{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:242RKW7ZGD46B6LHPLSKRW3WTW","short_pith_number":"pith:242RKW7Z","schema_version":"1.0","canonical_sha256":"d735155bf930f9e0f9677ae4a8db769d8684d3b750c240b01ebbc3d578411355","source":{"kind":"arxiv","id":"2106.01364","version":1},"attestation_state":"computed","paper":{"title":"The Semi-Supervised iNaturalist Challenge at the FGVC8 Workshop","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jong-Chyi Su, Subhransu Maji","submitted_at":"2021-06-02T17:59:41Z","abstract_excerpt":"Semi-iNat is a challenging dataset for semi-supervised classification with a long-tailed distribution of classes, fine-grained categories, and domain shifts between labeled and unlabeled data. This dataset is behind the second iteration of the semi-supervised recognition challenge to be held at the FGVC8 workshop at CVPR 2021. Different from the previous one, this dataset (i) includes images of species from different kingdoms in the natural taxonomy, (ii) is at a larger scale -- with 810 in-class and 1629 out-of-class species for a total of 330k images, and (iii) does not provide in/out-of-cla"},"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":"2106.01364","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-02T17:59:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5920807c36e85f20f0d9924a9c53d7dfabde6d72ce8b5a1130f60e2ab53665e7","abstract_canon_sha256":"d6b778550daea4b5780446147d8cb2e535482c0ad0863d9a14907d0eb9d4d23b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:51:54.603853Z","signature_b64":"8TKDb8LFpvsBj258hswnGmNHNK7eb+jbNuwwC559HVD8cxEdLGzsIgZGCbKIaDqqmH1MbFrH+SD2oAzSilaVBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d735155bf930f9e0f9677ae4a8db769d8684d3b750c240b01ebbc3d578411355","last_reissued_at":"2026-07-05T02:51:54.603393Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:51:54.603393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Semi-Supervised iNaturalist Challenge at the FGVC8 Workshop","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jong-Chyi Su, Subhransu Maji","submitted_at":"2021-06-02T17:59:41Z","abstract_excerpt":"Semi-iNat is a challenging dataset for semi-supervised classification with a long-tailed distribution of classes, fine-grained categories, and domain shifts between labeled and unlabeled data. This dataset is behind the second iteration of the semi-supervised recognition challenge to be held at the FGVC8 workshop at CVPR 2021. Different from the previous one, this dataset (i) includes images of species from different kingdoms in the natural taxonomy, (ii) is at a larger scale -- with 810 in-class and 1629 out-of-class species for a total of 330k images, and (iii) does not provide in/out-of-cla"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.01364","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/2106.01364/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":"2106.01364","created_at":"2026-07-05T02:51:54.603450+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.01364v1","created_at":"2026-07-05T02:51:54.603450+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.01364","created_at":"2026-07-05T02:51:54.603450+00:00"},{"alias_kind":"pith_short_12","alias_value":"242RKW7ZGD46","created_at":"2026-07-05T02:51:54.603450+00:00"},{"alias_kind":"pith_short_16","alias_value":"242RKW7ZGD46B6LH","created_at":"2026-07-05T02:51:54.603450+00:00"},{"alias_kind":"pith_short_8","alias_value":"242RKW7Z","created_at":"2026-07-05T02:51:54.603450+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.24443","citing_title":"Diversify and Conquer: Open-set Disagreement for Robust Semi-supervised Learning with Outliers","ref_index":44,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/242RKW7ZGD46B6LHPLSKRW3WTW","json":"https://pith.science/pith/242RKW7ZGD46B6LHPLSKRW3WTW.json","graph_json":"https://pith.science/api/pith-number/242RKW7ZGD46B6LHPLSKRW3WTW/graph.json","events_json":"https://pith.science/api/pith-number/242RKW7ZGD46B6LHPLSKRW3WTW/events.json","paper":"https://pith.science/paper/242RKW7Z"},"agent_actions":{"view_html":"https://pith.science/pith/242RKW7ZGD46B6LHPLSKRW3WTW","download_json":"https://pith.science/pith/242RKW7ZGD46B6LHPLSKRW3WTW.json","view_paper":"https://pith.science/paper/242RKW7Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.01364&json=true","fetch_graph":"https://pith.science/api/pith-number/242RKW7ZGD46B6LHPLSKRW3WTW/graph.json","fetch_events":"https://pith.science/api/pith-number/242RKW7ZGD46B6LHPLSKRW3WTW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/242RKW7ZGD46B6LHPLSKRW3WTW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/242RKW7ZGD46B6LHPLSKRW3WTW/action/storage_attestation","attest_author":"https://pith.science/pith/242RKW7ZGD46B6LHPLSKRW3WTW/action/author_attestation","sign_citation":"https://pith.science/pith/242RKW7ZGD46B6LHPLSKRW3WTW/action/citation_signature","submit_replication":"https://pith.science/pith/242RKW7ZGD46B6LHPLSKRW3WTW/action/replication_record"}},"created_at":"2026-07-05T02:51:54.603450+00:00","updated_at":"2026-07-05T02:51:54.603450+00:00"}