{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6BBIIR7Y7Y2GMOKTHKR3FJC2CA","short_pith_number":"pith:6BBIIR7Y","schema_version":"1.0","canonical_sha256":"f0428447f8fe346639533aa3b2a45a1003c695404fe0e7d5ec927d8f9f33e367","source":{"kind":"arxiv","id":"2603.12824","version":2},"attestation_state":"computed","paper":{"title":"NanoVDR: Distilling a 2B Vision-Language Retriever into a 70M Text-Only Encoder for Visual Document Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.IR","authors_text":"Yao Zhang, Yu Xiao, Zhuchenyang Liu","submitted_at":"2026-03-13T09:24:23Z","abstract_excerpt":"Vision-Language Model (VLM) based retrievers have advanced visual document retrieval (VDR) to impressive quality. They require the same multi-billion parameter encoder for both document indexing and query encoding, incurring high latency and GPU dependence even for plain-text queries. We observe that this design is unnecessarily symmetric: documents are visually complex and demand strong visual understanding, whereas queries are just short text strings. NanoVDR exploits this query--document asymmetry by decoupling the two encoding paths: a frozen 2B VLM teacher indexes documents offline, while"},"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":"2603.12824","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-03-13T09:24:23Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"633f29593bcc8eaa7d75f7fbb3caf775a411af72272166b3e512668666ee2428","abstract_canon_sha256":"908fd43c863d31a856fcd33408ffc6bee14000a3b52659f75256fe68f9f4c481"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:05:12.030006Z","signature_b64":"ktpRbAOiRTcuvIXtMQH5XPKXZjQtSuvP0t8pYMSuP4L3Yy5vejuXSHdjyBwYh5qmgQusT+uN44tZs9ZoLvYGBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0428447f8fe346639533aa3b2a45a1003c695404fe0e7d5ec927d8f9f33e367","last_reissued_at":"2026-05-28T01:05:12.029485Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:05:12.029485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NanoVDR: Distilling a 2B Vision-Language Retriever into a 70M Text-Only Encoder for Visual Document Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.IR","authors_text":"Yao Zhang, Yu Xiao, Zhuchenyang Liu","submitted_at":"2026-03-13T09:24:23Z","abstract_excerpt":"Vision-Language Model (VLM) based retrievers have advanced visual document retrieval (VDR) to impressive quality. They require the same multi-billion parameter encoder for both document indexing and query encoding, incurring high latency and GPU dependence even for plain-text queries. We observe that this design is unnecessarily symmetric: documents are visually complex and demand strong visual understanding, whereas queries are just short text strings. NanoVDR exploits this query--document asymmetry by decoupling the two encoding paths: a frozen 2B VLM teacher indexes documents offline, while"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.12824","kind":"arxiv","version":2},"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/2603.12824/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":"2603.12824","created_at":"2026-05-28T01:05:12.029536+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.12824v2","created_at":"2026-05-28T01:05:12.029536+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.12824","created_at":"2026-05-28T01:05:12.029536+00:00"},{"alias_kind":"pith_short_12","alias_value":"6BBIIR7Y7Y2G","created_at":"2026-05-28T01:05:12.029536+00:00"},{"alias_kind":"pith_short_16","alias_value":"6BBIIR7Y7Y2GMOKT","created_at":"2026-05-28T01:05:12.029536+00:00"},{"alias_kind":"pith_short_8","alias_value":"6BBIIR7Y","created_at":"2026-05-28T01:05:12.029536+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/6BBIIR7Y7Y2GMOKTHKR3FJC2CA","json":"https://pith.science/pith/6BBIIR7Y7Y2GMOKTHKR3FJC2CA.json","graph_json":"https://pith.science/api/pith-number/6BBIIR7Y7Y2GMOKTHKR3FJC2CA/graph.json","events_json":"https://pith.science/api/pith-number/6BBIIR7Y7Y2GMOKTHKR3FJC2CA/events.json","paper":"https://pith.science/paper/6BBIIR7Y"},"agent_actions":{"view_html":"https://pith.science/pith/6BBIIR7Y7Y2GMOKTHKR3FJC2CA","download_json":"https://pith.science/pith/6BBIIR7Y7Y2GMOKTHKR3FJC2CA.json","view_paper":"https://pith.science/paper/6BBIIR7Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.12824&json=true","fetch_graph":"https://pith.science/api/pith-number/6BBIIR7Y7Y2GMOKTHKR3FJC2CA/graph.json","fetch_events":"https://pith.science/api/pith-number/6BBIIR7Y7Y2GMOKTHKR3FJC2CA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6BBIIR7Y7Y2GMOKTHKR3FJC2CA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6BBIIR7Y7Y2GMOKTHKR3FJC2CA/action/storage_attestation","attest_author":"https://pith.science/pith/6BBIIR7Y7Y2GMOKTHKR3FJC2CA/action/author_attestation","sign_citation":"https://pith.science/pith/6BBIIR7Y7Y2GMOKTHKR3FJC2CA/action/citation_signature","submit_replication":"https://pith.science/pith/6BBIIR7Y7Y2GMOKTHKR3FJC2CA/action/replication_record"}},"created_at":"2026-05-28T01:05:12.029536+00:00","updated_at":"2026-05-28T01:05:12.029536+00:00"}