{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6VAU6DGZJC2H3LJCH7OVNCI3TS","short_pith_number":"pith:6VAU6DGZ","schema_version":"1.0","canonical_sha256":"f5414f0cd948b47dad223fdd56891b9cbb4fa8b7632bbc4493ad1e413259fb23","source":{"kind":"arxiv","id":"2202.08926","version":1},"attestation_state":"computed","paper":{"title":"On Guiding Visual Attention with Language Specification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anna Rohrbach, Joseph Gonzalez, Keyan Nasseri, Lisa Dunlap, Suzanne Petryk, Trevor Darrell","submitted_at":"2022-02-17T22:40:19Z","abstract_excerpt":"While real world challenges typically define visual categories with language words or phrases, most visual classification methods define categories with numerical indices. However, the language specification of the classes provides an especially useful prior for biased and noisy datasets, where it can help disambiguate what features are task-relevant. Recently, large-scale multimodal models have been shown to recognize a wide variety of high-level concepts from a language specification even without additional image training data, but they are often unable to distinguish classes for more fine-g"},"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":"2202.08926","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-02-17T22:40:19Z","cross_cats_sorted":[],"title_canon_sha256":"a307c642cde88888b1a9586944681c49efcf313090153eebda0f3a080ec4207c","abstract_canon_sha256":"c6ce74327012aacc421209644205663873b78aa55bfd36ad6e426f2b3478c566"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:58:07.910899Z","signature_b64":"lFim9d/LErdo+QuRYI2EtmhIo0fo3Tk6tvXdNlIuHK9yAc4tul6qBd7UWwOTA9F/McYdVTVerKGhaQVRP6/lCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5414f0cd948b47dad223fdd56891b9cbb4fa8b7632bbc4493ad1e413259fb23","last_reissued_at":"2026-07-05T03:58:07.910492Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:58:07.910492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Guiding Visual Attention with Language Specification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anna Rohrbach, Joseph Gonzalez, Keyan Nasseri, Lisa Dunlap, Suzanne Petryk, Trevor Darrell","submitted_at":"2022-02-17T22:40:19Z","abstract_excerpt":"While real world challenges typically define visual categories with language words or phrases, most visual classification methods define categories with numerical indices. However, the language specification of the classes provides an especially useful prior for biased and noisy datasets, where it can help disambiguate what features are task-relevant. Recently, large-scale multimodal models have been shown to recognize a wide variety of high-level concepts from a language specification even without additional image training data, but they are often unable to distinguish classes for more fine-g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.08926","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/2202.08926/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":"2202.08926","created_at":"2026-07-05T03:58:07.910567+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.08926v1","created_at":"2026-07-05T03:58:07.910567+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.08926","created_at":"2026-07-05T03:58:07.910567+00:00"},{"alias_kind":"pith_short_12","alias_value":"6VAU6DGZJC2H","created_at":"2026-07-05T03:58:07.910567+00:00"},{"alias_kind":"pith_short_16","alias_value":"6VAU6DGZJC2H3LJC","created_at":"2026-07-05T03:58:07.910567+00:00"},{"alias_kind":"pith_short_8","alias_value":"6VAU6DGZ","created_at":"2026-07-05T03:58:07.910567+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/6VAU6DGZJC2H3LJCH7OVNCI3TS","json":"https://pith.science/pith/6VAU6DGZJC2H3LJCH7OVNCI3TS.json","graph_json":"https://pith.science/api/pith-number/6VAU6DGZJC2H3LJCH7OVNCI3TS/graph.json","events_json":"https://pith.science/api/pith-number/6VAU6DGZJC2H3LJCH7OVNCI3TS/events.json","paper":"https://pith.science/paper/6VAU6DGZ"},"agent_actions":{"view_html":"https://pith.science/pith/6VAU6DGZJC2H3LJCH7OVNCI3TS","download_json":"https://pith.science/pith/6VAU6DGZJC2H3LJCH7OVNCI3TS.json","view_paper":"https://pith.science/paper/6VAU6DGZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.08926&json=true","fetch_graph":"https://pith.science/api/pith-number/6VAU6DGZJC2H3LJCH7OVNCI3TS/graph.json","fetch_events":"https://pith.science/api/pith-number/6VAU6DGZJC2H3LJCH7OVNCI3TS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6VAU6DGZJC2H3LJCH7OVNCI3TS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6VAU6DGZJC2H3LJCH7OVNCI3TS/action/storage_attestation","attest_author":"https://pith.science/pith/6VAU6DGZJC2H3LJCH7OVNCI3TS/action/author_attestation","sign_citation":"https://pith.science/pith/6VAU6DGZJC2H3LJCH7OVNCI3TS/action/citation_signature","submit_replication":"https://pith.science/pith/6VAU6DGZJC2H3LJCH7OVNCI3TS/action/replication_record"}},"created_at":"2026-07-05T03:58:07.910567+00:00","updated_at":"2026-07-05T03:58:07.910567+00:00"}