{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:2KBHVJ2PFTH7QGZ56FO3ER3SO3","short_pith_number":"pith:2KBHVJ2P","schema_version":"1.0","canonical_sha256":"d2827aa74f2ccff81b3df15db2477276f2f3259a2bb3e77dcea6cb67fdc1e643","source":{"kind":"arxiv","id":"2010.03276","version":1},"attestation_state":"computed","paper":{"title":"ZEST: Zero-shot Learning from Text Descriptions using Textual Similarity and Visual Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gal Chechik, Reut Tsarfaty, Tzuf Paz-Argaman, Yuval Atzmon","submitted_at":"2020-10-07T08:57:34Z","abstract_excerpt":"We study the problem of recognizing visual entities from the textual descriptions of their classes. Specifically, given birds' images with free-text descriptions of their species, we learn to classify images of previously-unseen species based on specie descriptions. This setup has been studied in the vision community under the name zero-shot learning from text, focusing on learning to transfer knowledge about visual aspects of birds from seen classes to previously-unseen ones. Here, we suggest focusing on the textual description and distilling from the description the most relevant information"},"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":"2010.03276","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-07T08:57:34Z","cross_cats_sorted":[],"title_canon_sha256":"107592cc373e4a1c3e573975005107c33fab48c24192882b55550014bac2beb4","abstract_canon_sha256":"d62a2ccfe23142e02746171399b5de396be1c67d858abce74188a0098ed7ce7a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:41:11.514838Z","signature_b64":"r3xY0hyjsYH/UkSNN038d4ahK5qWS3lKIHNTlKMzYmgQLP9TUvwbtXWfmNrtOFVMx7pFLPCdY/dQuR+TaECWCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2827aa74f2ccff81b3df15db2477276f2f3259a2bb3e77dcea6cb67fdc1e643","last_reissued_at":"2026-07-05T01:41:11.514465Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:41:11.514465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ZEST: Zero-shot Learning from Text Descriptions using Textual Similarity and Visual Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gal Chechik, Reut Tsarfaty, Tzuf Paz-Argaman, Yuval Atzmon","submitted_at":"2020-10-07T08:57:34Z","abstract_excerpt":"We study the problem of recognizing visual entities from the textual descriptions of their classes. Specifically, given birds' images with free-text descriptions of their species, we learn to classify images of previously-unseen species based on specie descriptions. This setup has been studied in the vision community under the name zero-shot learning from text, focusing on learning to transfer knowledge about visual aspects of birds from seen classes to previously-unseen ones. Here, we suggest focusing on the textual description and distilling from the description the most relevant information"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.03276","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/2010.03276/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":"2010.03276","created_at":"2026-07-05T01:41:11.514532+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.03276v1","created_at":"2026-07-05T01:41:11.514532+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.03276","created_at":"2026-07-05T01:41:11.514532+00:00"},{"alias_kind":"pith_short_12","alias_value":"2KBHVJ2PFTH7","created_at":"2026-07-05T01:41:11.514532+00:00"},{"alias_kind":"pith_short_16","alias_value":"2KBHVJ2PFTH7QGZ5","created_at":"2026-07-05T01:41:11.514532+00:00"},{"alias_kind":"pith_short_8","alias_value":"2KBHVJ2P","created_at":"2026-07-05T01:41:11.514532+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.11375","citing_title":"Text and Image Are Mutually Beneficial: Enhancing Training-Free Few-Shot Classification with CLIP","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2KBHVJ2PFTH7QGZ56FO3ER3SO3","json":"https://pith.science/pith/2KBHVJ2PFTH7QGZ56FO3ER3SO3.json","graph_json":"https://pith.science/api/pith-number/2KBHVJ2PFTH7QGZ56FO3ER3SO3/graph.json","events_json":"https://pith.science/api/pith-number/2KBHVJ2PFTH7QGZ56FO3ER3SO3/events.json","paper":"https://pith.science/paper/2KBHVJ2P"},"agent_actions":{"view_html":"https://pith.science/pith/2KBHVJ2PFTH7QGZ56FO3ER3SO3","download_json":"https://pith.science/pith/2KBHVJ2PFTH7QGZ56FO3ER3SO3.json","view_paper":"https://pith.science/paper/2KBHVJ2P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.03276&json=true","fetch_graph":"https://pith.science/api/pith-number/2KBHVJ2PFTH7QGZ56FO3ER3SO3/graph.json","fetch_events":"https://pith.science/api/pith-number/2KBHVJ2PFTH7QGZ56FO3ER3SO3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2KBHVJ2PFTH7QGZ56FO3ER3SO3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2KBHVJ2PFTH7QGZ56FO3ER3SO3/action/storage_attestation","attest_author":"https://pith.science/pith/2KBHVJ2PFTH7QGZ56FO3ER3SO3/action/author_attestation","sign_citation":"https://pith.science/pith/2KBHVJ2PFTH7QGZ56FO3ER3SO3/action/citation_signature","submit_replication":"https://pith.science/pith/2KBHVJ2PFTH7QGZ56FO3ER3SO3/action/replication_record"}},"created_at":"2026-07-05T01:41:11.514532+00:00","updated_at":"2026-07-05T01:41:11.514532+00:00"}