{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:OMGMNUFMMWDERJDWLBCBEE43VK","short_pith_number":"pith:OMGMNUFM","schema_version":"1.0","canonical_sha256":"730cc6d0ac658648a476584412139baaac3804fd27116ddc3b6b9de6e79af7a8","source":{"kind":"arxiv","id":"2002.05714","version":1},"attestation_state":"computed","paper":{"title":"Automatically Discovering and Learning New Visual Categories with Ranking Statistics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Andrew Zisserman, Kai Han, Sebastien Ehrhardt, Sylvestre-Alvise Rebuffi","submitted_at":"2020-02-13T18:53:32Z","abstract_excerpt":"We tackle the problem of discovering novel classes in an image collection given labelled examples of other classes. This setting is similar to semi-supervised learning, but significantly harder because there are no labelled examples for the new classes. The challenge, then, is to leverage the information contained in the labelled images in order to learn a general-purpose clustering model and use the latter to identify the new classes in the unlabelled data. In this work we address this problem by combining three ideas: (1) we suggest that the common approach of bootstrapping an image represen"},"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":"2002.05714","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-13T18:53:32Z","cross_cats_sorted":[],"title_canon_sha256":"e880a316a73587106d3a8222a23fd7e8abe509f43f75dca3681b69c997dd47ed","abstract_canon_sha256":"52bb3a9167362b44aa45cb1400d78db2f72eca04f3f1b67fd7c6b67153e5e479"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:40:33.775564Z","signature_b64":"LN2cIt+2ixX42K5tb0hEWIqqhEGs32+8Cm9g+jmY7J0APAoB1roiM+pe59mBxFXY0W/FzcPoSGGbgYZT+6tACg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"730cc6d0ac658648a476584412139baaac3804fd27116ddc3b6b9de6e79af7a8","last_reissued_at":"2026-07-05T00:40:33.774553Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:40:33.774553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automatically Discovering and Learning New Visual Categories with Ranking Statistics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Andrew Zisserman, Kai Han, Sebastien Ehrhardt, Sylvestre-Alvise Rebuffi","submitted_at":"2020-02-13T18:53:32Z","abstract_excerpt":"We tackle the problem of discovering novel classes in an image collection given labelled examples of other classes. This setting is similar to semi-supervised learning, but significantly harder because there are no labelled examples for the new classes. The challenge, then, is to leverage the information contained in the labelled images in order to learn a general-purpose clustering model and use the latter to identify the new classes in the unlabelled data. In this work we address this problem by combining three ideas: (1) we suggest that the common approach of bootstrapping an image represen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.05714","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/2002.05714/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":"2002.05714","created_at":"2026-07-05T00:40:33.774618+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.05714v1","created_at":"2026-07-05T00:40:33.774618+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.05714","created_at":"2026-07-05T00:40:33.774618+00:00"},{"alias_kind":"pith_short_12","alias_value":"OMGMNUFMMWDE","created_at":"2026-07-05T00:40:33.774618+00:00"},{"alias_kind":"pith_short_16","alias_value":"OMGMNUFMMWDERJDW","created_at":"2026-07-05T00:40:33.774618+00:00"},{"alias_kind":"pith_short_8","alias_value":"OMGMNUFM","created_at":"2026-07-05T00:40:33.774618+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.21424","citing_title":"Unsupervised Incremental Learning Using Confidence-Based Pseudo-Labels","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OMGMNUFMMWDERJDWLBCBEE43VK","json":"https://pith.science/pith/OMGMNUFMMWDERJDWLBCBEE43VK.json","graph_json":"https://pith.science/api/pith-number/OMGMNUFMMWDERJDWLBCBEE43VK/graph.json","events_json":"https://pith.science/api/pith-number/OMGMNUFMMWDERJDWLBCBEE43VK/events.json","paper":"https://pith.science/paper/OMGMNUFM"},"agent_actions":{"view_html":"https://pith.science/pith/OMGMNUFMMWDERJDWLBCBEE43VK","download_json":"https://pith.science/pith/OMGMNUFMMWDERJDWLBCBEE43VK.json","view_paper":"https://pith.science/paper/OMGMNUFM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.05714&json=true","fetch_graph":"https://pith.science/api/pith-number/OMGMNUFMMWDERJDWLBCBEE43VK/graph.json","fetch_events":"https://pith.science/api/pith-number/OMGMNUFMMWDERJDWLBCBEE43VK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OMGMNUFMMWDERJDWLBCBEE43VK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OMGMNUFMMWDERJDWLBCBEE43VK/action/storage_attestation","attest_author":"https://pith.science/pith/OMGMNUFMMWDERJDWLBCBEE43VK/action/author_attestation","sign_citation":"https://pith.science/pith/OMGMNUFMMWDERJDWLBCBEE43VK/action/citation_signature","submit_replication":"https://pith.science/pith/OMGMNUFMMWDERJDWLBCBEE43VK/action/replication_record"}},"created_at":"2026-07-05T00:40:33.774618+00:00","updated_at":"2026-07-05T00:40:33.774618+00:00"}