{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VINQ4UHU554RFS3727QJL4QWKF","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":"cdd283665dd7aa7b117d6b67dfd334fb88235f792b59c1fe77f6781fd5c8be95","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-11-02T03:32:30Z","title_canon_sha256":"97bb3d0fdfdb534b2f16a1589d6cb38a39803ab6f791289428de8fe5c7c6530a"},"schema_version":"1.0","source":{"id":"2311.00967","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.00967","created_at":"2026-07-05T07:47:06Z"},{"alias_kind":"arxiv_version","alias_value":"2311.00967v2","created_at":"2026-07-05T07:47:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00967","created_at":"2026-07-05T07:47:06Z"},{"alias_kind":"pith_short_12","alias_value":"VINQ4UHU554R","created_at":"2026-07-05T07:47:06Z"},{"alias_kind":"pith_short_16","alias_value":"VINQ4UHU554RFS37","created_at":"2026-07-05T07:47:06Z"},{"alias_kind":"pith_short_8","alias_value":"VINQ4UHU","created_at":"2026-07-05T07:47:06Z"}],"graph_snapshots":[{"event_id":"sha256:f00e92f4cb6584bdac0db6d1688a5a33e122e584983b65ccc151c458e390f031","target":"graph","created_at":"2026-07-05T07:47:06Z","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/2311.00967/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are accelerating the development of language-guided robot planners. Meanwhile, symbolic planners offer the advantage of interpretability. This paper proposes a new task that bridges these two trends, namely, multimodal planning problem specification. The aim is to generate a problem description (PD), a machine-readable file used by the planners to find a plan. By generating PDs from language instruction and scene observation, we can drive symbolic planners in a language-guided framework. We propose a Vision-Language Interpreter (ViLaIn), a new framework that genera","authors_text":"Atsushi Hashimoto, Cristian C. Beltran-Hernandez, Kazutoshi Tanaka, Keisuke Shirai, Kento Kawaharazuka, Masashi Hamaya, Shinsuke Mori, Shohei Tanaka, Yoshitaka Ushiku","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-11-02T03:32:30Z","title":"Vision-Language Interpreter for Robot Task Planning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00967","kind":"arxiv","version":2},"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":"sha256:6bd4d38b94a2d4655b4b55c1ac9764e9f51a276d93073ee36dba3af0e11a7fab","target":"record","created_at":"2026-07-05T07:47:06Z","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":"cdd283665dd7aa7b117d6b67dfd334fb88235f792b59c1fe77f6781fd5c8be95","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-11-02T03:32:30Z","title_canon_sha256":"97bb3d0fdfdb534b2f16a1589d6cb38a39803ab6f791289428de8fe5c7c6530a"},"schema_version":"1.0","source":{"id":"2311.00967","kind":"arxiv","version":2}},"canonical_sha256":"aa1b0e50f4ef7912cb7fd7e095f216516457b5deea0a9208e1ea7225b56b2763","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa1b0e50f4ef7912cb7fd7e095f216516457b5deea0a9208e1ea7225b56b2763","first_computed_at":"2026-07-05T07:47:06.413656Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:47:06.413656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5TMV6yDVPdwanGB1lQdcBs6Yc1LbJjkVC19HaIreENXBVomPe96WDxgv+xdWKOPc6Kf6+STaloobB76grSCKBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:47:06.414023Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.00967","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6bd4d38b94a2d4655b4b55c1ac9764e9f51a276d93073ee36dba3af0e11a7fab","sha256:f00e92f4cb6584bdac0db6d1688a5a33e122e584983b65ccc151c458e390f031"],"state_sha256":"36cae64a867d1ea964376eb5b498b4db70c8930559e6724aa492f576f042b489"}