{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:N2AQWMAHHHK7F2ZQOXFXTZYWA3","short_pith_number":"pith:N2AQWMAH","schema_version":"1.0","canonical_sha256":"6e810b300739d5f2eb3075cb79e71606f2517720be07c5ae10d7cfa03e3946ff","source":{"kind":"arxiv","id":"2510.05213","version":2},"attestation_state":"computed","paper":{"title":"VER: Vision Expert Transformer for Robot Learning via Foundation Distillation and Dynamic Routing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Chensheng Peng, Haotian Lin, Jinghuan Shang, Lingfeng Sun, Masayoshi Tomizuka, Mingxiao Huo, Mingyu Ding, Mohit Bansal, Yixiao Wang, Yushi Du, Zhixuan Liang","submitted_at":"2025-10-06T18:00:43Z","abstract_excerpt":"Pretrained vision foundation models (VFMs) advance robotic learning via rich visual representations, yet individual VFMs typically excel only in specific domains, limiting generality across tasks. Distilling multiple VFMs into a unified representation for policy can mitigate this limitation but often yields inflexible task-specific feature selection and requires costly full re-training to incorporate robot-domain knowledge. We propose VER, a Vision Expert transformer for Robot learning. During pretraining, VER distills multiple VFMs into a vision expert library. It then fine-tunes only a light"},"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":"2510.05213","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-10-06T18:00:43Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f4fe917ce6077ef2c089709d6f511583995ab6df7aa2b22e5b3cdf7e71434a67","abstract_canon_sha256":"d160ae174457850927ac7c8ecbdf5a050e0731d4275eab44ef45d4892048eb8a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:01.095982Z","signature_b64":"CpXizkpoC4cAxx94gw5VAvlBH8fNi86TbLQYj4Sp13DYSsZUttx1ybvusA3WuVuS3zOETUqe24Q6BmFBPNndCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e810b300739d5f2eb3075cb79e71606f2517720be07c5ae10d7cfa03e3946ff","last_reissued_at":"2026-05-17T23:39:01.095446Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:01.095446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VER: Vision Expert Transformer for Robot Learning via Foundation Distillation and Dynamic Routing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Chensheng Peng, Haotian Lin, Jinghuan Shang, Lingfeng Sun, Masayoshi Tomizuka, Mingxiao Huo, Mingyu Ding, Mohit Bansal, Yixiao Wang, Yushi Du, Zhixuan Liang","submitted_at":"2025-10-06T18:00:43Z","abstract_excerpt":"Pretrained vision foundation models (VFMs) advance robotic learning via rich visual representations, yet individual VFMs typically excel only in specific domains, limiting generality across tasks. Distilling multiple VFMs into a unified representation for policy can mitigate this limitation but often yields inflexible task-specific feature selection and requires costly full re-training to incorporate robot-domain knowledge. We propose VER, a Vision Expert transformer for Robot learning. During pretraining, VER distills multiple VFMs into a vision expert library. It then fine-tunes only a light"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.05213","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":""},"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":"2510.05213","created_at":"2026-05-17T23:39:01.095535+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.05213v2","created_at":"2026-05-17T23:39:01.095535+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.05213","created_at":"2026-05-17T23:39:01.095535+00:00"},{"alias_kind":"pith_short_12","alias_value":"N2AQWMAHHHK7","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"N2AQWMAHHHK7F2ZQ","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"N2AQWMAH","created_at":"2026-05-18T12:33:37.589309+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/N2AQWMAHHHK7F2ZQOXFXTZYWA3","json":"https://pith.science/pith/N2AQWMAHHHK7F2ZQOXFXTZYWA3.json","graph_json":"https://pith.science/api/pith-number/N2AQWMAHHHK7F2ZQOXFXTZYWA3/graph.json","events_json":"https://pith.science/api/pith-number/N2AQWMAHHHK7F2ZQOXFXTZYWA3/events.json","paper":"https://pith.science/paper/N2AQWMAH"},"agent_actions":{"view_html":"https://pith.science/pith/N2AQWMAHHHK7F2ZQOXFXTZYWA3","download_json":"https://pith.science/pith/N2AQWMAHHHK7F2ZQOXFXTZYWA3.json","view_paper":"https://pith.science/paper/N2AQWMAH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.05213&json=true","fetch_graph":"https://pith.science/api/pith-number/N2AQWMAHHHK7F2ZQOXFXTZYWA3/graph.json","fetch_events":"https://pith.science/api/pith-number/N2AQWMAHHHK7F2ZQOXFXTZYWA3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N2AQWMAHHHK7F2ZQOXFXTZYWA3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N2AQWMAHHHK7F2ZQOXFXTZYWA3/action/storage_attestation","attest_author":"https://pith.science/pith/N2AQWMAHHHK7F2ZQOXFXTZYWA3/action/author_attestation","sign_citation":"https://pith.science/pith/N2AQWMAHHHK7F2ZQOXFXTZYWA3/action/citation_signature","submit_replication":"https://pith.science/pith/N2AQWMAHHHK7F2ZQOXFXTZYWA3/action/replication_record"}},"created_at":"2026-05-17T23:39:01.095535+00:00","updated_at":"2026-05-17T23:39:01.095535+00:00"}