{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OT2W6ZZHKHSBTXGNCUMB6SBLPB","short_pith_number":"pith:OT2W6ZZH","schema_version":"1.0","canonical_sha256":"74f56f672751e419dccd15181f482b7864aa041d51cd24f7834687dca6ad0ca4","source":{"kind":"arxiv","id":"2601.11906","version":2},"attestation_state":"computed","paper":{"title":"Visual-Language-Guided Task Planning for Horticultural Robots","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Aditya Potnis, Girish Chowdhary, Jose Cuaran, Kendall Koe, Naveen Kumar Uppalapati","submitted_at":"2026-01-17T04:45:31Z","abstract_excerpt":"Crop monitoring is essential for precision agriculture, but current systems lack high-level reasoning. We introduce a novel, modular framework that uses a Vision Language Model (VLM) to guide robotic task planning by actively querying heterogeneous data sources, including enriched RGB camera feeds and 2D semantic occupancy maps, interleaved with robotic action primitives. We contribute a comprehensive benchmark for short- and long-horizon crop monitoring tasks in monoculture and polyculture environments. Our results show that while zero-shot VLMs perform robustly for short-horizon tasks (achie"},"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":"2601.11906","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2026-01-17T04:45:31Z","cross_cats_sorted":[],"title_canon_sha256":"53049a98a43c12c0a28437841b9f4cf39c4d3617d68612288bc324a8fc1890db","abstract_canon_sha256":"2e016f6376e72851dbdcbe5af0a6c6cfcae56211d5988eae07ea7d85c7300acb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T00:15:24.682349Z","signature_b64":"Y4CYygXZPqUMjT4MH0pEcLWBgX6eDEfPqRDFX7kuXUtw6/S7j4bzD/J5hksSMUhPJRk2S2Hw8ygfgV9gNuYZDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74f56f672751e419dccd15181f482b7864aa041d51cd24f7834687dca6ad0ca4","last_reissued_at":"2026-06-26T00:15:24.681693Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T00:15:24.681693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual-Language-Guided Task Planning for Horticultural Robots","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Aditya Potnis, Girish Chowdhary, Jose Cuaran, Kendall Koe, Naveen Kumar Uppalapati","submitted_at":"2026-01-17T04:45:31Z","abstract_excerpt":"Crop monitoring is essential for precision agriculture, but current systems lack high-level reasoning. We introduce a novel, modular framework that uses a Vision Language Model (VLM) to guide robotic task planning by actively querying heterogeneous data sources, including enriched RGB camera feeds and 2D semantic occupancy maps, interleaved with robotic action primitives. We contribute a comprehensive benchmark for short- and long-horizon crop monitoring tasks in monoculture and polyculture environments. Our results show that while zero-shot VLMs perform robustly for short-horizon tasks (achie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.11906","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/2601.11906/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":"2601.11906","created_at":"2026-06-26T00:15:24.681768+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.11906v2","created_at":"2026-06-26T00:15:24.681768+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.11906","created_at":"2026-06-26T00:15:24.681768+00:00"},{"alias_kind":"pith_short_12","alias_value":"OT2W6ZZHKHSB","created_at":"2026-06-26T00:15:24.681768+00:00"},{"alias_kind":"pith_short_16","alias_value":"OT2W6ZZHKHSBTXGN","created_at":"2026-06-26T00:15:24.681768+00:00"},{"alias_kind":"pith_short_8","alias_value":"OT2W6ZZH","created_at":"2026-06-26T00:15:24.681768+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/OT2W6ZZHKHSBTXGNCUMB6SBLPB","json":"https://pith.science/pith/OT2W6ZZHKHSBTXGNCUMB6SBLPB.json","graph_json":"https://pith.science/api/pith-number/OT2W6ZZHKHSBTXGNCUMB6SBLPB/graph.json","events_json":"https://pith.science/api/pith-number/OT2W6ZZHKHSBTXGNCUMB6SBLPB/events.json","paper":"https://pith.science/paper/OT2W6ZZH"},"agent_actions":{"view_html":"https://pith.science/pith/OT2W6ZZHKHSBTXGNCUMB6SBLPB","download_json":"https://pith.science/pith/OT2W6ZZHKHSBTXGNCUMB6SBLPB.json","view_paper":"https://pith.science/paper/OT2W6ZZH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.11906&json=true","fetch_graph":"https://pith.science/api/pith-number/OT2W6ZZHKHSBTXGNCUMB6SBLPB/graph.json","fetch_events":"https://pith.science/api/pith-number/OT2W6ZZHKHSBTXGNCUMB6SBLPB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OT2W6ZZHKHSBTXGNCUMB6SBLPB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OT2W6ZZHKHSBTXGNCUMB6SBLPB/action/storage_attestation","attest_author":"https://pith.science/pith/OT2W6ZZHKHSBTXGNCUMB6SBLPB/action/author_attestation","sign_citation":"https://pith.science/pith/OT2W6ZZHKHSBTXGNCUMB6SBLPB/action/citation_signature","submit_replication":"https://pith.science/pith/OT2W6ZZHKHSBTXGNCUMB6SBLPB/action/replication_record"}},"created_at":"2026-06-26T00:15:24.681768+00:00","updated_at":"2026-06-26T00:15:24.681768+00:00"}