{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HT27CRULO4WY726SCKMDTXLPFG","short_pith_number":"pith:HT27CRUL","schema_version":"1.0","canonical_sha256":"3cf5f1468b772d8febd2129839dd6f29916af72b7f0e00e8fc627fd456b58c36","source":{"kind":"arxiv","id":"2608.04196","version":1},"attestation_state":"computed","paper":{"title":"SiMDex: Mining Similar Egocentric Videos for Cross-Embodiment Dexterous Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Liqun Huang, Minjie Cai, Nie Lin, Ruoshi Wen, Sijin Chen, Takehiko Ohkawa, Wei Xu, Xiao Ma, Yiming Bao, Yoichi Sato, Yunfei Li, Zhengming Zhu, Zhuohang Li","submitted_at":"2026-08-04T19:55:12Z","abstract_excerpt":"Recent years have witnessed an explosive trend of scaling ego-centric human videos for robot manipulation, yet it remains unclear which data actually benefits dexterous manipulation. We present SiMDex, a similarity-based data mining framework that casts human data selection for VLA post-training in dexterous manipulation as a recommendation problem. For each robot demonstration, SiMDex employs a three-layer recall-ranking-re-ranking pipeline to extract task-relevant subsets from a pool of ~32M egocentric human samples, operating in a morphology-agnostic action space that requires no changes to"},"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":"2608.04196","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-08-04T19:55:12Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"101bd4c220fd83e5ab1e1c54d7a801a1393273550a1d70ba3915bf111a04445e","abstract_canon_sha256":"f7379f394c1018346b6f76c334a85ca43a0cf39b09b8d7c4c5d84a1d2f19aea1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:31:27.673837Z","signature_b64":"mwRXWHxT4gWCop4XUTK9swLrhjlJO1E/jydFJokVLwcW2z5cCwCS1FICt5ryJ9XmXIQCSk2V8yUgoBlpiStnBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3cf5f1468b772d8febd2129839dd6f29916af72b7f0e00e8fc627fd456b58c36","last_reissued_at":"2026-08-06T01:31:27.672361Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:31:27.672361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SiMDex: Mining Similar Egocentric Videos for Cross-Embodiment Dexterous Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Liqun Huang, Minjie Cai, Nie Lin, Ruoshi Wen, Sijin Chen, Takehiko Ohkawa, Wei Xu, Xiao Ma, Yiming Bao, Yoichi Sato, Yunfei Li, Zhengming Zhu, Zhuohang Li","submitted_at":"2026-08-04T19:55:12Z","abstract_excerpt":"Recent years have witnessed an explosive trend of scaling ego-centric human videos for robot manipulation, yet it remains unclear which data actually benefits dexterous manipulation. We present SiMDex, a similarity-based data mining framework that casts human data selection for VLA post-training in dexterous manipulation as a recommendation problem. For each robot demonstration, SiMDex employs a three-layer recall-ranking-re-ranking pipeline to extract task-relevant subsets from a pool of ~32M egocentric human samples, operating in a morphology-agnostic action space that requires no changes to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04196","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/2608.04196/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":"2608.04196","created_at":"2026-08-06T01:31:27.674215+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.04196v1","created_at":"2026-08-06T01:31:27.674215+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04196","created_at":"2026-08-06T01:31:27.674215+00:00"},{"alias_kind":"pith_short_12","alias_value":"HT27CRULO4WY","created_at":"2026-08-06T01:31:27.674215+00:00"},{"alias_kind":"pith_short_16","alias_value":"HT27CRULO4WY726S","created_at":"2026-08-06T01:31:27.674215+00:00"},{"alias_kind":"pith_short_8","alias_value":"HT27CRUL","created_at":"2026-08-06T01:31:27.674215+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/HT27CRULO4WY726SCKMDTXLPFG","json":"https://pith.science/pith/HT27CRULO4WY726SCKMDTXLPFG.json","graph_json":"https://pith.science/api/pith-number/HT27CRULO4WY726SCKMDTXLPFG/graph.json","events_json":"https://pith.science/api/pith-number/HT27CRULO4WY726SCKMDTXLPFG/events.json","paper":"https://pith.science/paper/HT27CRUL"},"agent_actions":{"view_html":"https://pith.science/pith/HT27CRULO4WY726SCKMDTXLPFG","download_json":"https://pith.science/pith/HT27CRULO4WY726SCKMDTXLPFG.json","view_paper":"https://pith.science/paper/HT27CRUL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.04196&json=true","fetch_graph":"https://pith.science/api/pith-number/HT27CRULO4WY726SCKMDTXLPFG/graph.json","fetch_events":"https://pith.science/api/pith-number/HT27CRULO4WY726SCKMDTXLPFG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HT27CRULO4WY726SCKMDTXLPFG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HT27CRULO4WY726SCKMDTXLPFG/action/storage_attestation","attest_author":"https://pith.science/pith/HT27CRULO4WY726SCKMDTXLPFG/action/author_attestation","sign_citation":"https://pith.science/pith/HT27CRULO4WY726SCKMDTXLPFG/action/citation_signature","submit_replication":"https://pith.science/pith/HT27CRULO4WY726SCKMDTXLPFG/action/replication_record"}},"created_at":"2026-08-06T01:31:27.674215+00:00","updated_at":"2026-08-06T01:31:27.674215+00:00"}