{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:K2JE7TLPSFJ6J5ZG3HFGED6PDU","short_pith_number":"pith:K2JE7TLP","schema_version":"1.0","canonical_sha256":"56924fcd6f9153e4f726d9ca620fcf1d32bceb12ff407f3930740d5577321c27","source":{"kind":"arxiv","id":"2607.18695","version":1},"attestation_state":"computed","paper":{"title":"Attributes Should Come from Images, Not Class Names: Distribution-Conditioned Attribute Selection for Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Deepak Pathak, Deva Ramanan, Gautam Rajendrakumar Gare, Jia Shi, John Galeotti, Zhiqiu Lin","submitted_at":"2026-07-21T04:34:24Z","abstract_excerpt":"A popular route to interpretable zero-shot classification asks a large language model (LLM) to describe each class name and prompts CLIP with the resulting descriptors. We show that these descriptors carry little visual evidence of their own: removing the class name from the prompt collapses ImageNet accuracy from 59.5% to 15.5%. The diagnosis is that the descriptors are conditioned on the label rather than on the images, so they describe the concept in general and mislead exactly when the data shifts; an LLM insists that strawberries are red, but every strawberry in ImageNet-Sketch is a color"},"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":"2607.18695","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-21T04:34:24Z","cross_cats_sorted":["cs.AI","cs.LG","eess.IV"],"title_canon_sha256":"a564e16f74d77926a08a90dd2865cd2c693e836ead69a5e966d92294a62d0ab9","abstract_canon_sha256":"8366c486b78a0374a37b3d913790aaf7a908ff29fd6cd282207e8c0043bc1219"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-22T01:23:07.149907Z","signature_b64":"FSrtSRieTtnlrOYIUVvTZfIk0TU+VkBzYrl10YR/cgZNBYWVYhCQHYJ5DJiYPqCEN0gpeeoTa1BAZgHUJ270BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56924fcd6f9153e4f726d9ca620fcf1d32bceb12ff407f3930740d5577321c27","last_reissued_at":"2026-07-22T01:23:07.149089Z","signature_status":"signed_v1","first_computed_at":"2026-07-22T01:23:07.149089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attributes Should Come from Images, Not Class Names: Distribution-Conditioned Attribute Selection for Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Deepak Pathak, Deva Ramanan, Gautam Rajendrakumar Gare, Jia Shi, John Galeotti, Zhiqiu Lin","submitted_at":"2026-07-21T04:34:24Z","abstract_excerpt":"A popular route to interpretable zero-shot classification asks a large language model (LLM) to describe each class name and prompts CLIP with the resulting descriptors. We show that these descriptors carry little visual evidence of their own: removing the class name from the prompt collapses ImageNet accuracy from 59.5% to 15.5%. The diagnosis is that the descriptors are conditioned on the label rather than on the images, so they describe the concept in general and mislead exactly when the data shifts; an LLM insists that strawberries are red, but every strawberry in ImageNet-Sketch is a color"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18695","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/2607.18695/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":"2607.18695","created_at":"2026-07-22T01:23:07.149503+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.18695v1","created_at":"2026-07-22T01:23:07.149503+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18695","created_at":"2026-07-22T01:23:07.149503+00:00"},{"alias_kind":"pith_short_12","alias_value":"K2JE7TLPSFJ6","created_at":"2026-07-22T01:23:07.149503+00:00"},{"alias_kind":"pith_short_16","alias_value":"K2JE7TLPSFJ6J5ZG","created_at":"2026-07-22T01:23:07.149503+00:00"},{"alias_kind":"pith_short_8","alias_value":"K2JE7TLP","created_at":"2026-07-22T01:23:07.149503+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/K2JE7TLPSFJ6J5ZG3HFGED6PDU","json":"https://pith.science/pith/K2JE7TLPSFJ6J5ZG3HFGED6PDU.json","graph_json":"https://pith.science/api/pith-number/K2JE7TLPSFJ6J5ZG3HFGED6PDU/graph.json","events_json":"https://pith.science/api/pith-number/K2JE7TLPSFJ6J5ZG3HFGED6PDU/events.json","paper":"https://pith.science/paper/K2JE7TLP"},"agent_actions":{"view_html":"https://pith.science/pith/K2JE7TLPSFJ6J5ZG3HFGED6PDU","download_json":"https://pith.science/pith/K2JE7TLPSFJ6J5ZG3HFGED6PDU.json","view_paper":"https://pith.science/paper/K2JE7TLP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.18695&json=true","fetch_graph":"https://pith.science/api/pith-number/K2JE7TLPSFJ6J5ZG3HFGED6PDU/graph.json","fetch_events":"https://pith.science/api/pith-number/K2JE7TLPSFJ6J5ZG3HFGED6PDU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K2JE7TLPSFJ6J5ZG3HFGED6PDU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K2JE7TLPSFJ6J5ZG3HFGED6PDU/action/storage_attestation","attest_author":"https://pith.science/pith/K2JE7TLPSFJ6J5ZG3HFGED6PDU/action/author_attestation","sign_citation":"https://pith.science/pith/K2JE7TLPSFJ6J5ZG3HFGED6PDU/action/citation_signature","submit_replication":"https://pith.science/pith/K2JE7TLPSFJ6J5ZG3HFGED6PDU/action/replication_record"}},"created_at":"2026-07-22T01:23:07.149503+00:00","updated_at":"2026-07-22T01:23:07.149503+00:00"}