPEZF447RHBHWP6HCD","json":"https://pith.science/pith/BUEMZUD6YPEZF447RHBHWP6HCD.json","graph_json":"https://pith.science/api/pith-number/BUEMZUD6YPEZF447RHBHWP6HCD/graph.json","events_json":"https://pith.science/api/pith-number/BUEMZUD6YPEZF447RHBHWP6HCD/events.json","paper":"https://pith.science/paper/BUEMZUD6"},"agent_actions":{"view_html":"https://pith.science/pith/BUEMZUD6YPEZF447RHBHWP6HCD","download_json":"https://pith.science/pith/BUEMZUD6YPEZF447RHBHWP6HCD.json","view_paper":"https://pith.science/paper/BUEMZUD6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.14531&json=true","fetch_graph":"https://pith.science/api/pith-number/BUEMZUD6YPEZF447RHBHWP6HCD/graph.json","fetch_events":"https://pith.science/api/pith-number/BUEMZUD6YPEZF447RHBHWP6HCD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BUEMZUD6YPEZF447RHBHWP6HCD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BUEMZUD6YPEZF447RHBHWP6HCD/action/storage_attestation","attest_author":"https://pith.science/pith/BUEMZUD6YPEZF447RHBHWP6HCD/action/author_attestation","sign_citation":"https://pith.science/pith/BUEMZUD6YPEZF447RHBHWP6HCD/action/citation_signature","submit_replication":"https://pith.science/pith/BUEMZUD6YPEZF447RHBHWP6HCD/action/replication_record"}},"created_at":"2026-07-05T05:54:43.051947+00:00","updated_at":"2026-07-05T05:54:43.051947+00:00"}