{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:5AY6I2CG7AMMM2FGHATQAZYJTN","short_pith_number":"pith:5AY6I2CG","schema_version":"1.0","canonical_sha256":"e831e46846f818c668a638270067099b52683916b8a1c0213d32d0daef03ee18","source":{"kind":"arxiv","id":"2203.13307","version":1},"attestation_state":"computed","paper":{"title":"Tackling Online One-Class Incremental Learning by Removing Negative Contrasts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Eugene Belilovsky, Nader Asadi, Sudhir Mudur","submitted_at":"2022-03-24T19:17:29Z","abstract_excerpt":"Recent work studies the supervised online continual learning setting where a learner receives a stream of data whose class distribution changes over time. Distinct from other continual learning settings the learner is presented new samples only once and must distinguish between all seen classes. A number of successful methods in this setting focus on storing and replaying a subset of samples alongside incoming data in a computationally efficient manner. One recent proposal ER-AML achieved strong performance in this setting by applying an asymmetric loss based on contrastive learning to the inc"},"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":"2203.13307","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-24T19:17:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"aae5dc5154ddc32d3ddca34bfcc40a97ae18892d025b11855822bcbe51ffaad5","abstract_canon_sha256":"a500f5096b07f1e25f059e1ce7d02ee7cae25e7bd35378ad02669f0cafa34b15"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:08:30.466376Z","signature_b64":"Xr8rYLv9H44ZIrwrcKIC1B7FcI1ep7G7v8rZg32RnTzTLIIc6PY3uUXCv3DjOFRf7yYoGOA4HVHweIEE6fD/DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e831e46846f818c668a638270067099b52683916b8a1c0213d32d0daef03ee18","last_reissued_at":"2026-07-05T04:08:30.465937Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:08:30.465937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tackling Online One-Class Incremental Learning by Removing Negative Contrasts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Eugene Belilovsky, Nader Asadi, Sudhir Mudur","submitted_at":"2022-03-24T19:17:29Z","abstract_excerpt":"Recent work studies the supervised online continual learning setting where a learner receives a stream of data whose class distribution changes over time. Distinct from other continual learning settings the learner is presented new samples only once and must distinguish between all seen classes. A number of successful methods in this setting focus on storing and replaying a subset of samples alongside incoming data in a computationally efficient manner. One recent proposal ER-AML achieved strong performance in this setting by applying an asymmetric loss based on contrastive learning to the inc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.13307","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/2203.13307/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":"2203.13307","created_at":"2026-07-05T04:08:30.466007+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.13307v1","created_at":"2026-07-05T04:08:30.466007+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.13307","created_at":"2026-07-05T04:08:30.466007+00:00"},{"alias_kind":"pith_short_12","alias_value":"5AY6I2CG7AMM","created_at":"2026-07-05T04:08:30.466007+00:00"},{"alias_kind":"pith_short_16","alias_value":"5AY6I2CG7AMMM2FG","created_at":"2026-07-05T04:08:30.466007+00:00"},{"alias_kind":"pith_short_8","alias_value":"5AY6I2CG","created_at":"2026-07-05T04:08:30.466007+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.16763","citing_title":"Noise-Tolerant Coreset-Based Class Incremental Continual Learning","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5AY6I2CG7AMMM2FGHATQAZYJTN","json":"https://pith.science/pith/5AY6I2CG7AMMM2FGHATQAZYJTN.json","graph_json":"https://pith.science/api/pith-number/5AY6I2CG7AMMM2FGHATQAZYJTN/graph.json","events_json":"https://pith.science/api/pith-number/5AY6I2CG7AMMM2FGHATQAZYJTN/events.json","paper":"https://pith.science/paper/5AY6I2CG"},"agent_actions":{"view_html":"https://pith.science/pith/5AY6I2CG7AMMM2FGHATQAZYJTN","download_json":"https://pith.science/pith/5AY6I2CG7AMMM2FGHATQAZYJTN.json","view_paper":"https://pith.science/paper/5AY6I2CG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.13307&json=true","fetch_graph":"https://pith.science/api/pith-number/5AY6I2CG7AMMM2FGHATQAZYJTN/graph.json","fetch_events":"https://pith.science/api/pith-number/5AY6I2CG7AMMM2FGHATQAZYJTN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5AY6I2CG7AMMM2FGHATQAZYJTN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5AY6I2CG7AMMM2FGHATQAZYJTN/action/storage_attestation","attest_author":"https://pith.science/pith/5AY6I2CG7AMMM2FGHATQAZYJTN/action/author_attestation","sign_citation":"https://pith.science/pith/5AY6I2CG7AMMM2FGHATQAZYJTN/action/citation_signature","submit_replication":"https://pith.science/pith/5AY6I2CG7AMMM2FGHATQAZYJTN/action/replication_record"}},"created_at":"2026-07-05T04:08:30.466007+00:00","updated_at":"2026-07-05T04:08:30.466007+00:00"}