{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:N2AQWMAHHHK7F2ZQOXFXTZYWA3","short_pith_number":"pith:N2AQWMAH","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"},"canonical_sha256":"6e810b300739d5f2eb3075cb79e71606f2517720be07c5ae10d7cfa03e3946ff","source":{"kind":"arxiv","id":"2510.05213","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.05213","created_at":"2026-05-17T23:39:01Z"},{"alias_kind":"arxiv_version","alias_value":"2510.05213v2","created_at":"2026-05-17T23:39:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.05213","created_at":"2026-05-17T23:39:01Z"},{"alias_kind":"pith_short_12","alias_value":"N2AQWMAHHHK7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"N2AQWMAHHHK7F2ZQ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"N2AQWMAH","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:N2AQWMAHHHK7F2ZQOXFXTZYWA3","target":"record","payload":{"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"},"canonical_sha256":"6e810b300739d5f2eb3075cb79e71606f2517720be07c5ae10d7cfa03e3946ff","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"},"source_kind":"arxiv","source_id":"2510.05213","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HYkaLye/jg5D2T+TUyshUd22vhRpRTYOTGqJMxhHk4h1yXknhWIfqioO6Jb5Xro695wiXT+v3m918SFq/Ks7DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T04:11:29.352595Z"},"content_sha256":"7080591518e7f8a51af250d112522452c8182f7e92192c772d8f9124a931f0c8","schema_version":"1.0","event_id":"sha256:7080591518e7f8a51af250d112522452c8182f7e92192c772d8f9124a931f0c8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:N2AQWMAHHHK7F2ZQOXFXTZYWA3","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VCfP9oNI9EsEzL/yJ37RiF23obYnGEoDzVBGm76xjh90hDLIO9ULQms/DgNwPYYC7jJElNMhFIfqSZURdnEUBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T04:11:29.353275Z"},"content_sha256":"e5fe16723c36fad1e079b3d23a6e8dac7a07bfa446568d8e4f8481fb866a1b49","schema_version":"1.0","event_id":"sha256:e5fe16723c36fad1e079b3d23a6e8dac7a07bfa446568d8e4f8481fb866a1b49"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N2AQWMAHHHK7F2ZQOXFXTZYWA3/bundle.json","state_url":"https://pith.science/pith/N2AQWMAHHHK7F2ZQOXFXTZYWA3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N2AQWMAHHHK7F2ZQOXFXTZYWA3/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-26T04:11:29Z","links":{"resolver":"https://pith.science/pith/N2AQWMAHHHK7F2ZQOXFXTZYWA3","bundle":"https://pith.science/pith/N2AQWMAHHHK7F2ZQOXFXTZYWA3/bundle.json","state":"https://pith.science/pith/N2AQWMAHHHK7F2ZQOXFXTZYWA3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N2AQWMAHHHK7F2ZQOXFXTZYWA3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:N2AQWMAHHHK7F2ZQOXFXTZYWA3","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d160ae174457850927ac7c8ecbdf5a050e0731d4275eab44ef45d4892048eb8a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-10-06T18:00:43Z","title_canon_sha256":"f4fe917ce6077ef2c089709d6f511583995ab6df7aa2b22e5b3cdf7e71434a67"},"schema_version":"1.0","source":{"id":"2510.05213","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.05213","created_at":"2026-05-17T23:39:01Z"},{"alias_kind":"arxiv_version","alias_value":"2510.05213v2","created_at":"2026-05-17T23:39:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.05213","created_at":"2026-05-17T23:39:01Z"},{"alias_kind":"pith_short_12","alias_value":"N2AQWMAHHHK7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"N2AQWMAHHHK7F2ZQ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"N2AQWMAH","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:e5fe16723c36fad1e079b3d23a6e8dac7a07bfa446568d8e4f8481fb866a1b49","target":"graph","created_at":"2026-05-17T23:39:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Chensheng Peng, Haotian Lin, Jinghuan Shang, Lingfeng Sun, Masayoshi Tomizuka, Mingxiao Huo, Mingyu Ding, Mohit Bansal, Yixiao Wang, Yushi Du, Zhixuan Liang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-10-06T18:00:43Z","title":"VER: Vision Expert Transformer for Robot Learning via Foundation Distillation and Dynamic Routing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.05213","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7080591518e7f8a51af250d112522452c8182f7e92192c772d8f9124a931f0c8","target":"record","created_at":"2026-05-17T23:39:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d160ae174457850927ac7c8ecbdf5a050e0731d4275eab44ef45d4892048eb8a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-10-06T18:00:43Z","title_canon_sha256":"f4fe917ce6077ef2c089709d6f511583995ab6df7aa2b22e5b3cdf7e71434a67"},"schema_version":"1.0","source":{"id":"2510.05213","kind":"arxiv","version":2}},"canonical_sha256":"6e810b300739d5f2eb3075cb79e71606f2517720be07c5ae10d7cfa03e3946ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6e810b300739d5f2eb3075cb79e71606f2517720be07c5ae10d7cfa03e3946ff","first_computed_at":"2026-05-17T23:39:01.095446Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:01.095446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CpXizkpoC4cAxx94gw5VAvlBH8fNi86TbLQYj4Sp13DYSsZUttx1ybvusA3WuVuS3zOETUqe24Q6BmFBPNndCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:01.095982Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.05213","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7080591518e7f8a51af250d112522452c8182f7e92192c772d8f9124a931f0c8","sha256:e5fe16723c36fad1e079b3d23a6e8dac7a07bfa446568d8e4f8481fb866a1b49"],"state_sha256":"e0af6c4830eab9bc5c74b9e204b1f176c4c449ce13666ea5ac127dbd270ddbfe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xnYZgf6laY1f9RrijwcaBXhzKpli4Lutf0rhfgHwzX7zgqR65xxaP5jQotuh2h6dlMM9jv/9GY4zl4J/xWfyBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T04:11:29.356807Z","bundle_sha256":"a224fdaaf21b61b57a95157024f9f332b9144e3313e3e2279a3b70f2eef94fc7"}}