{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FAN67UA6O7RB32BPU4QBDE26BN","short_pith_number":"pith:FAN67UA6","schema_version":"1.0","canonical_sha256":"281befd01e77e21de82fa72011935e0b4b96080c05f9a1f9ae4163233ee558c5","source":{"kind":"arxiv","id":"2412.11148","version":1},"attestation_state":"computed","paper":{"title":"Redefining Normal: A Novel Object-Level Approach for Multi-Object Novelty Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cees G. M. Snoek, Efstratios Gavves, Mohammadreza Salehi, Nikolaos Apostolikas, Yuki M. Asano","submitted_at":"2024-12-15T10:47:09Z","abstract_excerpt":"In the realm of novelty detection, accurately identifying outliers in data without specific class information poses a significant challenge. While current methods excel in single-object scenarios, they struggle with multi-object situations due to their focus on individual objects. Our paper suggests a novel approach: redefining `normal' at the object level in training datasets. Rather than the usual image-level view, we consider the most dominant object in a dataset as the norm, offering a perspective that is more effective for real-world scenarios. Adapting to our object-level definition of `"},"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":"2412.11148","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-15T10:47:09Z","cross_cats_sorted":[],"title_canon_sha256":"c3663656b4333283a7ea4e458e6be53bb44dd129dc5b858767e2dd4af7900fb6","abstract_canon_sha256":"d770c6fcd995ff24f966b938d3703f63293c03108336c69af3da1a6e0edac1bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:28.176565Z","signature_b64":"iL/2Z/zcp53TSvLr4Q++DKEmSjoayev+RF3CRtb3u8DzV15hZQ4MHGtljSlWKYvrrBi8pVK/o64C0h0gDXx2CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"281befd01e77e21de82fa72011935e0b4b96080c05f9a1f9ae4163233ee558c5","last_reissued_at":"2026-07-05T09:49:28.176176Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:28.176176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Redefining Normal: A Novel Object-Level Approach for Multi-Object Novelty Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cees G. M. Snoek, Efstratios Gavves, Mohammadreza Salehi, Nikolaos Apostolikas, Yuki M. Asano","submitted_at":"2024-12-15T10:47:09Z","abstract_excerpt":"In the realm of novelty detection, accurately identifying outliers in data without specific class information poses a significant challenge. While current methods excel in single-object scenarios, they struggle with multi-object situations due to their focus on individual objects. Our paper suggests a novel approach: redefining `normal' at the object level in training datasets. Rather than the usual image-level view, we consider the most dominant object in a dataset as the norm, offering a perspective that is more effective for real-world scenarios. Adapting to our object-level definition of `"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11148","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/2412.11148/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":"2412.11148","created_at":"2026-07-05T09:49:28.176231+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.11148v1","created_at":"2026-07-05T09:49:28.176231+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11148","created_at":"2026-07-05T09:49:28.176231+00:00"},{"alias_kind":"pith_short_12","alias_value":"FAN67UA6O7RB","created_at":"2026-07-05T09:49:28.176231+00:00"},{"alias_kind":"pith_short_16","alias_value":"FAN67UA6O7RB32BP","created_at":"2026-07-05T09:49:28.176231+00:00"},{"alias_kind":"pith_short_8","alias_value":"FAN67UA6","created_at":"2026-07-05T09:49:28.176231+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/FAN67UA6O7RB32BPU4QBDE26BN","json":"https://pith.science/pith/FAN67UA6O7RB32BPU4QBDE26BN.json","graph_json":"https://pith.science/api/pith-number/FAN67UA6O7RB32BPU4QBDE26BN/graph.json","events_json":"https://pith.science/api/pith-number/FAN67UA6O7RB32BPU4QBDE26BN/events.json","paper":"https://pith.science/paper/FAN67UA6"},"agent_actions":{"view_html":"https://pith.science/pith/FAN67UA6O7RB32BPU4QBDE26BN","download_json":"https://pith.science/pith/FAN67UA6O7RB32BPU4QBDE26BN.json","view_paper":"https://pith.science/paper/FAN67UA6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.11148&json=true","fetch_graph":"https://pith.science/api/pith-number/FAN67UA6O7RB32BPU4QBDE26BN/graph.json","fetch_events":"https://pith.science/api/pith-number/FAN67UA6O7RB32BPU4QBDE26BN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FAN67UA6O7RB32BPU4QBDE26BN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FAN67UA6O7RB32BPU4QBDE26BN/action/storage_attestation","attest_author":"https://pith.science/pith/FAN67UA6O7RB32BPU4QBDE26BN/action/author_attestation","sign_citation":"https://pith.science/pith/FAN67UA6O7RB32BPU4QBDE26BN/action/citation_signature","submit_replication":"https://pith.science/pith/FAN67UA6O7RB32BPU4QBDE26BN/action/replication_record"}},"created_at":"2026-07-05T09:49:28.176231+00:00","updated_at":"2026-07-05T09:49:28.176231+00:00"}