{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:V6CA3VNQJ6R35G4LLTVIM76GXZ","short_pith_number":"pith:V6CA3VNQ","schema_version":"1.0","canonical_sha256":"af840dd5b04fa3be9b8b5cea867fc6be543e35feb832938fdfdfe3e4dffe22a8","source":{"kind":"arxiv","id":"2310.00227","version":1},"attestation_state":"computed","paper":{"title":"Scaling for Training Time and Post-hoc Out-of-distribution Detection Enhancement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Angela Yao, Gianni Franchi, Kai Xu, Rongyu Chen","submitted_at":"2023-09-30T02:10:54Z","abstract_excerpt":"The capacity of a modern deep learning system to determine if a sample falls within its realm of knowledge is fundamental and important. In this paper, we offer insights and analyses of recent state-of-the-art out-of-distribution (OOD) detection methods - extremely simple activation shaping (ASH). We demonstrate that activation pruning has a detrimental effect on OOD detection, while activation scaling enhances it. Moreover, we propose SCALE, a simple yet effective post-hoc network enhancement method for OOD detection, which attains state-of-the-art OOD detection performance without compromisi"},"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":"2310.00227","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-30T02:10:54Z","cross_cats_sorted":[],"title_canon_sha256":"ecb56ee260de63d918f19aaa09a39fa27ceac01c0cb178a6f1e9ee881fcad789","abstract_canon_sha256":"4975a0e30022a29550f1465431c6ff2a9533959c5ccb10b8797a50a4410cb8a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:56:03.104599Z","signature_b64":"2KCQTGauGqj4cnhN6oboU9PbH6ixkCEUK3L4eKQD+OkLFAG2R/O5BzBTUMAKn+F9KDN1O3Ihij7ZsNFt+wx3Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af840dd5b04fa3be9b8b5cea867fc6be543e35feb832938fdfdfe3e4dffe22a8","last_reissued_at":"2026-07-05T06:56:03.104105Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:56:03.104105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling for Training Time and Post-hoc Out-of-distribution Detection Enhancement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Angela Yao, Gianni Franchi, Kai Xu, Rongyu Chen","submitted_at":"2023-09-30T02:10:54Z","abstract_excerpt":"The capacity of a modern deep learning system to determine if a sample falls within its realm of knowledge is fundamental and important. In this paper, we offer insights and analyses of recent state-of-the-art out-of-distribution (OOD) detection methods - extremely simple activation shaping (ASH). We demonstrate that activation pruning has a detrimental effect on OOD detection, while activation scaling enhances it. Moreover, we propose SCALE, a simple yet effective post-hoc network enhancement method for OOD detection, which attains state-of-the-art OOD detection performance without compromisi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.00227","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/2310.00227/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":"2310.00227","created_at":"2026-07-05T06:56:03.104164+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.00227v1","created_at":"2026-07-05T06:56:03.104164+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.00227","created_at":"2026-07-05T06:56:03.104164+00:00"},{"alias_kind":"pith_short_12","alias_value":"V6CA3VNQJ6R3","created_at":"2026-07-05T06:56:03.104164+00:00"},{"alias_kind":"pith_short_16","alias_value":"V6CA3VNQJ6R35G4L","created_at":"2026-07-05T06:56:03.104164+00:00"},{"alias_kind":"pith_short_8","alias_value":"V6CA3VNQ","created_at":"2026-07-05T06:56:03.104164+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05536","citing_title":"Dual Feature Decoupling for Fine-Grained OOD Detection","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V6CA3VNQJ6R35G4LLTVIM76GXZ","json":"https://pith.science/pith/V6CA3VNQJ6R35G4LLTVIM76GXZ.json","graph_json":"https://pith.science/api/pith-number/V6CA3VNQJ6R35G4LLTVIM76GXZ/graph.json","events_json":"https://pith.science/api/pith-number/V6CA3VNQJ6R35G4LLTVIM76GXZ/events.json","paper":"https://pith.science/paper/V6CA3VNQ"},"agent_actions":{"view_html":"https://pith.science/pith/V6CA3VNQJ6R35G4LLTVIM76GXZ","download_json":"https://pith.science/pith/V6CA3VNQJ6R35G4LLTVIM76GXZ.json","view_paper":"https://pith.science/paper/V6CA3VNQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.00227&json=true","fetch_graph":"https://pith.science/api/pith-number/V6CA3VNQJ6R35G4LLTVIM76GXZ/graph.json","fetch_events":"https://pith.science/api/pith-number/V6CA3VNQJ6R35G4LLTVIM76GXZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V6CA3VNQJ6R35G4LLTVIM76GXZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V6CA3VNQJ6R35G4LLTVIM76GXZ/action/storage_attestation","attest_author":"https://pith.science/pith/V6CA3VNQJ6R35G4LLTVIM76GXZ/action/author_attestation","sign_citation":"https://pith.science/pith/V6CA3VNQJ6R35G4LLTVIM76GXZ/action/citation_signature","submit_replication":"https://pith.science/pith/V6CA3VNQJ6R35G4LLTVIM76GXZ/action/replication_record"}},"created_at":"2026-07-05T06:56:03.104164+00:00","updated_at":"2026-07-05T06:56:03.104164+00:00"}