{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:7FSRUMGWHDWIQEYKBNDWDEIXNR","short_pith_number":"pith:7FSRUMGW","schema_version":"1.0","canonical_sha256":"f9651a30d638ec88130a0b476191176c6b496ec68d5e9d5bf577ceb5e6822d05","source":{"kind":"arxiv","id":"1605.05395","version":1},"attestation_state":"computed","paper":{"title":"Learning Deep Representations of Fine-grained Visual Descriptions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bernt Schiele, Honglak Lee, Scott Reed, Zeynep Akata","submitted_at":"2016-05-17T23:08:46Z","abstract_excerpt":"State-of-the-art methods for zero-shot visual recognition formulate learning as a joint embedding problem of images and side information. In these formulations the current best complement to visual features are attributes: manually encoded vectors describing shared characteristics among categories. Despite good performance, attributes have limitations: (1) finer-grained recognition requires commensurately more attributes, and (2) attributes do not provide a natural language interface. We propose to overcome these limitations by training neural language models from scratch; i.e. without pre-tra"},"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":"1605.05395","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-05-17T23:08:46Z","cross_cats_sorted":[],"title_canon_sha256":"ac82d154b16480583ec8d260b5da929079686bc4d9c2377dfeb2b1dbac898a04","abstract_canon_sha256":"f124164890a1bf79dcb8b4e1c5e987dfd5695580740b826ce9fb0c824be2e040"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:14:35.127058Z","signature_b64":"UEvn0odfbDHuJuoXcLJ/rRoU2/uNM2dbiZdAOctA1HhNYrBknXxRii9LH2p8rDi4SSYTKmftrQA7iHp5u12RCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9651a30d638ec88130a0b476191176c6b496ec68d5e9d5bf577ceb5e6822d05","last_reissued_at":"2026-05-18T01:14:35.126276Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:14:35.126276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Deep Representations of Fine-grained Visual Descriptions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bernt Schiele, Honglak Lee, Scott Reed, Zeynep Akata","submitted_at":"2016-05-17T23:08:46Z","abstract_excerpt":"State-of-the-art methods for zero-shot visual recognition formulate learning as a joint embedding problem of images and side information. In these formulations the current best complement to visual features are attributes: manually encoded vectors describing shared characteristics among categories. Despite good performance, attributes have limitations: (1) finer-grained recognition requires commensurately more attributes, and (2) attributes do not provide a natural language interface. We propose to overcome these limitations by training neural language models from scratch; i.e. without pre-tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.05395","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":""},"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":"1605.05395","created_at":"2026-05-18T01:14:35.126424+00:00"},{"alias_kind":"arxiv_version","alias_value":"1605.05395v1","created_at":"2026-05-18T01:14:35.126424+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.05395","created_at":"2026-05-18T01:14:35.126424+00:00"},{"alias_kind":"pith_short_12","alias_value":"7FSRUMGWHDWI","created_at":"2026-05-18T12:30:04.600751+00:00"},{"alias_kind":"pith_short_16","alias_value":"7FSRUMGWHDWIQEYK","created_at":"2026-05-18T12:30:04.600751+00:00"},{"alias_kind":"pith_short_8","alias_value":"7FSRUMGW","created_at":"2026-05-18T12:30:04.600751+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/7FSRUMGWHDWIQEYKBNDWDEIXNR","json":"https://pith.science/pith/7FSRUMGWHDWIQEYKBNDWDEIXNR.json","graph_json":"https://pith.science/api/pith-number/7FSRUMGWHDWIQEYKBNDWDEIXNR/graph.json","events_json":"https://pith.science/api/pith-number/7FSRUMGWHDWIQEYKBNDWDEIXNR/events.json","paper":"https://pith.science/paper/7FSRUMGW"},"agent_actions":{"view_html":"https://pith.science/pith/7FSRUMGWHDWIQEYKBNDWDEIXNR","download_json":"https://pith.science/pith/7FSRUMGWHDWIQEYKBNDWDEIXNR.json","view_paper":"https://pith.science/paper/7FSRUMGW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1605.05395&json=true","fetch_graph":"https://pith.science/api/pith-number/7FSRUMGWHDWIQEYKBNDWDEIXNR/graph.json","fetch_events":"https://pith.science/api/pith-number/7FSRUMGWHDWIQEYKBNDWDEIXNR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7FSRUMGWHDWIQEYKBNDWDEIXNR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7FSRUMGWHDWIQEYKBNDWDEIXNR/action/storage_attestation","attest_author":"https://pith.science/pith/7FSRUMGWHDWIQEYKBNDWDEIXNR/action/author_attestation","sign_citation":"https://pith.science/pith/7FSRUMGWHDWIQEYKBNDWDEIXNR/action/citation_signature","submit_replication":"https://pith.science/pith/7FSRUMGWHDWIQEYKBNDWDEIXNR/action/replication_record"}},"created_at":"2026-05-18T01:14:35.126424+00:00","updated_at":"2026-05-18T01:14:35.126424+00:00"}