{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:HOA5P2KI6NSP7GJCT3THGYISL6","short_pith_number":"pith:HOA5P2KI","schema_version":"1.0","canonical_sha256":"3b81d7e948f364ff99229ee67361125faa52fd27b87c7a9ba94b5a5f3ac2b040","source":{"kind":"arxiv","id":"2012.01227","version":3},"attestation_state":"computed","paper":{"title":"Message Passing Adaptive Resonance Theory for Online Active Semi-supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Byoung-Tak Zhang, Hyundo Lee, Hyunseo Kim, Injune Hwang, Joseph J. Lim, Taehyeong Kim, Won-Seok Choi","submitted_at":"2020-12-02T14:14:42Z","abstract_excerpt":"Active learning is widely used to reduce labeling effort and training time by repeatedly querying only the most beneficial samples from unlabeled data. In real-world problems where data cannot be stored indefinitely due to limited storage or privacy issues, the query selection and the model update should be performed as soon as a new data sample is observed. Various online active learning methods have been studied to deal with these challenges; however, there are difficulties in selecting representative query samples and updating the model efficiently without forgetting. In this study, we prop"},"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":"2012.01227","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-02T14:14:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b8997949d70ee84ce52129a2e309ebe77738434432c9524e7281f8f18515958b","abstract_canon_sha256":"c1f83633577a35f2557cacd51d1821598c4d1aef0070f39ca80099f5f0fa26c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:56:37.614471Z","signature_b64":"RwpE0DoohluvufGTJ9c1Xjo71JrwEU85MQ2yagD5T4u8NzWwkpkW6cseYe8iZgg8o6XBbqmpWy28OE5WHeEHAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b81d7e948f364ff99229ee67361125faa52fd27b87c7a9ba94b5a5f3ac2b040","last_reissued_at":"2026-07-05T02:56:37.614035Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:56:37.614035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Message Passing Adaptive Resonance Theory for Online Active Semi-supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Byoung-Tak Zhang, Hyundo Lee, Hyunseo Kim, Injune Hwang, Joseph J. Lim, Taehyeong Kim, Won-Seok Choi","submitted_at":"2020-12-02T14:14:42Z","abstract_excerpt":"Active learning is widely used to reduce labeling effort and training time by repeatedly querying only the most beneficial samples from unlabeled data. In real-world problems where data cannot be stored indefinitely due to limited storage or privacy issues, the query selection and the model update should be performed as soon as a new data sample is observed. Various online active learning methods have been studied to deal with these challenges; however, there are difficulties in selecting representative query samples and updating the model efficiently without forgetting. In this study, we prop"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.01227","kind":"arxiv","version":3},"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/2012.01227/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":"2012.01227","created_at":"2026-07-05T02:56:37.614099+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.01227v3","created_at":"2026-07-05T02:56:37.614099+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.01227","created_at":"2026-07-05T02:56:37.614099+00:00"},{"alias_kind":"pith_short_12","alias_value":"HOA5P2KI6NSP","created_at":"2026-07-05T02:56:37.614099+00:00"},{"alias_kind":"pith_short_16","alias_value":"HOA5P2KI6NSP7GJC","created_at":"2026-07-05T02:56:37.614099+00:00"},{"alias_kind":"pith_short_8","alias_value":"HOA5P2KI","created_at":"2026-07-05T02:56:37.614099+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/HOA5P2KI6NSP7GJCT3THGYISL6","json":"https://pith.science/pith/HOA5P2KI6NSP7GJCT3THGYISL6.json","graph_json":"https://pith.science/api/pith-number/HOA5P2KI6NSP7GJCT3THGYISL6/graph.json","events_json":"https://pith.science/api/pith-number/HOA5P2KI6NSP7GJCT3THGYISL6/events.json","paper":"https://pith.science/paper/HOA5P2KI"},"agent_actions":{"view_html":"https://pith.science/pith/HOA5P2KI6NSP7GJCT3THGYISL6","download_json":"https://pith.science/pith/HOA5P2KI6NSP7GJCT3THGYISL6.json","view_paper":"https://pith.science/paper/HOA5P2KI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.01227&json=true","fetch_graph":"https://pith.science/api/pith-number/HOA5P2KI6NSP7GJCT3THGYISL6/graph.json","fetch_events":"https://pith.science/api/pith-number/HOA5P2KI6NSP7GJCT3THGYISL6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HOA5P2KI6NSP7GJCT3THGYISL6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HOA5P2KI6NSP7GJCT3THGYISL6/action/storage_attestation","attest_author":"https://pith.science/pith/HOA5P2KI6NSP7GJCT3THGYISL6/action/author_attestation","sign_citation":"https://pith.science/pith/HOA5P2KI6NSP7GJCT3THGYISL6/action/citation_signature","submit_replication":"https://pith.science/pith/HOA5P2KI6NSP7GJCT3THGYISL6/action/replication_record"}},"created_at":"2026-07-05T02:56:37.614099+00:00","updated_at":"2026-07-05T02:56:37.614099+00:00"}