{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LP3GO6JMLP7NZNEFLPAIW6A527","short_pith_number":"pith:LP3GO6JM","schema_version":"1.0","canonical_sha256":"5bf667792c5bfedcb4855bc08b781dd7f127ee9c5bd62891c52b664a4af64f8d","source":{"kind":"arxiv","id":"2212.05102","version":3},"attestation_state":"computed","paper":{"title":"A soft nearest-neighbor framework for continual semi-supervised learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Elisa Ricci, Enrico Fini, Karteek Alahari, Moin Nabi, Zhiqi Kang","submitted_at":"2022-12-09T20:03:59Z","abstract_excerpt":"Despite significant advances, the performance of state-of-the-art continual learning approaches hinges on the unrealistic scenario of fully labeled data. In this paper, we tackle this challenge and propose an approach for continual semi-supervised learning--a setting where not all the data samples are labeled. A primary issue in this scenario is the model forgetting representations of unlabeled data and overfitting the labeled samples. We leverage the power of nearest-neighbor classifiers to nonlinearly partition the feature space and flexibly model the underlying data distribution thanks to i"},"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":"2212.05102","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-09T20:03:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e8fa663e33351dfaf3db8e46cb509551768dc80e31c45adb1ee430d3283fa579","abstract_canon_sha256":"e03c04e5021b9a2e17c6de20a5c685f23128bf1aca172b680b40d431d0e10c1a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:49:17.869197Z","signature_b64":"qkboS0yvACsNQpGZI6SbTPWbgQzdmBNlJoJIPijzXtaHcma1tOX5L+BscX4N1auRH97ukOeuf8Ox/WiewqAqCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5bf667792c5bfedcb4855bc08b781dd7f127ee9c5bd62891c52b664a4af64f8d","last_reissued_at":"2026-07-05T06:49:17.868655Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:49:17.868655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A soft nearest-neighbor framework for continual semi-supervised learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Elisa Ricci, Enrico Fini, Karteek Alahari, Moin Nabi, Zhiqi Kang","submitted_at":"2022-12-09T20:03:59Z","abstract_excerpt":"Despite significant advances, the performance of state-of-the-art continual learning approaches hinges on the unrealistic scenario of fully labeled data. In this paper, we tackle this challenge and propose an approach for continual semi-supervised learning--a setting where not all the data samples are labeled. A primary issue in this scenario is the model forgetting representations of unlabeled data and overfitting the labeled samples. We leverage the power of nearest-neighbor classifiers to nonlinearly partition the feature space and flexibly model the underlying data distribution thanks to i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.05102","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/2212.05102/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":"2212.05102","created_at":"2026-07-05T06:49:17.868717+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.05102v3","created_at":"2026-07-05T06:49:17.868717+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.05102","created_at":"2026-07-05T06:49:17.868717+00:00"},{"alias_kind":"pith_short_12","alias_value":"LP3GO6JMLP7N","created_at":"2026-07-05T06:49:17.868717+00:00"},{"alias_kind":"pith_short_16","alias_value":"LP3GO6JMLP7NZNEF","created_at":"2026-07-05T06:49:17.868717+00:00"},{"alias_kind":"pith_short_8","alias_value":"LP3GO6JM","created_at":"2026-07-05T06:49:17.868717+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/LP3GO6JMLP7NZNEFLPAIW6A527","json":"https://pith.science/pith/LP3GO6JMLP7NZNEFLPAIW6A527.json","graph_json":"https://pith.science/api/pith-number/LP3GO6JMLP7NZNEFLPAIW6A527/graph.json","events_json":"https://pith.science/api/pith-number/LP3GO6JMLP7NZNEFLPAIW6A527/events.json","paper":"https://pith.science/paper/LP3GO6JM"},"agent_actions":{"view_html":"https://pith.science/pith/LP3GO6JMLP7NZNEFLPAIW6A527","download_json":"https://pith.science/pith/LP3GO6JMLP7NZNEFLPAIW6A527.json","view_paper":"https://pith.science/paper/LP3GO6JM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.05102&json=true","fetch_graph":"https://pith.science/api/pith-number/LP3GO6JMLP7NZNEFLPAIW6A527/graph.json","fetch_events":"https://pith.science/api/pith-number/LP3GO6JMLP7NZNEFLPAIW6A527/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LP3GO6JMLP7NZNEFLPAIW6A527/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LP3GO6JMLP7NZNEFLPAIW6A527/action/storage_attestation","attest_author":"https://pith.science/pith/LP3GO6JMLP7NZNEFLPAIW6A527/action/author_attestation","sign_citation":"https://pith.science/pith/LP3GO6JMLP7NZNEFLPAIW6A527/action/citation_signature","submit_replication":"https://pith.science/pith/LP3GO6JMLP7NZNEFLPAIW6A527/action/replication_record"}},"created_at":"2026-07-05T06:49:17.868717+00:00","updated_at":"2026-07-05T06:49:17.868717+00:00"}