{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RXL6HYQAV4UJ6J52SBDRKNILJ6","short_pith_number":"pith:RXL6HYQA","schema_version":"1.0","canonical_sha256":"8dd7e3e200af289f27ba904715350b4f80456e2672cd7c5b5da406fb3aeb7aeb","source":{"kind":"arxiv","id":"2606.01600","version":1},"attestation_state":"computed","paper":{"title":"RoboTrustBench: Benchmarking the Trustworthiness of Video World Models for Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.RO"],"primary_cat":"cs.CV","authors_text":"Anirudha Majumdar, Bin Zhu, Huiqiong Li, Jiayu Wang, Jingjing Chen, Zhiting Mei","submitted_at":"2026-06-01T02:56:09Z","abstract_excerpt":"Video world models are increasingly used in robotic manipulation, yet existing benchmarks mostly evaluate them under valid, feasible, and safe instructions. We introduce RoboTrustBench, a benchmark for evaluating the trustworthiness of video world models under four scenarios: Normal, Constraint-Sensitive, Counterfactual, and Adversarial. Built from real-world DROID episodes, RoboTrustBench contains 1,207 expert-validated instruction-image pairs and a six-dimensional evaluation protocol with 13 fine-grained criteria. Evaluating seven representative video world models with human and MLLM assessm"},"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":"2606.01600","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T02:56:09Z","cross_cats_sorted":["cs.CL","cs.RO"],"title_canon_sha256":"13b742999711125ae682212c4147b99dcc2d667a0853571245a4d4d6737ec92c","abstract_canon_sha256":"049c9d9aad412c6f336a219ab5ec443956fa7ecdfa12b0418f4e74a238ef592a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:37.699236Z","signature_b64":"YfhiaVeyhDItysEXBfXhP26LekpbFVtxmqOdcMajCxv2b8m2OPsPaIbz5TCna7+MFyWAI2X42ShlEssx+utQDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8dd7e3e200af289f27ba904715350b4f80456e2672cd7c5b5da406fb3aeb7aeb","last_reissued_at":"2026-06-02T02:04:37.698819Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:37.698819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RoboTrustBench: Benchmarking the Trustworthiness of Video World Models for Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.RO"],"primary_cat":"cs.CV","authors_text":"Anirudha Majumdar, Bin Zhu, Huiqiong Li, Jiayu Wang, Jingjing Chen, Zhiting Mei","submitted_at":"2026-06-01T02:56:09Z","abstract_excerpt":"Video world models are increasingly used in robotic manipulation, yet existing benchmarks mostly evaluate them under valid, feasible, and safe instructions. We introduce RoboTrustBench, a benchmark for evaluating the trustworthiness of video world models under four scenarios: Normal, Constraint-Sensitive, Counterfactual, and Adversarial. Built from real-world DROID episodes, RoboTrustBench contains 1,207 expert-validated instruction-image pairs and a six-dimensional evaluation protocol with 13 fine-grained criteria. Evaluating seven representative video world models with human and MLLM assessm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01600","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/2606.01600/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":"2606.01600","created_at":"2026-06-02T02:04:37.698877+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01600v1","created_at":"2026-06-02T02:04:37.698877+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01600","created_at":"2026-06-02T02:04:37.698877+00:00"},{"alias_kind":"pith_short_12","alias_value":"RXL6HYQAV4UJ","created_at":"2026-06-02T02:04:37.698877+00:00"},{"alias_kind":"pith_short_16","alias_value":"RXL6HYQAV4UJ6J52","created_at":"2026-06-02T02:04:37.698877+00:00"},{"alias_kind":"pith_short_8","alias_value":"RXL6HYQA","created_at":"2026-06-02T02:04:37.698877+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/RXL6HYQAV4UJ6J52SBDRKNILJ6","json":"https://pith.science/pith/RXL6HYQAV4UJ6J52SBDRKNILJ6.json","graph_json":"https://pith.science/api/pith-number/RXL6HYQAV4UJ6J52SBDRKNILJ6/graph.json","events_json":"https://pith.science/api/pith-number/RXL6HYQAV4UJ6J52SBDRKNILJ6/events.json","paper":"https://pith.science/paper/RXL6HYQA"},"agent_actions":{"view_html":"https://pith.science/pith/RXL6HYQAV4UJ6J52SBDRKNILJ6","download_json":"https://pith.science/pith/RXL6HYQAV4UJ6J52SBDRKNILJ6.json","view_paper":"https://pith.science/paper/RXL6HYQA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01600&json=true","fetch_graph":"https://pith.science/api/pith-number/RXL6HYQAV4UJ6J52SBDRKNILJ6/graph.json","fetch_events":"https://pith.science/api/pith-number/RXL6HYQAV4UJ6J52SBDRKNILJ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RXL6HYQAV4UJ6J52SBDRKNILJ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RXL6HYQAV4UJ6J52SBDRKNILJ6/action/storage_attestation","attest_author":"https://pith.science/pith/RXL6HYQAV4UJ6J52SBDRKNILJ6/action/author_attestation","sign_citation":"https://pith.science/pith/RXL6HYQAV4UJ6J52SBDRKNILJ6/action/citation_signature","submit_replication":"https://pith.science/pith/RXL6HYQAV4UJ6J52SBDRKNILJ6/action/replication_record"}},"created_at":"2026-06-02T02:04:37.698877+00:00","updated_at":"2026-06-02T02:04:37.698877+00:00"}