{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VINQ4UHU554RFS3727QJL4QWKF","short_pith_number":"pith:VINQ4UHU","schema_version":"1.0","canonical_sha256":"aa1b0e50f4ef7912cb7fd7e095f216516457b5deea0a9208e1ea7225b56b2763","source":{"kind":"arxiv","id":"2311.00967","version":2},"attestation_state":"computed","paper":{"title":"Vision-Language Interpreter for Robot Task Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.RO","authors_text":"Atsushi Hashimoto, Cristian C. Beltran-Hernandez, Kazutoshi Tanaka, Keisuke Shirai, Kento Kawaharazuka, Masashi Hamaya, Shinsuke Mori, Shohei Tanaka, Yoshitaka Ushiku","submitted_at":"2023-11-02T03:32:30Z","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"},"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":"2311.00967","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-11-02T03:32:30Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"97bb3d0fdfdb534b2f16a1589d6cb38a39803ab6f791289428de8fe5c7c6530a","abstract_canon_sha256":"cdd283665dd7aa7b117d6b67dfd334fb88235f792b59c1fe77f6781fd5c8be95"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:47:06.414023Z","signature_b64":"5TMV6yDVPdwanGB1lQdcBs6Yc1LbJjkVC19HaIreENXBVomPe96WDxgv+xdWKOPc6Kf6+STaloobB76grSCKBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa1b0e50f4ef7912cb7fd7e095f216516457b5deea0a9208e1ea7225b56b2763","last_reissued_at":"2026-07-05T07:47:06.413656Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:47:06.413656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vision-Language Interpreter for Robot Task Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.RO","authors_text":"Atsushi Hashimoto, Cristian C. Beltran-Hernandez, Kazutoshi Tanaka, Keisuke Shirai, Kento Kawaharazuka, Masashi Hamaya, Shinsuke Mori, Shohei Tanaka, Yoshitaka Ushiku","submitted_at":"2023-11-02T03:32:30Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00967","kind":"arxiv","version":2},"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/2311.00967/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":"2311.00967","created_at":"2026-07-05T07:47:06.413711+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.00967v2","created_at":"2026-07-05T07:47:06.413711+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00967","created_at":"2026-07-05T07:47:06.413711+00:00"},{"alias_kind":"pith_short_12","alias_value":"VINQ4UHU554R","created_at":"2026-07-05T07:47:06.413711+00:00"},{"alias_kind":"pith_short_16","alias_value":"VINQ4UHU554RFS37","created_at":"2026-07-05T07:47:06.413711+00:00"},{"alias_kind":"pith_short_8","alias_value":"VINQ4UHU","created_at":"2026-07-05T07:47:06.413711+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/VINQ4UHU554RFS3727QJL4QWKF","json":"https://pith.science/pith/VINQ4UHU554RFS3727QJL4QWKF.json","graph_json":"https://pith.science/api/pith-number/VINQ4UHU554RFS3727QJL4QWKF/graph.json","events_json":"https://pith.science/api/pith-number/VINQ4UHU554RFS3727QJL4QWKF/events.json","paper":"https://pith.science/paper/VINQ4UHU"},"agent_actions":{"view_html":"https://pith.science/pith/VINQ4UHU554RFS3727QJL4QWKF","download_json":"https://pith.science/pith/VINQ4UHU554RFS3727QJL4QWKF.json","view_paper":"https://pith.science/paper/VINQ4UHU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.00967&json=true","fetch_graph":"https://pith.science/api/pith-number/VINQ4UHU554RFS3727QJL4QWKF/graph.json","fetch_events":"https://pith.science/api/pith-number/VINQ4UHU554RFS3727QJL4QWKF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VINQ4UHU554RFS3727QJL4QWKF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VINQ4UHU554RFS3727QJL4QWKF/action/storage_attestation","attest_author":"https://pith.science/pith/VINQ4UHU554RFS3727QJL4QWKF/action/author_attestation","sign_citation":"https://pith.science/pith/VINQ4UHU554RFS3727QJL4QWKF/action/citation_signature","submit_replication":"https://pith.science/pith/VINQ4UHU554RFS3727QJL4QWKF/action/replication_record"}},"created_at":"2026-07-05T07:47:06.413711+00:00","updated_at":"2026-07-05T07:47:06.413711+00:00"}