{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HIQARWTPTDV2TTNKJWNYLDSH5Z","short_pith_number":"pith:HIQARWTP","schema_version":"1.0","canonical_sha256":"3a2008da6f98eba9cdaa4d9b858e47ee4a207e5c6ea89c948f1dba26a6f318b8","source":{"kind":"arxiv","id":"2606.13040","version":1},"attestation_state":"computed","paper":{"title":"RoboProcessBench: Benchmarking Process-Aware Understanding in Vision-Language Robotic Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chaofan Ma, Dayu Xia, Guangtao Zhai, Hua Chen, Huiting Ji, Jiezhang Cao, Yang Liu, Yao Mu, Yingjie Zhou, Yue Shi","submitted_at":"2026-06-11T08:20:42Z","abstract_excerpt":"Vision-language models (VLMs) are increasingly explored as visual critics, reward generators, and failure detectors in robotic manipulation. These roles implicitly require models to judge not only final task success, but also how a manipulation execution is physically and temporally progressing. However, existing evaluations fail to test whether VLMs possess fine-grained process understanding. To address this gap, we present RoboProcessBench, a benchmark for process-aware understanding in vision-language robotic manipulation. RoboProcessBench decomposes such capability into two complementary d"},"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":"2606.13040","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-11T08:20:42Z","cross_cats_sorted":[],"title_canon_sha256":"d1e80fa2d40756d73c81874e2ee2ccc45be2091e5346db79aa63711eb4f46daf","abstract_canon_sha256":"43199dc7218b66f7083aaa5b7de262c8690232dd56e16226ba1e9b40b2f4aebc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:09:38.075059Z","signature_b64":"EVvEV+WCxR7J2ixq14EZfbis1lZVFElFAtJ0WuwgSuGXLVmBzm41RDAII96Lo+xOtK0QffJCzEazmrZSeVIqAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a2008da6f98eba9cdaa4d9b858e47ee4a207e5c6ea89c948f1dba26a6f318b8","last_reissued_at":"2026-06-12T01:09:38.074620Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:09:38.074620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RoboProcessBench: Benchmarking Process-Aware Understanding in Vision-Language Robotic Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chaofan Ma, Dayu Xia, Guangtao Zhai, Hua Chen, Huiting Ji, Jiezhang Cao, Yang Liu, Yao Mu, Yingjie Zhou, Yue Shi","submitted_at":"2026-06-11T08:20:42Z","abstract_excerpt":"Vision-language models (VLMs) are increasingly explored as visual critics, reward generators, and failure detectors in robotic manipulation. These roles implicitly require models to judge not only final task success, but also how a manipulation execution is physically and temporally progressing. However, existing evaluations fail to test whether VLMs possess fine-grained process understanding. To address this gap, we present RoboProcessBench, a benchmark for process-aware understanding in vision-language robotic manipulation. RoboProcessBench decomposes such capability into two complementary d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.13040","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/2606.13040/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":"2606.13040","created_at":"2026-06-12T01:09:38.074688+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.13040v1","created_at":"2026-06-12T01:09:38.074688+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.13040","created_at":"2026-06-12T01:09:38.074688+00:00"},{"alias_kind":"pith_short_12","alias_value":"HIQARWTPTDV2","created_at":"2026-06-12T01:09:38.074688+00:00"},{"alias_kind":"pith_short_16","alias_value":"HIQARWTPTDV2TTNK","created_at":"2026-06-12T01:09:38.074688+00:00"},{"alias_kind":"pith_short_8","alias_value":"HIQARWTP","created_at":"2026-06-12T01:09:38.074688+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/HIQARWTPTDV2TTNKJWNYLDSH5Z","json":"https://pith.science/pith/HIQARWTPTDV2TTNKJWNYLDSH5Z.json","graph_json":"https://pith.science/api/pith-number/HIQARWTPTDV2TTNKJWNYLDSH5Z/graph.json","events_json":"https://pith.science/api/pith-number/HIQARWTPTDV2TTNKJWNYLDSH5Z/events.json","paper":"https://pith.science/paper/HIQARWTP"},"agent_actions":{"view_html":"https://pith.science/pith/HIQARWTPTDV2TTNKJWNYLDSH5Z","download_json":"https://pith.science/pith/HIQARWTPTDV2TTNKJWNYLDSH5Z.json","view_paper":"https://pith.science/paper/HIQARWTP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.13040&json=true","fetch_graph":"https://pith.science/api/pith-number/HIQARWTPTDV2TTNKJWNYLDSH5Z/graph.json","fetch_events":"https://pith.science/api/pith-number/HIQARWTPTDV2TTNKJWNYLDSH5Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HIQARWTPTDV2TTNKJWNYLDSH5Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HIQARWTPTDV2TTNKJWNYLDSH5Z/action/storage_attestation","attest_author":"https://pith.science/pith/HIQARWTPTDV2TTNKJWNYLDSH5Z/action/author_attestation","sign_citation":"https://pith.science/pith/HIQARWTPTDV2TTNKJWNYLDSH5Z/action/citation_signature","submit_replication":"https://pith.science/pith/HIQARWTPTDV2TTNKJWNYLDSH5Z/action/replication_record"}},"created_at":"2026-06-12T01:09:38.074688+00:00","updated_at":"2026-06-12T01:09:38.074688+00:00"}