{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:VBK32SSEU2QC5D3EACCVUO7CQU","short_pith_number":"pith:VBK32SSE","schema_version":"1.0","canonical_sha256":"a855bd4a44a6a02e8f6400855a3be28525600cf0f030aeb67a0e8d92454d4079","source":{"kind":"arxiv","id":"1409.8403","version":2},"attestation_state":"computed","paper":{"title":"Evaluation of Output Embeddings for Fine-Grained Image Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bernt Schiele, Daniel Walter, Honglak Lee, Scott Reed, Zeynep Akata","submitted_at":"2014-09-30T06:49:53Z","abstract_excerpt":"Image classification has advanced significantly in recent years with the availability of large-scale image sets. However, fine-grained classification remains a major challenge due to the annotation cost of large numbers of fine-grained categories. This project shows that compelling classification performance can be achieved on such categories even without labeled training data. Given image and class embeddings, we learn a compatibility function such that matching embeddings are assigned a higher score than mismatching ones; zero-shot classification of an image proceeds by finding the label yie"},"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":"1409.8403","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-09-30T06:49:53Z","cross_cats_sorted":[],"title_canon_sha256":"6588bcbdcf30ec5a340ee3d531bb5b9e98458a2b60c644edede2da93e1c0f113","abstract_canon_sha256":"608161569347806218ad63e98f41672a73381a45b36d63ce7dc7d3e57bd2f8fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:16:35.178471Z","signature_b64":"W5EtzD/hN2ImGsGCK6UqhdpERVSzhmdZxyF6ZtDVPaus45OphzbiPPdGpalkbnopgL0tWL69gh15ntG2kuW3CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a855bd4a44a6a02e8f6400855a3be28525600cf0f030aeb67a0e8d92454d4079","last_reissued_at":"2026-05-18T01:16:35.177862Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:16:35.177862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluation of Output Embeddings for Fine-Grained Image Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bernt Schiele, Daniel Walter, Honglak Lee, Scott Reed, Zeynep Akata","submitted_at":"2014-09-30T06:49:53Z","abstract_excerpt":"Image classification has advanced significantly in recent years with the availability of large-scale image sets. However, fine-grained classification remains a major challenge due to the annotation cost of large numbers of fine-grained categories. This project shows that compelling classification performance can be achieved on such categories even without labeled training data. Given image and class embeddings, we learn a compatibility function such that matching embeddings are assigned a higher score than mismatching ones; zero-shot classification of an image proceeds by finding the label yie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1409.8403","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":""},"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":"1409.8403","created_at":"2026-05-18T01:16:35.177943+00:00"},{"alias_kind":"arxiv_version","alias_value":"1409.8403v2","created_at":"2026-05-18T01:16:35.177943+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1409.8403","created_at":"2026-05-18T01:16:35.177943+00:00"},{"alias_kind":"pith_short_12","alias_value":"VBK32SSEU2QC","created_at":"2026-05-18T12:28:52.271510+00:00"},{"alias_kind":"pith_short_16","alias_value":"VBK32SSEU2QC5D3E","created_at":"2026-05-18T12:28:52.271510+00:00"},{"alias_kind":"pith_short_8","alias_value":"VBK32SSE","created_at":"2026-05-18T12:28:52.271510+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/VBK32SSEU2QC5D3EACCVUO7CQU","json":"https://pith.science/pith/VBK32SSEU2QC5D3EACCVUO7CQU.json","graph_json":"https://pith.science/api/pith-number/VBK32SSEU2QC5D3EACCVUO7CQU/graph.json","events_json":"https://pith.science/api/pith-number/VBK32SSEU2QC5D3EACCVUO7CQU/events.json","paper":"https://pith.science/paper/VBK32SSE"},"agent_actions":{"view_html":"https://pith.science/pith/VBK32SSEU2QC5D3EACCVUO7CQU","download_json":"https://pith.science/pith/VBK32SSEU2QC5D3EACCVUO7CQU.json","view_paper":"https://pith.science/paper/VBK32SSE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1409.8403&json=true","fetch_graph":"https://pith.science/api/pith-number/VBK32SSEU2QC5D3EACCVUO7CQU/graph.json","fetch_events":"https://pith.science/api/pith-number/VBK32SSEU2QC5D3EACCVUO7CQU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VBK32SSEU2QC5D3EACCVUO7CQU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VBK32SSEU2QC5D3EACCVUO7CQU/action/storage_attestation","attest_author":"https://pith.science/pith/VBK32SSEU2QC5D3EACCVUO7CQU/action/author_attestation","sign_citation":"https://pith.science/pith/VBK32SSEU2QC5D3EACCVUO7CQU/action/citation_signature","submit_replication":"https://pith.science/pith/VBK32SSEU2QC5D3EACCVUO7CQU/action/replication_record"}},"created_at":"2026-05-18T01:16:35.177943+00:00","updated_at":"2026-05-18T01:16:35.177943+00:00"}