{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:V4KG67NP7N45YJ2O7OO4NMV5TA","short_pith_number":"pith:V4KG67NP","schema_version":"1.0","canonical_sha256":"af146f7daffb79dc274efb9dc6b2bd981d320f9b70429e1adf428ff602bb8774","source":{"kind":"arxiv","id":"2312.16409","version":2},"attestation_state":"computed","paper":{"title":"Dynamic Sub-graph Distillation for Robust Semi-supervised Continual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Pengfei Zhu, Qinghua Hu, Yan Fan, Yu Wang","submitted_at":"2023-12-27T04:40:12Z","abstract_excerpt":"Continual learning (CL) has shown promising results and comparable performance to learning at once in a fully supervised manner. However, CL strategies typically require a large number of labeled samples, making their real-life deployment challenging. In this work, we focus on semi-supervised continual learning (SSCL), where the model progressively learns from partially labeled data with unknown categories. We provide a comprehensive analysis of SSCL and demonstrate that unreliable distributions of unlabeled data lead to unstable training and refinement of the progressing stages. This problem "},"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":"2312.16409","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-27T04:40:12Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"a4ea728f7207601eb385382bbcedfa0b01a7a79a66fb3f8b1fc8db856558a218","abstract_canon_sha256":"6fc545e31dde9b0860c8169a8280efa27e67066d7d58fdae11fe125bad295a26"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:34.236272Z","signature_b64":"rkKgychG++byccWQFCIg2M850qyGtRMjUz+tP6lEn9lOl8HtarrbzwE5Eh4uQm1196uxvQk0sQU9jhM9SAFiAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af146f7daffb79dc274efb9dc6b2bd981d320f9b70429e1adf428ff602bb8774","last_reissued_at":"2026-07-05T10:00:34.235810Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:34.235810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Sub-graph Distillation for Robust Semi-supervised Continual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Pengfei Zhu, Qinghua Hu, Yan Fan, Yu Wang","submitted_at":"2023-12-27T04:40:12Z","abstract_excerpt":"Continual learning (CL) has shown promising results and comparable performance to learning at once in a fully supervised manner. However, CL strategies typically require a large number of labeled samples, making their real-life deployment challenging. In this work, we focus on semi-supervised continual learning (SSCL), where the model progressively learns from partially labeled data with unknown categories. We provide a comprehensive analysis of SSCL and demonstrate that unreliable distributions of unlabeled data lead to unstable training and refinement of the progressing stages. This problem "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.16409","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/2312.16409/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":"2312.16409","created_at":"2026-07-05T10:00:34.235870+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.16409v2","created_at":"2026-07-05T10:00:34.235870+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.16409","created_at":"2026-07-05T10:00:34.235870+00:00"},{"alias_kind":"pith_short_12","alias_value":"V4KG67NP7N45","created_at":"2026-07-05T10:00:34.235870+00:00"},{"alias_kind":"pith_short_16","alias_value":"V4KG67NP7N45YJ2O","created_at":"2026-07-05T10:00:34.235870+00:00"},{"alias_kind":"pith_short_8","alias_value":"V4KG67NP","created_at":"2026-07-05T10:00:34.235870+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/V4KG67NP7N45YJ2O7OO4NMV5TA","json":"https://pith.science/pith/V4KG67NP7N45YJ2O7OO4NMV5TA.json","graph_json":"https://pith.science/api/pith-number/V4KG67NP7N45YJ2O7OO4NMV5TA/graph.json","events_json":"https://pith.science/api/pith-number/V4KG67NP7N45YJ2O7OO4NMV5TA/events.json","paper":"https://pith.science/paper/V4KG67NP"},"agent_actions":{"view_html":"https://pith.science/pith/V4KG67NP7N45YJ2O7OO4NMV5TA","download_json":"https://pith.science/pith/V4KG67NP7N45YJ2O7OO4NMV5TA.json","view_paper":"https://pith.science/paper/V4KG67NP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.16409&json=true","fetch_graph":"https://pith.science/api/pith-number/V4KG67NP7N45YJ2O7OO4NMV5TA/graph.json","fetch_events":"https://pith.science/api/pith-number/V4KG67NP7N45YJ2O7OO4NMV5TA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V4KG67NP7N45YJ2O7OO4NMV5TA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V4KG67NP7N45YJ2O7OO4NMV5TA/action/storage_attestation","attest_author":"https://pith.science/pith/V4KG67NP7N45YJ2O7OO4NMV5TA/action/author_attestation","sign_citation":"https://pith.science/pith/V4KG67NP7N45YJ2O7OO4NMV5TA/action/citation_signature","submit_replication":"https://pith.science/pith/V4KG67NP7N45YJ2O7OO4NMV5TA/action/replication_record"}},"created_at":"2026-07-05T10:00:34.235870+00:00","updated_at":"2026-07-05T10:00:34.235870+00:00"}