{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7OQXIGDO5EBOMXEGVLVDJKQ5G3","short_pith_number":"pith:7OQXIGDO","schema_version":"1.0","canonical_sha256":"fba174186ee902e65c86aaea34aa1d36d66ae7f32e4e88e9b9b51a724497e58b","source":{"kind":"arxiv","id":"2606.08881","version":1},"attestation_state":"computed","paper":{"title":"Benchmarking Vision-Language-Action Models on SO-101: Failure and Recovery Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Xinchuan Qiu, Yi Yu","submitted_at":"2026-06-07T23:39:03Z","abstract_excerpt":"Vision-Language-Action (VLA) models have demonstrated strong generalization in robotic manipulation, yet existing evaluations are primarily conducted in simulation or on expensive robotic platforms, leaving their robustness on affordable real-world robots largely unexplored. We present a standardized real-world benchmark for evaluating representative VLA and imitation learning policies on the low-cost SO-101 robotic platform. The benchmark comprises four representative manipulation tasks together with unified evaluation protocols, enabling systematic comparison under embodiment uncertainty. Us"},"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":"2606.08881","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-07T23:39:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"44ce935d76c3958dd73e30eb73ee00b7af4029c3c7048d41bbca890d033a60a2","abstract_canon_sha256":"0f9ca95d8a55aa71132a04044d8984533cb117dab8b1a84b4e60b86e1ba2fed6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:07:45.111242Z","signature_b64":"xdpa+iM6TfSIR5PinTGHtMF495s8hAN6YtQ9sW1tdbB/gLRPuMf/zSfcDd0ZJVHumLxCuFe2BMuX7qdMhT8qDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fba174186ee902e65c86aaea34aa1d36d66ae7f32e4e88e9b9b51a724497e58b","last_reissued_at":"2026-06-09T02:07:45.110463Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:07:45.110463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Vision-Language-Action Models on SO-101: Failure and Recovery Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Xinchuan Qiu, Yi Yu","submitted_at":"2026-06-07T23:39:03Z","abstract_excerpt":"Vision-Language-Action (VLA) models have demonstrated strong generalization in robotic manipulation, yet existing evaluations are primarily conducted in simulation or on expensive robotic platforms, leaving their robustness on affordable real-world robots largely unexplored. We present a standardized real-world benchmark for evaluating representative VLA and imitation learning policies on the low-cost SO-101 robotic platform. The benchmark comprises four representative manipulation tasks together with unified evaluation protocols, enabling systematic comparison under embodiment uncertainty. Us"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08881","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/2606.08881/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":"2606.08881","created_at":"2026-06-09T02:07:45.110585+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.08881v1","created_at":"2026-06-09T02:07:45.110585+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08881","created_at":"2026-06-09T02:07:45.110585+00:00"},{"alias_kind":"pith_short_12","alias_value":"7OQXIGDO5EBO","created_at":"2026-06-09T02:07:45.110585+00:00"},{"alias_kind":"pith_short_16","alias_value":"7OQXIGDO5EBOMXEG","created_at":"2026-06-09T02:07:45.110585+00:00"},{"alias_kind":"pith_short_8","alias_value":"7OQXIGDO","created_at":"2026-06-09T02:07:45.110585+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/7OQXIGDO5EBOMXEGVLVDJKQ5G3","json":"https://pith.science/pith/7OQXIGDO5EBOMXEGVLVDJKQ5G3.json","graph_json":"https://pith.science/api/pith-number/7OQXIGDO5EBOMXEGVLVDJKQ5G3/graph.json","events_json":"https://pith.science/api/pith-number/7OQXIGDO5EBOMXEGVLVDJKQ5G3/events.json","paper":"https://pith.science/paper/7OQXIGDO"},"agent_actions":{"view_html":"https://pith.science/pith/7OQXIGDO5EBOMXEGVLVDJKQ5G3","download_json":"https://pith.science/pith/7OQXIGDO5EBOMXEGVLVDJKQ5G3.json","view_paper":"https://pith.science/paper/7OQXIGDO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.08881&json=true","fetch_graph":"https://pith.science/api/pith-number/7OQXIGDO5EBOMXEGVLVDJKQ5G3/graph.json","fetch_events":"https://pith.science/api/pith-number/7OQXIGDO5EBOMXEGVLVDJKQ5G3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7OQXIGDO5EBOMXEGVLVDJKQ5G3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7OQXIGDO5EBOMXEGVLVDJKQ5G3/action/storage_attestation","attest_author":"https://pith.science/pith/7OQXIGDO5EBOMXEGVLVDJKQ5G3/action/author_attestation","sign_citation":"https://pith.science/pith/7OQXIGDO5EBOMXEGVLVDJKQ5G3/action/citation_signature","submit_replication":"https://pith.science/pith/7OQXIGDO5EBOMXEGVLVDJKQ5G3/action/replication_record"}},"created_at":"2026-06-09T02:07:45.110585+00:00","updated_at":"2026-06-09T02:07:45.110585+00:00"}