{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7AGJ6DQKOR5BQFACVOJIKQM6B7","short_pith_number":"pith:7AGJ6DQK","schema_version":"1.0","canonical_sha256":"f80c9f0e0a747a181402ab9285419e0fd6597270a7eee2afb3aa750b78ef1152","source":{"kind":"arxiv","id":"2309.13415","version":1},"attestation_state":"computed","paper":{"title":"Dream the Impossible: Outlier Imagination with Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Xiaojin Zhu, Xuefeng Du, Yixuan Li, Yiyou Sun","submitted_at":"2023-09-23T15:58:27Z","abstract_excerpt":"Utilizing auxiliary outlier datasets to regularize the machine learning model has demonstrated promise for out-of-distribution (OOD) detection and safe prediction. Due to the labor intensity in data collection and cleaning, automating outlier data generation has been a long-desired alternative. Despite the appeal, generating photo-realistic outliers in the high dimensional pixel space has been an open challenge for the field. To tackle the problem, this paper proposes a new framework DREAM-OOD, which enables imagining photo-realistic outliers by way of diffusion models, provided with only the "},"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":"2309.13415","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-23T15:58:27Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"f91226c5f3da4d7f5a2d38ac2befda0c152c521a82a81cfe412d08ec92e62541","abstract_canon_sha256":"92bd18538c83b0585374bea505e24c8cd08ba3503eabd17b6418f0e4d0ac80a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:53:52.467818Z","signature_b64":"0NrDASdAzut+6VC9f/yTVhfWJL6z5AvH3vSMVI4ZLGqIs52UMXBWsJWepYJpkUyI2uG0RcqMVMd/GxhcYlxEDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f80c9f0e0a747a181402ab9285419e0fd6597270a7eee2afb3aa750b78ef1152","last_reissued_at":"2026-07-05T06:53:52.467397Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:53:52.467397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dream the Impossible: Outlier Imagination with Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Xiaojin Zhu, Xuefeng Du, Yixuan Li, Yiyou Sun","submitted_at":"2023-09-23T15:58:27Z","abstract_excerpt":"Utilizing auxiliary outlier datasets to regularize the machine learning model has demonstrated promise for out-of-distribution (OOD) detection and safe prediction. Due to the labor intensity in data collection and cleaning, automating outlier data generation has been a long-desired alternative. Despite the appeal, generating photo-realistic outliers in the high dimensional pixel space has been an open challenge for the field. To tackle the problem, this paper proposes a new framework DREAM-OOD, which enables imagining photo-realistic outliers by way of diffusion models, provided with only the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.13415","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/2309.13415/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":"2309.13415","created_at":"2026-07-05T06:53:52.467457+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.13415v1","created_at":"2026-07-05T06:53:52.467457+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.13415","created_at":"2026-07-05T06:53:52.467457+00:00"},{"alias_kind":"pith_short_12","alias_value":"7AGJ6DQKOR5B","created_at":"2026-07-05T06:53:52.467457+00:00"},{"alias_kind":"pith_short_16","alias_value":"7AGJ6DQKOR5BQFAC","created_at":"2026-07-05T06:53:52.467457+00:00"},{"alias_kind":"pith_short_8","alias_value":"7AGJ6DQK","created_at":"2026-07-05T06:53:52.467457+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.16971","citing_title":"RODEO: Robust Outlier Detection via Exposing Adaptive Out-of-Distribution Samples","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7AGJ6DQKOR5BQFACVOJIKQM6B7","json":"https://pith.science/pith/7AGJ6DQKOR5BQFACVOJIKQM6B7.json","graph_json":"https://pith.science/api/pith-number/7AGJ6DQKOR5BQFACVOJIKQM6B7/graph.json","events_json":"https://pith.science/api/pith-number/7AGJ6DQKOR5BQFACVOJIKQM6B7/events.json","paper":"https://pith.science/paper/7AGJ6DQK"},"agent_actions":{"view_html":"https://pith.science/pith/7AGJ6DQKOR5BQFACVOJIKQM6B7","download_json":"https://pith.science/pith/7AGJ6DQKOR5BQFACVOJIKQM6B7.json","view_paper":"https://pith.science/paper/7AGJ6DQK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.13415&json=true","fetch_graph":"https://pith.science/api/pith-number/7AGJ6DQKOR5BQFACVOJIKQM6B7/graph.json","fetch_events":"https://pith.science/api/pith-number/7AGJ6DQKOR5BQFACVOJIKQM6B7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7AGJ6DQKOR5BQFACVOJIKQM6B7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7AGJ6DQKOR5BQFACVOJIKQM6B7/action/storage_attestation","attest_author":"https://pith.science/pith/7AGJ6DQKOR5BQFACVOJIKQM6B7/action/author_attestation","sign_citation":"https://pith.science/pith/7AGJ6DQKOR5BQFACVOJIKQM6B7/action/citation_signature","submit_replication":"https://pith.science/pith/7AGJ6DQKOR5BQFACVOJIKQM6B7/action/replication_record"}},"created_at":"2026-07-05T06:53:52.467457+00:00","updated_at":"2026-07-05T06:53:52.467457+00:00"}