{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DN5AQLOB33ZV6MCRVQGKXY7IU3","short_pith_number":"pith:DN5AQLOB","schema_version":"1.0","canonical_sha256":"1b7a082dc1def35f3051ac0cabe3e8a6eace3f84aead0c2b1ebb39d141197e19","source":{"kind":"arxiv","id":"2308.15575","version":1},"attestation_state":"computed","paper":{"title":"Prototype Fission: Closing Set for Robust Open-set Semi-supervised Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Xuwei Tan, Yaqian Li, Yi-Jie Huang","submitted_at":"2023-08-29T19:04:42Z","abstract_excerpt":"Semi-supervised Learning (SSL) has been proven vulnerable to out-of-distribution (OOD) samples in realistic large-scale unsupervised datasets due to over-confident pseudo-labeling OODs as in-distribution (ID). A key underlying problem is class-wise latent space spreading from closed seen space to open unseen space, and the bias is further magnified in SSL's self-training loops. To close the ID distribution set so that OODs are better rejected for safe SSL, we propose Prototype Fission(PF) to divide class-wise latent spaces into compact sub-spaces by automatic fine-grained latent space mining, "},"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":"2308.15575","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-29T19:04:42Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"8ab66f59c0a5c60887730ccd784c94615420594e8273d51fd3a1f9d17c217b8d","abstract_canon_sha256":"73711c8de9d392f392c18b0a3534a4aefcafdfc4626ca803d6d4491d8a8eef06"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:46:09.679297Z","signature_b64":"BAoYHafMgs9OjuOXUgqC5urdB6VsWTegsY8OGyOB+Vbrw/pqORrkQ2feqtGsIMPFHZBXKF2ePMsCoQgzbi55DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b7a082dc1def35f3051ac0cabe3e8a6eace3f84aead0c2b1ebb39d141197e19","last_reissued_at":"2026-07-05T06:46:09.678902Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:46:09.678902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prototype Fission: Closing Set for Robust Open-set Semi-supervised Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Xuwei Tan, Yaqian Li, Yi-Jie Huang","submitted_at":"2023-08-29T19:04:42Z","abstract_excerpt":"Semi-supervised Learning (SSL) has been proven vulnerable to out-of-distribution (OOD) samples in realistic large-scale unsupervised datasets due to over-confident pseudo-labeling OODs as in-distribution (ID). A key underlying problem is class-wise latent space spreading from closed seen space to open unseen space, and the bias is further magnified in SSL's self-training loops. To close the ID distribution set so that OODs are better rejected for safe SSL, we propose Prototype Fission(PF) to divide class-wise latent spaces into compact sub-spaces by automatic fine-grained latent space mining, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.15575","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/2308.15575/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":"2308.15575","created_at":"2026-07-05T06:46:09.678958+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.15575v1","created_at":"2026-07-05T06:46:09.678958+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.15575","created_at":"2026-07-05T06:46:09.678958+00:00"},{"alias_kind":"pith_short_12","alias_value":"DN5AQLOB33ZV","created_at":"2026-07-05T06:46:09.678958+00:00"},{"alias_kind":"pith_short_16","alias_value":"DN5AQLOB33ZV6MCR","created_at":"2026-07-05T06:46:09.678958+00:00"},{"alias_kind":"pith_short_8","alias_value":"DN5AQLOB","created_at":"2026-07-05T06:46:09.678958+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.06570","citing_title":"Evolving from Unknown to Known: Retentive Angular Representation Learning for Incremental Open Set Recognition","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DN5AQLOB33ZV6MCRVQGKXY7IU3","json":"https://pith.science/pith/DN5AQLOB33ZV6MCRVQGKXY7IU3.json","graph_json":"https://pith.science/api/pith-number/DN5AQLOB33ZV6MCRVQGKXY7IU3/graph.json","events_json":"https://pith.science/api/pith-number/DN5AQLOB33ZV6MCRVQGKXY7IU3/events.json","paper":"https://pith.science/paper/DN5AQLOB"},"agent_actions":{"view_html":"https://pith.science/pith/DN5AQLOB33ZV6MCRVQGKXY7IU3","download_json":"https://pith.science/pith/DN5AQLOB33ZV6MCRVQGKXY7IU3.json","view_paper":"https://pith.science/paper/DN5AQLOB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.15575&json=true","fetch_graph":"https://pith.science/api/pith-number/DN5AQLOB33ZV6MCRVQGKXY7IU3/graph.json","fetch_events":"https://pith.science/api/pith-number/DN5AQLOB33ZV6MCRVQGKXY7IU3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DN5AQLOB33ZV6MCRVQGKXY7IU3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DN5AQLOB33ZV6MCRVQGKXY7IU3/action/storage_attestation","attest_author":"https://pith.science/pith/DN5AQLOB33ZV6MCRVQGKXY7IU3/action/author_attestation","sign_citation":"https://pith.science/pith/DN5AQLOB33ZV6MCRVQGKXY7IU3/action/citation_signature","submit_replication":"https://pith.science/pith/DN5AQLOB33ZV6MCRVQGKXY7IU3/action/replication_record"}},"created_at":"2026-07-05T06:46:09.678958+00:00","updated_at":"2026-07-05T06:46:09.678958+00:00"}