{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:73CL5H45W6OF32YLOUKZTRYGTV","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":"15d1d70509f341e36c34907d9c3961af559252d22596412f3d800d45d3030eb3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-04-17T20:07:24Z","title_canon_sha256":"89ccaa633abddda05b27b635b5b1d4fa9af1ec05b0fffc8b95a714a9066b6c9e"},"schema_version":"1.0","source":{"id":"2304.08587","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.08587","created_at":"2026-07-05T06:22:03Z"},{"alias_kind":"arxiv_version","alias_value":"2304.08587v3","created_at":"2026-07-05T06:22:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.08587","created_at":"2026-07-05T06:22:03Z"},{"alias_kind":"pith_short_12","alias_value":"73CL5H45W6OF","created_at":"2026-07-05T06:22:03Z"},{"alias_kind":"pith_short_16","alias_value":"73CL5H45W6OF32YL","created_at":"2026-07-05T06:22:03Z"},{"alias_kind":"pith_short_8","alias_value":"73CL5H45","created_at":"2026-07-05T06:22:03Z"}],"graph_snapshots":[{"event_id":"sha256:47ad2e966cc2a839e57b6c2366dd9f024cc99c8bb8934eda55178bacc1ffed2b","target":"graph","created_at":"2026-07-05T06:22:03Z","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/2304.08587/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Classical planning systems have shown great advances in utilizing rule-based human knowledge to compute accurate plans for service robots, but they face challenges due to the strong assumptions of perfect perception and action executions. To tackle these challenges, one solution is to connect the symbolic states and actions generated by classical planners to the robot's sensory observations, thus closing the perception-action loop. This research proposes a visually-grounded planning framework, named TPVQA, which leverages Vision-Language Models (VLMs) to detect action failures and verify actio","authors_text":"Andy Kaminski, Chad Esselink, Hao Yang, Saeid Amiri, Shiqi Zhang, Xiaohan Zhang, Yan Ding","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-04-17T20:07:24Z","title":"Grounding Classical Task Planners via Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.08587","kind":"arxiv","version":3},"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":"sha256:0c75b8052f59be577739b9c5f43e21e2b8d2a5134501b8533b6c7efb4a7d2144","target":"record","created_at":"2026-07-05T06:22:03Z","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":"15d1d70509f341e36c34907d9c3961af559252d22596412f3d800d45d3030eb3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-04-17T20:07:24Z","title_canon_sha256":"89ccaa633abddda05b27b635b5b1d4fa9af1ec05b0fffc8b95a714a9066b6c9e"},"schema_version":"1.0","source":{"id":"2304.08587","kind":"arxiv","version":3}},"canonical_sha256":"fec4be9f9db79c5deb0b751599c7069d6cc27452a2f659212c83d60c395b30c3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fec4be9f9db79c5deb0b751599c7069d6cc27452a2f659212c83d60c395b30c3","first_computed_at":"2026-07-05T06:22:03.206638Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:22:03.206638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o47KMwX6SjmM5/rpGuIbPtLGkDuSiIoY+sQh++7QzP4L/uGJuh1H51x1ETRMDB0IGAlXhxuVeV8rJkfvQ4syAA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:22:03.207111Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.08587","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0c75b8052f59be577739b9c5f43e21e2b8d2a5134501b8533b6c7efb4a7d2144","sha256:47ad2e966cc2a839e57b6c2366dd9f024cc99c8bb8934eda55178bacc1ffed2b"],"state_sha256":"498159016ed9fcf1fb1b9778c03cc7ccdb319545aef286eff1dc2fc4c7a67a4b"}