{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DXKNQNXHNPSJZG4QBIAC6M5P45","short_pith_number":"pith:DXKNQNXH","schema_version":"1.0","canonical_sha256":"1dd4d836e76be49c9b900a002f33afe762f691db0a79e2248baf429c13624b6d","source":{"kind":"arxiv","id":"2507.10778","version":2},"attestation_state":"computed","paper":{"title":"Warehouse Spatial Question Answering with LLM Agent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bahaa Alattar, Cheng-Yen Yang, Chung-I Huang, Hsiang-Wei Huang, Jen-Hao Cheng, Jenq-Neng Hwang, Kuang-Ming Chen, Kwangju Kim, Pyongkun Kim, Sangwon Kim, Yi-Ru Lin","submitted_at":"2025-07-14T20:05:55Z","abstract_excerpt":"Spatial understanding has been a challenging task for existing Multi-modal Large Language Models~(MLLMs). Previous methods leverage large-scale MLLM finetuning to enhance MLLM's spatial understanding ability. In this paper, we present a data-efficient approach. We propose a LLM agent system with strong and advanced spatial reasoning ability, which can be used to solve the challenging spatial question answering task in complex indoor warehouse scenarios. Our system integrates multiple tools that allow the LLM agent to conduct spatial reasoning and API tools interaction to answer the given compl"},"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":"2507.10778","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-14T20:05:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"54848ddc7319db5183b17a5a17757e1eaf0372d00deef46911971ec8f5e07b6f","abstract_canon_sha256":"fc21b8e6169c4743df2f0288ea6a51857dceeb48042b4c2b147712fb34fe9da7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:48.920418Z","signature_b64":"ftt5MPGjQfI5aZJ5Q8dvtlgVYykfkNBd/lgEjCdMKZ8fzZg+dZ92Q7u9nTyeDgVMRLiFE6iF5XMrX5f1z5zfAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1dd4d836e76be49c9b900a002f33afe762f691db0a79e2248baf429c13624b6d","last_reissued_at":"2026-07-05T11:53:48.919912Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:48.919912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Warehouse Spatial Question Answering with LLM Agent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bahaa Alattar, Cheng-Yen Yang, Chung-I Huang, Hsiang-Wei Huang, Jen-Hao Cheng, Jenq-Neng Hwang, Kuang-Ming Chen, Kwangju Kim, Pyongkun Kim, Sangwon Kim, Yi-Ru Lin","submitted_at":"2025-07-14T20:05:55Z","abstract_excerpt":"Spatial understanding has been a challenging task for existing Multi-modal Large Language Models~(MLLMs). Previous methods leverage large-scale MLLM finetuning to enhance MLLM's spatial understanding ability. In this paper, we present a data-efficient approach. We propose a LLM agent system with strong and advanced spatial reasoning ability, which can be used to solve the challenging spatial question answering task in complex indoor warehouse scenarios. Our system integrates multiple tools that allow the LLM agent to conduct spatial reasoning and API tools interaction to answer the given compl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10778","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/2507.10778/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":"2507.10778","created_at":"2026-07-05T11:53:48.919974+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.10778v2","created_at":"2026-07-05T11:53:48.919974+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10778","created_at":"2026-07-05T11:53:48.919974+00:00"},{"alias_kind":"pith_short_12","alias_value":"DXKNQNXHNPSJ","created_at":"2026-07-05T11:53:48.919974+00:00"},{"alias_kind":"pith_short_16","alias_value":"DXKNQNXHNPSJZG4Q","created_at":"2026-07-05T11:53:48.919974+00:00"},{"alias_kind":"pith_short_8","alias_value":"DXKNQNXH","created_at":"2026-07-05T11:53:48.919974+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/DXKNQNXHNPSJZG4QBIAC6M5P45","json":"https://pith.science/pith/DXKNQNXHNPSJZG4QBIAC6M5P45.json","graph_json":"https://pith.science/api/pith-number/DXKNQNXHNPSJZG4QBIAC6M5P45/graph.json","events_json":"https://pith.science/api/pith-number/DXKNQNXHNPSJZG4QBIAC6M5P45/events.json","paper":"https://pith.science/paper/DXKNQNXH"},"agent_actions":{"view_html":"https://pith.science/pith/DXKNQNXHNPSJZG4QBIAC6M5P45","download_json":"https://pith.science/pith/DXKNQNXHNPSJZG4QBIAC6M5P45.json","view_paper":"https://pith.science/paper/DXKNQNXH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.10778&json=true","fetch_graph":"https://pith.science/api/pith-number/DXKNQNXHNPSJZG4QBIAC6M5P45/graph.json","fetch_events":"https://pith.science/api/pith-number/DXKNQNXHNPSJZG4QBIAC6M5P45/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DXKNQNXHNPSJZG4QBIAC6M5P45/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DXKNQNXHNPSJZG4QBIAC6M5P45/action/storage_attestation","attest_author":"https://pith.science/pith/DXKNQNXHNPSJZG4QBIAC6M5P45/action/author_attestation","sign_citation":"https://pith.science/pith/DXKNQNXHNPSJZG4QBIAC6M5P45/action/citation_signature","submit_replication":"https://pith.science/pith/DXKNQNXHNPSJZG4QBIAC6M5P45/action/replication_record"}},"created_at":"2026-07-05T11:53:48.919974+00:00","updated_at":"2026-07-05T11:53:48.919974+00:00"}