{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SGQTYOWKA7RW7HMWWSNQSTWOTZ","short_pith_number":"pith:SGQTYOWK","schema_version":"1.0","canonical_sha256":"91a13c3aca07e36f9d96b49b094ece9e4a1aa648d23411685b80b7cdcde2efb0","source":{"kind":"arxiv","id":"2606.17200","version":1},"attestation_state":"computed","paper":{"title":"ACE-Ego-0: Unifying Egocentric Human and Robotic Data for VLA Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chunxiao Liu, Ganlong Zhao, Guoquan Ye, Hao Li, Haotian Hou, Hongsheng Li, Jianbo Liu, Siyuan Huang, Tongyan Fang, Xiaogang Wang, Yufei Liu","submitted_at":"2026-06-15T18:40:18Z","abstract_excerpt":"Vision-Language-Action (VLA) models benefit from large-scale and diverse embodied data, yet scaling robot trajectory collection is costly and labor-intensive. Recent advances show that large-scale egocentric human videos provide complementary real-world supervision in pretraining. However, joint training on human and robot data remains challenging due to divergences in action spaces, embodiment structures, temporal dynamics, and supervision quality. We introduce ACE-EGO-0, a unified VLA pretraining framework jointly leveraging heterogeneous data sources. To extract large-scale pretraining supe"},"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":"2606.17200","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-15T18:40:18Z","cross_cats_sorted":[],"title_canon_sha256":"1e50d04a9b4d19c32aedf78269749ae640a678cff73c0dbb5a9506ab5828bf4d","abstract_canon_sha256":"5ce7b6d8a73b73585cce0626c8c692377a0eec7a471916c2fe0e29867b494e5d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:05.769560Z","signature_b64":"f4c1MB1c+iN2Ng91zSCZHRuMKs1OJNGtQ2PoyptRijkfRXgOuEMOFZD30eifuwwDjwNIy37Dd43yZ6eINWfCDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91a13c3aca07e36f9d96b49b094ece9e4a1aa648d23411685b80b7cdcde2efb0","last_reissued_at":"2026-06-19T16:10:05.769133Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:05.769133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ACE-Ego-0: Unifying Egocentric Human and Robotic Data for VLA Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chunxiao Liu, Ganlong Zhao, Guoquan Ye, Hao Li, Haotian Hou, Hongsheng Li, Jianbo Liu, Siyuan Huang, Tongyan Fang, Xiaogang Wang, Yufei Liu","submitted_at":"2026-06-15T18:40:18Z","abstract_excerpt":"Vision-Language-Action (VLA) models benefit from large-scale and diverse embodied data, yet scaling robot trajectory collection is costly and labor-intensive. Recent advances show that large-scale egocentric human videos provide complementary real-world supervision in pretraining. However, joint training on human and robot data remains challenging due to divergences in action spaces, embodiment structures, temporal dynamics, and supervision quality. We introduce ACE-EGO-0, a unified VLA pretraining framework jointly leveraging heterogeneous data sources. To extract large-scale pretraining supe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17200","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/2606.17200/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":"2606.17200","created_at":"2026-06-19T16:10:05.769192+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.17200v1","created_at":"2026-06-19T16:10:05.769192+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17200","created_at":"2026-06-19T16:10:05.769192+00:00"},{"alias_kind":"pith_short_12","alias_value":"SGQTYOWKA7RW","created_at":"2026-06-19T16:10:05.769192+00:00"},{"alias_kind":"pith_short_16","alias_value":"SGQTYOWKA7RW7HMW","created_at":"2026-06-19T16:10:05.769192+00:00"},{"alias_kind":"pith_short_8","alias_value":"SGQTYOWK","created_at":"2026-06-19T16:10:05.769192+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/SGQTYOWKA7RW7HMWWSNQSTWOTZ","json":"https://pith.science/pith/SGQTYOWKA7RW7HMWWSNQSTWOTZ.json","graph_json":"https://pith.science/api/pith-number/SGQTYOWKA7RW7HMWWSNQSTWOTZ/graph.json","events_json":"https://pith.science/api/pith-number/SGQTYOWKA7RW7HMWWSNQSTWOTZ/events.json","paper":"https://pith.science/paper/SGQTYOWK"},"agent_actions":{"view_html":"https://pith.science/pith/SGQTYOWKA7RW7HMWWSNQSTWOTZ","download_json":"https://pith.science/pith/SGQTYOWKA7RW7HMWWSNQSTWOTZ.json","view_paper":"https://pith.science/paper/SGQTYOWK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.17200&json=true","fetch_graph":"https://pith.science/api/pith-number/SGQTYOWKA7RW7HMWWSNQSTWOTZ/graph.json","fetch_events":"https://pith.science/api/pith-number/SGQTYOWKA7RW7HMWWSNQSTWOTZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SGQTYOWKA7RW7HMWWSNQSTWOTZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SGQTYOWKA7RW7HMWWSNQSTWOTZ/action/storage_attestation","attest_author":"https://pith.science/pith/SGQTYOWKA7RW7HMWWSNQSTWOTZ/action/author_attestation","sign_citation":"https://pith.science/pith/SGQTYOWKA7RW7HMWWSNQSTWOTZ/action/citation_signature","submit_replication":"https://pith.science/pith/SGQTYOWKA7RW7HMWWSNQSTWOTZ/action/replication_record"}},"created_at":"2026-06-19T16:10:05.769192+00:00","updated_at":"2026-06-19T16:10:05.769192+00:00"}