{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:AMYNEOKTGA55FIFZXEFTEHKEHZ","short_pith_number":"pith:AMYNEOKT","schema_version":"1.0","canonical_sha256":"0330d23953303bd2a0b9b90b321d443e6872fdd2b4d359eafe3ef41aa175ac36","source":{"kind":"arxiv","id":"2111.11595","version":1},"attestation_state":"computed","paper":{"title":"Semi-Supervised Learning with Taxonomic Labels","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":"2021-11-23T00:50:25Z","abstract_excerpt":"We propose techniques to incorporate coarse taxonomic labels to train image classifiers in fine-grained domains. Such labels can often be obtained with a smaller effort for fine-grained domains such as the natural world where categories are organized according to a biological taxonomy. On the Semi-iNat dataset consisting of 810 species across three Kingdoms, incorporating Phylum labels improves the Species level classification accuracy by 6% in a transfer learning setting using ImageNet pre-trained models. Incorporating the hierarchical label structure with a state-of-the-art semi-supervised l"},"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":"2111.11595","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-23T00:50:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ec1dbb41e545f88c6831da2721e3796067fe2600d68e057562945b6d06464cbb","abstract_canon_sha256":"0fb5076e98cc10b654893645ea6f4d22e8bfbccc44540914cef4dbfae8031137"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:34:10.641997Z","signature_b64":"lOM8xgkL4iMVp+54KxnEt2FobYqXbMsFplgS7IYzZNu0vFAdBVSbF6ZG1KPiPdd5HYz1AjG7dB01fS1vpuXIAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0330d23953303bd2a0b9b90b321d443e6872fdd2b4d359eafe3ef41aa175ac36","last_reissued_at":"2026-07-05T03:34:10.641530Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:34:10.641530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semi-Supervised Learning with Taxonomic Labels","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":"2021-11-23T00:50:25Z","abstract_excerpt":"We propose techniques to incorporate coarse taxonomic labels to train image classifiers in fine-grained domains. Such labels can often be obtained with a smaller effort for fine-grained domains such as the natural world where categories are organized according to a biological taxonomy. On the Semi-iNat dataset consisting of 810 species across three Kingdoms, incorporating Phylum labels improves the Species level classification accuracy by 6% in a transfer learning setting using ImageNet pre-trained models. Incorporating the hierarchical label structure with a state-of-the-art semi-supervised l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.11595","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/2111.11595/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":"2111.11595","created_at":"2026-07-05T03:34:10.641601+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.11595v1","created_at":"2026-07-05T03:34:10.641601+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.11595","created_at":"2026-07-05T03:34:10.641601+00:00"},{"alias_kind":"pith_short_12","alias_value":"AMYNEOKTGA55","created_at":"2026-07-05T03:34:10.641601+00:00"},{"alias_kind":"pith_short_16","alias_value":"AMYNEOKTGA55FIFZ","created_at":"2026-07-05T03:34:10.641601+00:00"},{"alias_kind":"pith_short_8","alias_value":"AMYNEOKT","created_at":"2026-07-05T03:34:10.641601+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.21476","citing_title":"Global and Local Entailment Learning for Natural World Imagery","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AMYNEOKTGA55FIFZXEFTEHKEHZ","json":"https://pith.science/pith/AMYNEOKTGA55FIFZXEFTEHKEHZ.json","graph_json":"https://pith.science/api/pith-number/AMYNEOKTGA55FIFZXEFTEHKEHZ/graph.json","events_json":"https://pith.science/api/pith-number/AMYNEOKTGA55FIFZXEFTEHKEHZ/events.json","paper":"https://pith.science/paper/AMYNEOKT"},"agent_actions":{"view_html":"https://pith.science/pith/AMYNEOKTGA55FIFZXEFTEHKEHZ","download_json":"https://pith.science/pith/AMYNEOKTGA55FIFZXEFTEHKEHZ.json","view_paper":"https://pith.science/paper/AMYNEOKT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.11595&json=true","fetch_graph":"https://pith.science/api/pith-number/AMYNEOKTGA55FIFZXEFTEHKEHZ/graph.json","fetch_events":"https://pith.science/api/pith-number/AMYNEOKTGA55FIFZXEFTEHKEHZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AMYNEOKTGA55FIFZXEFTEHKEHZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AMYNEOKTGA55FIFZXEFTEHKEHZ/action/storage_attestation","attest_author":"https://pith.science/pith/AMYNEOKTGA55FIFZXEFTEHKEHZ/action/author_attestation","sign_citation":"https://pith.science/pith/AMYNEOKTGA55FIFZXEFTEHKEHZ/action/citation_signature","submit_replication":"https://pith.science/pith/AMYNEOKTGA55FIFZXEFTEHKEHZ/action/replication_record"}},"created_at":"2026-07-05T03:34:10.641601+00:00","updated_at":"2026-07-05T03:34:10.641601+00:00"}