{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:F222RL77XY47FIYCR5FHBXX3BD","short_pith_number":"pith:F222RL77","schema_version":"1.0","canonical_sha256":"2eb5a8afffbe39f2a3028f4a70defb08d9181c1437c1cd196693b6a4ff191257","source":{"kind":"arxiv","id":"2409.12479","version":1},"attestation_state":"computed","paper":{"title":"Learning Multi-Manifold Embedding for Out-Of-Distribution Detection","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Jeng-Lin Li, Ming-Ching Chang, Wei-Chao Chen","submitted_at":"2024-09-19T05:43:00Z","abstract_excerpt":"Detecting out-of-distribution (OOD) samples is crucial for trustworthy AI in real-world applications. Leveraging recent advances in representation learning and latent embeddings, Various scoring algorithms estimate distributions beyond the training data. However, a single embedding space falls short in characterizing in-distribution data and defending against diverse OOD conditions. This paper introduces a novel Multi-Manifold Embedding Learning (MMEL) framework, optimizing hypersphere and hyperbolic spaces jointly for enhanced OOD detection. MMEL generates representative embeddings and employ"},"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":"2409.12479","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-19T05:43:00Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"bfe7572c92e1fb6578552ecff950151f779a26402780b505a505bd07b4006919","abstract_canon_sha256":"4a9cd573f8b3105b1e8a79dfc3102c72710918de2c8c4b09e9107444f5a3aa4b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:07.587369Z","signature_b64":"sA7feqkmpCztHg7EYsvWn2kLz/Ld1LRcJNikJlbFS0V0FF0d+rTj0fw1Gb2YKWlkCuwSFtE2TCxlHyQgWdfxBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2eb5a8afffbe39f2a3028f4a70defb08d9181c1437c1cd196693b6a4ff191257","last_reissued_at":"2026-07-05T09:09:07.586935Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:07.586935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Multi-Manifold Embedding for Out-Of-Distribution Detection","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Jeng-Lin Li, Ming-Ching Chang, Wei-Chao Chen","submitted_at":"2024-09-19T05:43:00Z","abstract_excerpt":"Detecting out-of-distribution (OOD) samples is crucial for trustworthy AI in real-world applications. Leveraging recent advances in representation learning and latent embeddings, Various scoring algorithms estimate distributions beyond the training data. However, a single embedding space falls short in characterizing in-distribution data and defending against diverse OOD conditions. This paper introduces a novel Multi-Manifold Embedding Learning (MMEL) framework, optimizing hypersphere and hyperbolic spaces jointly for enhanced OOD detection. MMEL generates representative embeddings and employ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.12479","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/2409.12479/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":"2409.12479","created_at":"2026-07-05T09:09:07.586995+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.12479v1","created_at":"2026-07-05T09:09:07.586995+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.12479","created_at":"2026-07-05T09:09:07.586995+00:00"},{"alias_kind":"pith_short_12","alias_value":"F222RL77XY47","created_at":"2026-07-05T09:09:07.586995+00:00"},{"alias_kind":"pith_short_16","alias_value":"F222RL77XY47FIYC","created_at":"2026-07-05T09:09:07.586995+00:00"},{"alias_kind":"pith_short_8","alias_value":"F222RL77","created_at":"2026-07-05T09:09:07.586995+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/F222RL77XY47FIYCR5FHBXX3BD","json":"https://pith.science/pith/F222RL77XY47FIYCR5FHBXX3BD.json","graph_json":"https://pith.science/api/pith-number/F222RL77XY47FIYCR5FHBXX3BD/graph.json","events_json":"https://pith.science/api/pith-number/F222RL77XY47FIYCR5FHBXX3BD/events.json","paper":"https://pith.science/paper/F222RL77"},"agent_actions":{"view_html":"https://pith.science/pith/F222RL77XY47FIYCR5FHBXX3BD","download_json":"https://pith.science/pith/F222RL77XY47FIYCR5FHBXX3BD.json","view_paper":"https://pith.science/paper/F222RL77","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.12479&json=true","fetch_graph":"https://pith.science/api/pith-number/F222RL77XY47FIYCR5FHBXX3BD/graph.json","fetch_events":"https://pith.science/api/pith-number/F222RL77XY47FIYCR5FHBXX3BD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F222RL77XY47FIYCR5FHBXX3BD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F222RL77XY47FIYCR5FHBXX3BD/action/storage_attestation","attest_author":"https://pith.science/pith/F222RL77XY47FIYCR5FHBXX3BD/action/author_attestation","sign_citation":"https://pith.science/pith/F222RL77XY47FIYCR5FHBXX3BD/action/citation_signature","submit_replication":"https://pith.science/pith/F222RL77XY47FIYCR5FHBXX3BD/action/replication_record"}},"created_at":"2026-07-05T09:09:07.586995+00:00","updated_at":"2026-07-05T09:09:07.586995+00:00"}