{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6RVPIZG4EYLF4AMT72MOTLFMOX","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":"79c6443905b94f51047c4c80194a51863e1813a3910ce59c5ccff24006b5065d","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-24T06:03:42Z","title_canon_sha256":"1d3553f4645dc02bcd6649749b2557e87545ec07f36fcceecc1154720f9520ae"},"schema_version":"1.0","source":{"id":"2412.18194","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.18194","created_at":"2026-07-05T09:53:51Z"},{"alias_kind":"arxiv_version","alias_value":"2412.18194v1","created_at":"2026-07-05T09:53:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18194","created_at":"2026-07-05T09:53:51Z"},{"alias_kind":"pith_short_12","alias_value":"6RVPIZG4EYLF","created_at":"2026-07-05T09:53:51Z"},{"alias_kind":"pith_short_16","alias_value":"6RVPIZG4EYLF4AMT","created_at":"2026-07-05T09:53:51Z"},{"alias_kind":"pith_short_8","alias_value":"6RVPIZG4","created_at":"2026-07-05T09:53:51Z"}],"graph_snapshots":[{"event_id":"sha256:f4bf166db8405702cd68a713663d32eaca8fb759e3ffb65979e14fea1e494e14","target":"graph","created_at":"2026-07-05T09:53:51Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2412.18194/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"General-purposed embodied agents are designed to understand the users' natural instructions or intentions and act precisely to complete universal tasks. Recently, methods based on foundation models especially Vision-Language-Action models (VLAs) have shown a substantial potential to solve language-conditioned manipulation (LCM) tasks well. However, existing benchmarks do not adequately meet the needs of VLAs and relative algorithms. To better define such general-purpose tasks in the context of LLMs and advance the research in VLAs, we present VLABench, an open-source benchmark for evaluating u","authors_text":"Peiju Liu, Qinghui Gao, Shiduo Zhang, Xiaopeng Yu, Xipeng Qiu, Yuan Li, Yu-Gang Jiang, Zhangyue Yin, Zhaoye Fei, Zhe Xu, Zuxuan Wu","cross_cats":["cs.AI","cs.CL","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-24T06:03:42Z","title":"VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18194","kind":"arxiv","version":1},"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":"sha256:74edfdd5207188ef9e749df59a976a460782f5b24dd5c952333bfea1b8504d7a","target":"record","created_at":"2026-07-05T09:53:51Z","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":"79c6443905b94f51047c4c80194a51863e1813a3910ce59c5ccff24006b5065d","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-24T06:03:42Z","title_canon_sha256":"1d3553f4645dc02bcd6649749b2557e87545ec07f36fcceecc1154720f9520ae"},"schema_version":"1.0","source":{"id":"2412.18194","kind":"arxiv","version":1}},"canonical_sha256":"f46af464dc26165e0193fe98e9acac75faedf11d96b92043b1a8d58bb6b8fb8d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f46af464dc26165e0193fe98e9acac75faedf11d96b92043b1a8d58bb6b8fb8d","first_computed_at":"2026-07-05T09:53:51.369642Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:53:51.369642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2CdkUiGy9ccv3rm6IKBZH8fGIzoJbzg3ZlqT1zsekCHRjMASrrzkhYL3uSvbxHQKcJp+NNpM5s0T/+054l3UAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:53:51.370129Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.18194","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:74edfdd5207188ef9e749df59a976a460782f5b24dd5c952333bfea1b8504d7a","sha256:f4bf166db8405702cd68a713663d32eaca8fb759e3ffb65979e14fea1e494e14"],"state_sha256":"c654eb73f7355427b7ab5769d6027881793a8c905cca1c73732adaded9657204"}