{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XW5FCNOEYWW7RKBVVUXM4Q37XQ","short_pith_number":"pith:XW5FCNOE","schema_version":"1.0","canonical_sha256":"bdba5135c4c5adf8a835ad2ece437fbc2d0114cbfff9be402b531d83d173aad8","source":{"kind":"arxiv","id":"2309.07726","version":2},"attestation_state":"computed","paper":{"title":"GRID: Scene-Graph-based Instruction-driven Robotic Task Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Cong Tai, Long Zeng, Qinghongbing Xie, Weihang Huang, Xiang Wu, Xiaoxin Deng, Xinyue Zhu, Zhe Ni","submitted_at":"2023-09-14T14:02:56Z","abstract_excerpt":"Recent works have shown that Large Language Models (LLMs) can facilitate the grounding of instructions for robotic task planning. Despite this progress, most existing works have primarily focused on utilizing raw images to aid LLMs in understanding environmental information. However, this approach not only limits the scope of observation but also typically necessitates extensive multimodal data collection and large-scale models. In this paper, we propose a novel approach called Graph-based Robotic Instruction Decomposer (GRID), which leverages scene graphs instead of images to perceive global "},"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":"2309.07726","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-09-14T14:02:56Z","cross_cats_sorted":[],"title_canon_sha256":"cc878264f944774ec58b0d9ebb9f5e1b0c2a3eebfd7b604ccd34f7ead429a75c","abstract_canon_sha256":"14a1475bdd6e928e6c165bb644009098ac78f7212ff11cb1c89ad7abaddf3b19"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:03.603974Z","signature_b64":"UvbDJnmLpaRb5G5+E9l3KybHFu7A0LSTKj9pWO7wdFamuaEOvQ2AL9GPlscLMp968Y+46zxKv9L2XiPwebDWCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bdba5135c4c5adf8a835ad2ece437fbc2d0114cbfff9be402b531d83d173aad8","last_reissued_at":"2026-07-05T07:54:03.603473Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:03.603473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GRID: Scene-Graph-based Instruction-driven Robotic Task Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Cong Tai, Long Zeng, Qinghongbing Xie, Weihang Huang, Xiang Wu, Xiaoxin Deng, Xinyue Zhu, Zhe Ni","submitted_at":"2023-09-14T14:02:56Z","abstract_excerpt":"Recent works have shown that Large Language Models (LLMs) can facilitate the grounding of instructions for robotic task planning. Despite this progress, most existing works have primarily focused on utilizing raw images to aid LLMs in understanding environmental information. However, this approach not only limits the scope of observation but also typically necessitates extensive multimodal data collection and large-scale models. In this paper, we propose a novel approach called Graph-based Robotic Instruction Decomposer (GRID), which leverages scene graphs instead of images to perceive global "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.07726","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/2309.07726/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":"2309.07726","created_at":"2026-07-05T07:54:03.603533+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.07726v2","created_at":"2026-07-05T07:54:03.603533+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.07726","created_at":"2026-07-05T07:54:03.603533+00:00"},{"alias_kind":"pith_short_12","alias_value":"XW5FCNOEYWW7","created_at":"2026-07-05T07:54:03.603533+00:00"},{"alias_kind":"pith_short_16","alias_value":"XW5FCNOEYWW7RKBV","created_at":"2026-07-05T07:54:03.603533+00:00"},{"alias_kind":"pith_short_8","alias_value":"XW5FCNOE","created_at":"2026-07-05T07:54:03.603533+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2401.03568","citing_title":"Agent AI: Surveying the Horizons of Multimodal Interaction","ref_index":136,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XW5FCNOEYWW7RKBVVUXM4Q37XQ","json":"https://pith.science/pith/XW5FCNOEYWW7RKBVVUXM4Q37XQ.json","graph_json":"https://pith.science/api/pith-number/XW5FCNOEYWW7RKBVVUXM4Q37XQ/graph.json","events_json":"https://pith.science/api/pith-number/XW5FCNOEYWW7RKBVVUXM4Q37XQ/events.json","paper":"https://pith.science/paper/XW5FCNOE"},"agent_actions":{"view_html":"https://pith.science/pith/XW5FCNOEYWW7RKBVVUXM4Q37XQ","download_json":"https://pith.science/pith/XW5FCNOEYWW7RKBVVUXM4Q37XQ.json","view_paper":"https://pith.science/paper/XW5FCNOE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.07726&json=true","fetch_graph":"https://pith.science/api/pith-number/XW5FCNOEYWW7RKBVVUXM4Q37XQ/graph.json","fetch_events":"https://pith.science/api/pith-number/XW5FCNOEYWW7RKBVVUXM4Q37XQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XW5FCNOEYWW7RKBVVUXM4Q37XQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XW5FCNOEYWW7RKBVVUXM4Q37XQ/action/storage_attestation","attest_author":"https://pith.science/pith/XW5FCNOEYWW7RKBVVUXM4Q37XQ/action/author_attestation","sign_citation":"https://pith.science/pith/XW5FCNOEYWW7RKBVVUXM4Q37XQ/action/citation_signature","submit_replication":"https://pith.science/pith/XW5FCNOEYWW7RKBVVUXM4Q37XQ/action/replication_record"}},"created_at":"2026-07-05T07:54:03.603533+00:00","updated_at":"2026-07-05T07:54:03.603533+00:00"}