{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MNGXRBWRJHCHVFR7BQFTVHUPMF","short_pith_number":"pith:MNGXRBWR","schema_version":"1.0","canonical_sha256":"634d7886d149c47a963f0c0b3a9e8f61529ba6fc6c525f6acb0c0c46c7371640","source":{"kind":"arxiv","id":"2105.14399","version":10},"attestation_state":"computed","paper":{"title":"Enhanced Isotropy Maximization Loss: Seamless and High-Performance Out-of-Distribution Detection Simply Replacing the SoftMax Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"David Mac\\^edo, Teresa Ludermir","submitted_at":"2021-05-30T00:55:03Z","abstract_excerpt":"Current out-of-distribution detection approaches usually present special requirements (e.g., collecting outlier data and hyperparameter validation) and produce side effects (e.g., classification accuracy drop and slow/inefficient inferences). Recently, entropic out-of-distribution detection has been proposed as a seamless approach (i.e., a solution that avoids all previously mentioned drawbacks). The entropic out-of-distribution detection solution uses the IsoMax loss for training and the entropic score for out-of-distribution detection. The IsoMax loss works as a drop-in replacement of the So"},"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":"2105.14399","kind":"arxiv","version":10},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-30T00:55:03Z","cross_cats_sorted":["cs.AI","cs.CV","cs.NE"],"title_canon_sha256":"682bf9e8b2368f9768e9738412e90a8b19d1d35a8ba09d0115a115b7784851f6","abstract_canon_sha256":"eb6be117410f8a32945521dca13f931a099a4155ae66321a8aa6e80bbf9d6056"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:11:24.713032Z","signature_b64":"U7UHYNeb6sARk9N82SdQ5/MkKns74f4HbXY7r7RFjLhqQ/H20TaZziwsozrQMO8dPVlo7kABwGqH7EQ2t9YCAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"634d7886d149c47a963f0c0b3a9e8f61529ba6fc6c525f6acb0c0c46c7371640","last_reissued_at":"2026-07-05T04:11:24.712537Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:11:24.712537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhanced Isotropy Maximization Loss: Seamless and High-Performance Out-of-Distribution Detection Simply Replacing the SoftMax Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"David Mac\\^edo, Teresa Ludermir","submitted_at":"2021-05-30T00:55:03Z","abstract_excerpt":"Current out-of-distribution detection approaches usually present special requirements (e.g., collecting outlier data and hyperparameter validation) and produce side effects (e.g., classification accuracy drop and slow/inefficient inferences). Recently, entropic out-of-distribution detection has been proposed as a seamless approach (i.e., a solution that avoids all previously mentioned drawbacks). The entropic out-of-distribution detection solution uses the IsoMax loss for training and the entropic score for out-of-distribution detection. The IsoMax loss works as a drop-in replacement of the So"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.14399","kind":"arxiv","version":10},"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/2105.14399/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":"2105.14399","created_at":"2026-07-05T04:11:24.712595+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.14399v10","created_at":"2026-07-05T04:11:24.712595+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.14399","created_at":"2026-07-05T04:11:24.712595+00:00"},{"alias_kind":"pith_short_12","alias_value":"MNGXRBWRJHCH","created_at":"2026-07-05T04:11:24.712595+00:00"},{"alias_kind":"pith_short_16","alias_value":"MNGXRBWRJHCHVFR7","created_at":"2026-07-05T04:11:24.712595+00:00"},{"alias_kind":"pith_short_8","alias_value":"MNGXRBWR","created_at":"2026-07-05T04:11:24.712595+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.23027","citing_title":"Diverse Prototypical Ensembles Improve Robustness to Subpopulation Shift","ref_index":2015,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MNGXRBWRJHCHVFR7BQFTVHUPMF","json":"https://pith.science/pith/MNGXRBWRJHCHVFR7BQFTVHUPMF.json","graph_json":"https://pith.science/api/pith-number/MNGXRBWRJHCHVFR7BQFTVHUPMF/graph.json","events_json":"https://pith.science/api/pith-number/MNGXRBWRJHCHVFR7BQFTVHUPMF/events.json","paper":"https://pith.science/paper/MNGXRBWR"},"agent_actions":{"view_html":"https://pith.science/pith/MNGXRBWRJHCHVFR7BQFTVHUPMF","download_json":"https://pith.science/pith/MNGXRBWRJHCHVFR7BQFTVHUPMF.json","view_paper":"https://pith.science/paper/MNGXRBWR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.14399&json=true","fetch_graph":"https://pith.science/api/pith-number/MNGXRBWRJHCHVFR7BQFTVHUPMF/graph.json","fetch_events":"https://pith.science/api/pith-number/MNGXRBWRJHCHVFR7BQFTVHUPMF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MNGXRBWRJHCHVFR7BQFTVHUPMF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MNGXRBWRJHCHVFR7BQFTVHUPMF/action/storage_attestation","attest_author":"https://pith.science/pith/MNGXRBWRJHCHVFR7BQFTVHUPMF/action/author_attestation","sign_citation":"https://pith.science/pith/MNGXRBWRJHCHVFR7BQFTVHUPMF/action/citation_signature","submit_replication":"https://pith.science/pith/MNGXRBWRJHCHVFR7BQFTVHUPMF/action/replication_record"}},"created_at":"2026-07-05T04:11:24.712595+00:00","updated_at":"2026-07-05T04:11:24.712595+00:00"}