{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YDNTUVLV7VA2BYERBHSP3NJJFI","short_pith_number":"pith:YDNTUVLV","schema_version":"1.0","canonical_sha256":"c0db3a5575fd41a0e09109e4fdb5292a030db463b8a74574112cf8f9b6ffb483","source":{"kind":"arxiv","id":"2606.19584","version":1},"attestation_state":"computed","paper":{"title":"Language-Instructed Vision Embeddings for Controllable and Generalizable Perception","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengzhi Mao, Wen-Sheng Chu, Xudong Lin","submitted_at":"2026-06-17T20:39:04Z","abstract_excerpt":"Vision foundation models are typically trained as static feature extractors, placing the burden of task adaptation onto large downstream models. We propose an alternative paradigm: instead of solely feeding visual features into language models, we use language itself to dynamically guide the vision encoder. Our method, Language-Instructed Vision Embeddings (LIVE), leverages language as high-level guidance to produce task-centric embeddings at inference time, removing the need for task-specific retraining. This enables the encoder to focus on contextually relevant aspects of the input, yielding"},"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":"2606.19584","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T20:39:04Z","cross_cats_sorted":[],"title_canon_sha256":"0665193aab6fdbdd38a9eaae96fc05f9b3fff647db66af05f85cda258a6b2352","abstract_canon_sha256":"ec67dff31a15aa8978663cf593d6714c2fd92d6667d96e6350fb173c2b59a3be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:29.477975Z","signature_b64":"GfXZcWh8ahpYfDr3dxhNON6vxPpwEMNHI+OGqiE4abTMt4PNjNciYXGM5ms4ASZ1PJYR7BIOHwAo5DlzS2tCAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0db3a5575fd41a0e09109e4fdb5292a030db463b8a74574112cf8f9b6ffb483","last_reissued_at":"2026-06-19T16:12:29.477628Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:29.477628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language-Instructed Vision Embeddings for Controllable and Generalizable Perception","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengzhi Mao, Wen-Sheng Chu, Xudong Lin","submitted_at":"2026-06-17T20:39:04Z","abstract_excerpt":"Vision foundation models are typically trained as static feature extractors, placing the burden of task adaptation onto large downstream models. We propose an alternative paradigm: instead of solely feeding visual features into language models, we use language itself to dynamically guide the vision encoder. Our method, Language-Instructed Vision Embeddings (LIVE), leverages language as high-level guidance to produce task-centric embeddings at inference time, removing the need for task-specific retraining. This enables the encoder to focus on contextually relevant aspects of the input, yielding"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19584","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/2606.19584/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":"2606.19584","created_at":"2026-06-19T16:12:29.477690+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.19584v1","created_at":"2026-06-19T16:12:29.477690+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19584","created_at":"2026-06-19T16:12:29.477690+00:00"},{"alias_kind":"pith_short_12","alias_value":"YDNTUVLV7VA2","created_at":"2026-06-19T16:12:29.477690+00:00"},{"alias_kind":"pith_short_16","alias_value":"YDNTUVLV7VA2BYER","created_at":"2026-06-19T16:12:29.477690+00:00"},{"alias_kind":"pith_short_8","alias_value":"YDNTUVLV","created_at":"2026-06-19T16:12:29.477690+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/YDNTUVLV7VA2BYERBHSP3NJJFI","json":"https://pith.science/pith/YDNTUVLV7VA2BYERBHSP3NJJFI.json","graph_json":"https://pith.science/api/pith-number/YDNTUVLV7VA2BYERBHSP3NJJFI/graph.json","events_json":"https://pith.science/api/pith-number/YDNTUVLV7VA2BYERBHSP3NJJFI/events.json","paper":"https://pith.science/paper/YDNTUVLV"},"agent_actions":{"view_html":"https://pith.science/pith/YDNTUVLV7VA2BYERBHSP3NJJFI","download_json":"https://pith.science/pith/YDNTUVLV7VA2BYERBHSP3NJJFI.json","view_paper":"https://pith.science/paper/YDNTUVLV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.19584&json=true","fetch_graph":"https://pith.science/api/pith-number/YDNTUVLV7VA2BYERBHSP3NJJFI/graph.json","fetch_events":"https://pith.science/api/pith-number/YDNTUVLV7VA2BYERBHSP3NJJFI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YDNTUVLV7VA2BYERBHSP3NJJFI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YDNTUVLV7VA2BYERBHSP3NJJFI/action/storage_attestation","attest_author":"https://pith.science/pith/YDNTUVLV7VA2BYERBHSP3NJJFI/action/author_attestation","sign_citation":"https://pith.science/pith/YDNTUVLV7VA2BYERBHSP3NJJFI/action/citation_signature","submit_replication":"https://pith.science/pith/YDNTUVLV7VA2BYERBHSP3NJJFI/action/replication_record"}},"created_at":"2026-06-19T16:12:29.477690+00:00","updated_at":"2026-06-19T16:12:29.477690+00:00"}