{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:T6UKXETIZVEXVTW2TDF2PG5T47","short_pith_number":"pith:T6UKXETI","schema_version":"1.0","canonical_sha256":"9fa8ab9268cd497aceda98cba79bb3e7fbfb011cdb6b45d56ea0acb7bff9b1f8","source":{"kind":"arxiv","id":"2102.07848","version":2},"attestation_state":"computed","paper":{"title":"Self-Supervised Features Improve Open-World Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Akshay Raj Dhamija, Chunchun Li, Jonathan Schwan, Mohsen Jafarzadeh, Terrance E. Boult, Touqeer Ahmad","submitted_at":"2021-02-15T21:03:05Z","abstract_excerpt":"This paper identifies the flaws in existing open-world learning approaches and attempts to provide a complete picture in the form of \\textbf{True Open-World Learning}. We accomplish this by proposing a comprehensive generalize-able open-world learning protocol capable of evaluating various components of open-world learning in an operational setting. We argue that in true open-world learning, the underlying feature representation should be learned in a self-supervised manner. Under this self-supervised feature representation, we introduce the problem of detecting unknowns as samples belonging t"},"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":"2102.07848","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-02-15T21:03:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4a983c75e3e05ee6f2e6264a9062ffdb83e11e138afaac6919f1770d3c3b6932","abstract_canon_sha256":"d162073e917aef77a20d4f5f486066085828e4ec18f62d8a74994759934fb513"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:36:09.870254Z","signature_b64":"mxqBh3m3lwnFwm1Oexm40HpSmTEljImcn/NRbEX+X2OjyUNtKU4o0qNbHxRqeprn3DOQcnlTOZI7R3olzB+TAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fa8ab9268cd497aceda98cba79bb3e7fbfb011cdb6b45d56ea0acb7bff9b1f8","last_reissued_at":"2026-07-05T02:36:09.869756Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:36:09.869756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Supervised Features Improve Open-World Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Akshay Raj Dhamija, Chunchun Li, Jonathan Schwan, Mohsen Jafarzadeh, Terrance E. Boult, Touqeer Ahmad","submitted_at":"2021-02-15T21:03:05Z","abstract_excerpt":"This paper identifies the flaws in existing open-world learning approaches and attempts to provide a complete picture in the form of \\textbf{True Open-World Learning}. We accomplish this by proposing a comprehensive generalize-able open-world learning protocol capable of evaluating various components of open-world learning in an operational setting. We argue that in true open-world learning, the underlying feature representation should be learned in a self-supervised manner. Under this self-supervised feature representation, we introduce the problem of detecting unknowns as samples belonging t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.07848","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/2102.07848/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":"2102.07848","created_at":"2026-07-05T02:36:09.869814+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.07848v2","created_at":"2026-07-05T02:36:09.869814+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.07848","created_at":"2026-07-05T02:36:09.869814+00:00"},{"alias_kind":"pith_short_12","alias_value":"T6UKXETIZVEX","created_at":"2026-07-05T02:36:09.869814+00:00"},{"alias_kind":"pith_short_16","alias_value":"T6UKXETIZVEXVTW2","created_at":"2026-07-05T02:36:09.869814+00:00"},{"alias_kind":"pith_short_8","alias_value":"T6UKXETI","created_at":"2026-07-05T02:36:09.869814+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.24393","citing_title":"Complexity of Linear Regions in Self-supervised Deep ReLU Networks","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T6UKXETIZVEXVTW2TDF2PG5T47","json":"https://pith.science/pith/T6UKXETIZVEXVTW2TDF2PG5T47.json","graph_json":"https://pith.science/api/pith-number/T6UKXETIZVEXVTW2TDF2PG5T47/graph.json","events_json":"https://pith.science/api/pith-number/T6UKXETIZVEXVTW2TDF2PG5T47/events.json","paper":"https://pith.science/paper/T6UKXETI"},"agent_actions":{"view_html":"https://pith.science/pith/T6UKXETIZVEXVTW2TDF2PG5T47","download_json":"https://pith.science/pith/T6UKXETIZVEXVTW2TDF2PG5T47.json","view_paper":"https://pith.science/paper/T6UKXETI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.07848&json=true","fetch_graph":"https://pith.science/api/pith-number/T6UKXETIZVEXVTW2TDF2PG5T47/graph.json","fetch_events":"https://pith.science/api/pith-number/T6UKXETIZVEXVTW2TDF2PG5T47/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T6UKXETIZVEXVTW2TDF2PG5T47/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T6UKXETIZVEXVTW2TDF2PG5T47/action/storage_attestation","attest_author":"https://pith.science/pith/T6UKXETIZVEXVTW2TDF2PG5T47/action/author_attestation","sign_citation":"https://pith.science/pith/T6UKXETIZVEXVTW2TDF2PG5T47/action/citation_signature","submit_replication":"https://pith.science/pith/T6UKXETIZVEXVTW2TDF2PG5T47/action/replication_record"}},"created_at":"2026-07-05T02:36:09.869814+00:00","updated_at":"2026-07-05T02:36:09.869814+00:00"}