{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:T2E7ROG6YCUBB2AFXPPYEXWXOM","short_pith_number":"pith:T2E7ROG6","schema_version":"1.0","canonical_sha256":"9e89f8b8dec0a810e805bbdf825ed7733f0171dd8877b9f6ea389b8aec49082c","source":{"kind":"arxiv","id":"2412.15668","version":2},"attestation_state":"computed","paper":{"title":"Adaptive Hierarchical Graph Cut for Multi-granularity Out-of-distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arvind Easwaran, Blaise Genest, Ponnuthurai Nagaratnam Suganthan, Xiang Fang","submitted_at":"2024-12-20T08:32:02Z","abstract_excerpt":"This paper focuses on a significant yet challenging task: out-of-distribution detection (OOD detection), which aims to distinguish and reject test samples with semantic shifts, so as to prevent models trained on in-distribution (ID) data from producing unreliable predictions. Although previous works have made decent success, they are ineffective for real-world challenging applications since these methods simply regard all unlabeled data as OOD data and ignore the case that different datasets have different label granularity. For example, \"cat\" on CIFAR-10 and \"tabby cat\" on Tiny-ImageNet share"},"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":"2412.15668","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-20T08:32:02Z","cross_cats_sorted":[],"title_canon_sha256":"acad3fde1c65ff230bf94162de7e74981d7731a4a1193dcf8167d350b48081a1","abstract_canon_sha256":"211b07ba5d236603e5ef9d46151cfe9e5451e9bc9716d42561478ede7bdee225"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:04:59.331106Z","signature_b64":"ayCGarpa28/aj9RutoH1GAN7iP+SvFEOPMMD+qx/f2aMtjMBxbM4QPf3UUh3aZ13GvFFwZeLHpg1QdiInWyvAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e89f8b8dec0a810e805bbdf825ed7733f0171dd8877b9f6ea389b8aec49082c","last_reissued_at":"2026-05-26T02:04:59.330286Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:04:59.330286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Hierarchical Graph Cut for Multi-granularity Out-of-distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arvind Easwaran, Blaise Genest, Ponnuthurai Nagaratnam Suganthan, Xiang Fang","submitted_at":"2024-12-20T08:32:02Z","abstract_excerpt":"This paper focuses on a significant yet challenging task: out-of-distribution detection (OOD detection), which aims to distinguish and reject test samples with semantic shifts, so as to prevent models trained on in-distribution (ID) data from producing unreliable predictions. Although previous works have made decent success, they are ineffective for real-world challenging applications since these methods simply regard all unlabeled data as OOD data and ignore the case that different datasets have different label granularity. For example, \"cat\" on CIFAR-10 and \"tabby cat\" on Tiny-ImageNet share"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15668","kind":"arxiv","version":2},"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/2412.15668/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":"2412.15668","created_at":"2026-05-26T02:04:59.330429+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.15668v2","created_at":"2026-05-26T02:04:59.330429+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15668","created_at":"2026-05-26T02:04:59.330429+00:00"},{"alias_kind":"pith_short_12","alias_value":"T2E7ROG6YCUB","created_at":"2026-05-26T02:04:59.330429+00:00"},{"alias_kind":"pith_short_16","alias_value":"T2E7ROG6YCUBB2AF","created_at":"2026-05-26T02:04:59.330429+00:00"},{"alias_kind":"pith_short_8","alias_value":"T2E7ROG6","created_at":"2026-05-26T02:04:59.330429+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/T2E7ROG6YCUBB2AFXPPYEXWXOM","json":"https://pith.science/pith/T2E7ROG6YCUBB2AFXPPYEXWXOM.json","graph_json":"https://pith.science/api/pith-number/T2E7ROG6YCUBB2AFXPPYEXWXOM/graph.json","events_json":"https://pith.science/api/pith-number/T2E7ROG6YCUBB2AFXPPYEXWXOM/events.json","paper":"https://pith.science/paper/T2E7ROG6"},"agent_actions":{"view_html":"https://pith.science/pith/T2E7ROG6YCUBB2AFXPPYEXWXOM","download_json":"https://pith.science/pith/T2E7ROG6YCUBB2AFXPPYEXWXOM.json","view_paper":"https://pith.science/paper/T2E7ROG6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.15668&json=true","fetch_graph":"https://pith.science/api/pith-number/T2E7ROG6YCUBB2AFXPPYEXWXOM/graph.json","fetch_events":"https://pith.science/api/pith-number/T2E7ROG6YCUBB2AFXPPYEXWXOM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T2E7ROG6YCUBB2AFXPPYEXWXOM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T2E7ROG6YCUBB2AFXPPYEXWXOM/action/storage_attestation","attest_author":"https://pith.science/pith/T2E7ROG6YCUBB2AFXPPYEXWXOM/action/author_attestation","sign_citation":"https://pith.science/pith/T2E7ROG6YCUBB2AFXPPYEXWXOM/action/citation_signature","submit_replication":"https://pith.science/pith/T2E7ROG6YCUBB2AFXPPYEXWXOM/action/replication_record"}},"created_at":"2026-05-26T02:04:59.330429+00:00","updated_at":"2026-05-26T02:04:59.330429+00:00"}