{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:64CEJDRQQG27MKAVLTQ7OYUUDT","short_pith_number":"pith:64CEJDRQ","schema_version":"1.0","canonical_sha256":"f704448e3081b5f628155ce1f762941cdf3b6fd4afedf0a3aaad894207fc5a2c","source":{"kind":"arxiv","id":"2408.10107","version":1},"attestation_state":"computed","paper":{"title":"Perturb-and-Compare Approach for Detecting Out-of-Distribution Samples in Constrained Access Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Changdae Oh, Heeyoung Lee, Hoyoon Byun, JinYeong Bak, Kyungwoo Song","submitted_at":"2024-08-19T15:51:31Z","abstract_excerpt":"Accessing machine learning models through remote APIs has been gaining prevalence following the recent trend of scaling up model parameters for increased performance. Even though these models exhibit remarkable ability, detecting out-of-distribution (OOD) samples remains a crucial safety concern for end users as these samples may induce unreliable outputs from the model. In this work, we propose an OOD detection framework, MixDiff, that is applicable even when the model's parameters or its activations are not accessible to the end user. To bypass the access restriction, MixDiff applies an iden"},"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":"2408.10107","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-19T15:51:31Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"4e6f5929b026113d1e0b8e51ba9de39c27e2f3aeec7ed1581d16c1b15cd77f60","abstract_canon_sha256":"59fda38e96f9d63462c6fb5c19870c2b24ff01e4cf8bffa819bce292e1d6e1a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:51.430847Z","signature_b64":"B+LF61293ZDctVzx1KfWwXd75vZYf6YOtrmP/sdVMSgdA4SxbcILN135Nl7DNXUWZQH+PlOKB8IxUVVtN53xCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f704448e3081b5f628155ce1f762941cdf3b6fd4afedf0a3aaad894207fc5a2c","last_reissued_at":"2026-07-05T08:56:51.430405Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:51.430405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Perturb-and-Compare Approach for Detecting Out-of-Distribution Samples in Constrained Access Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Changdae Oh, Heeyoung Lee, Hoyoon Byun, JinYeong Bak, Kyungwoo Song","submitted_at":"2024-08-19T15:51:31Z","abstract_excerpt":"Accessing machine learning models through remote APIs has been gaining prevalence following the recent trend of scaling up model parameters for increased performance. Even though these models exhibit remarkable ability, detecting out-of-distribution (OOD) samples remains a crucial safety concern for end users as these samples may induce unreliable outputs from the model. In this work, we propose an OOD detection framework, MixDiff, that is applicable even when the model's parameters or its activations are not accessible to the end user. To bypass the access restriction, MixDiff applies an iden"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10107","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/2408.10107/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":"2408.10107","created_at":"2026-07-05T08:56:51.430461+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.10107v1","created_at":"2026-07-05T08:56:51.430461+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10107","created_at":"2026-07-05T08:56:51.430461+00:00"},{"alias_kind":"pith_short_12","alias_value":"64CEJDRQQG27","created_at":"2026-07-05T08:56:51.430461+00:00"},{"alias_kind":"pith_short_16","alias_value":"64CEJDRQQG27MKAV","created_at":"2026-07-05T08:56:51.430461+00:00"},{"alias_kind":"pith_short_8","alias_value":"64CEJDRQ","created_at":"2026-07-05T08:56:51.430461+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/64CEJDRQQG27MKAVLTQ7OYUUDT","json":"https://pith.science/pith/64CEJDRQQG27MKAVLTQ7OYUUDT.json","graph_json":"https://pith.science/api/pith-number/64CEJDRQQG27MKAVLTQ7OYUUDT/graph.json","events_json":"https://pith.science/api/pith-number/64CEJDRQQG27MKAVLTQ7OYUUDT/events.json","paper":"https://pith.science/paper/64CEJDRQ"},"agent_actions":{"view_html":"https://pith.science/pith/64CEJDRQQG27MKAVLTQ7OYUUDT","download_json":"https://pith.science/pith/64CEJDRQQG27MKAVLTQ7OYUUDT.json","view_paper":"https://pith.science/paper/64CEJDRQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.10107&json=true","fetch_graph":"https://pith.science/api/pith-number/64CEJDRQQG27MKAVLTQ7OYUUDT/graph.json","fetch_events":"https://pith.science/api/pith-number/64CEJDRQQG27MKAVLTQ7OYUUDT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/64CEJDRQQG27MKAVLTQ7OYUUDT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/64CEJDRQQG27MKAVLTQ7OYUUDT/action/storage_attestation","attest_author":"https://pith.science/pith/64CEJDRQQG27MKAVLTQ7OYUUDT/action/author_attestation","sign_citation":"https://pith.science/pith/64CEJDRQQG27MKAVLTQ7OYUUDT/action/citation_signature","submit_replication":"https://pith.science/pith/64CEJDRQQG27MKAVLTQ7OYUUDT/action/replication_record"}},"created_at":"2026-07-05T08:56:51.430461+00:00","updated_at":"2026-07-05T08:56:51.430461+00:00"}