{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7DKBTABM3WXS5TD2JNVJY7KO4H","short_pith_number":"pith:7DKBTABM","schema_version":"1.0","canonical_sha256":"f8d419802cddaf2ecc7a4b6a9c7d4ee1dc8b63e7f4ca215a99377ecb712296e6","source":{"kind":"arxiv","id":"2507.12391","version":1},"attestation_state":"computed","paper":{"title":"Assessing the Value of Visual Input: A Benchmark of Multimodal Large Language Models for Robotic Path Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ana Davila, Jacinto Colan, Yasuhisa Hasegawa","submitted_at":"2025-07-16T16:37:13Z","abstract_excerpt":"Large Language Models (LLMs) show potential for enhancing robotic path planning. This paper assesses visual input's utility for multimodal LLMs in such tasks via a comprehensive benchmark. We evaluated 15 multimodal LLMs on generating valid and optimal paths in 2D grid environments, simulating simplified robotic planning, comparing text-only versus text-plus-visual inputs across varying model sizes and grid complexities. Our results indicate moderate success rates on simpler small grids, where visual input or few-shot text prompting offered some benefits. However, performance significantly deg"},"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":"2507.12391","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-07-16T16:37:13Z","cross_cats_sorted":[],"title_canon_sha256":"df85f611946f2dfc404865398bcfb3f12f47aacfc1d1637b2eddfe4381ecb1c1","abstract_canon_sha256":"ab9d9e54c59da9a12b8d21767a9dd3f8570529c9e535923a945d033aa50f9468"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:19.609848Z","signature_b64":"4sS2rrhB+DlrkxDD5C7qt3WNVxi5q1mGJIT40KSMrCXhEp5GCwXmJTdif/eTziun0fXfiYr7LgviiQn9OUBQCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8d419802cddaf2ecc7a4b6a9c7d4ee1dc8b63e7f4ca215a99377ecb712296e6","last_reissued_at":"2026-07-05T11:38:19.609332Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:19.609332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Assessing the Value of Visual Input: A Benchmark of Multimodal Large Language Models for Robotic Path Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ana Davila, Jacinto Colan, Yasuhisa Hasegawa","submitted_at":"2025-07-16T16:37:13Z","abstract_excerpt":"Large Language Models (LLMs) show potential for enhancing robotic path planning. This paper assesses visual input's utility for multimodal LLMs in such tasks via a comprehensive benchmark. We evaluated 15 multimodal LLMs on generating valid and optimal paths in 2D grid environments, simulating simplified robotic planning, comparing text-only versus text-plus-visual inputs across varying model sizes and grid complexities. Our results indicate moderate success rates on simpler small grids, where visual input or few-shot text prompting offered some benefits. However, performance significantly deg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12391","kind":"arxiv","version":1},"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/2507.12391/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":"2507.12391","created_at":"2026-07-05T11:38:19.609395+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.12391v1","created_at":"2026-07-05T11:38:19.609395+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12391","created_at":"2026-07-05T11:38:19.609395+00:00"},{"alias_kind":"pith_short_12","alias_value":"7DKBTABM3WXS","created_at":"2026-07-05T11:38:19.609395+00:00"},{"alias_kind":"pith_short_16","alias_value":"7DKBTABM3WXS5TD2","created_at":"2026-07-05T11:38:19.609395+00:00"},{"alias_kind":"pith_short_8","alias_value":"7DKBTABM","created_at":"2026-07-05T11:38:19.609395+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.02359","citing_title":"Why Do MLLMs Struggle with Spatial Understanding? A Systematic Analysis from Data to Architecture","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7DKBTABM3WXS5TD2JNVJY7KO4H","json":"https://pith.science/pith/7DKBTABM3WXS5TD2JNVJY7KO4H.json","graph_json":"https://pith.science/api/pith-number/7DKBTABM3WXS5TD2JNVJY7KO4H/graph.json","events_json":"https://pith.science/api/pith-number/7DKBTABM3WXS5TD2JNVJY7KO4H/events.json","paper":"https://pith.science/paper/7DKBTABM"},"agent_actions":{"view_html":"https://pith.science/pith/7DKBTABM3WXS5TD2JNVJY7KO4H","download_json":"https://pith.science/pith/7DKBTABM3WXS5TD2JNVJY7KO4H.json","view_paper":"https://pith.science/paper/7DKBTABM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.12391&json=true","fetch_graph":"https://pith.science/api/pith-number/7DKBTABM3WXS5TD2JNVJY7KO4H/graph.json","fetch_events":"https://pith.science/api/pith-number/7DKBTABM3WXS5TD2JNVJY7KO4H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7DKBTABM3WXS5TD2JNVJY7KO4H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7DKBTABM3WXS5TD2JNVJY7KO4H/action/storage_attestation","attest_author":"https://pith.science/pith/7DKBTABM3WXS5TD2JNVJY7KO4H/action/author_attestation","sign_citation":"https://pith.science/pith/7DKBTABM3WXS5TD2JNVJY7KO4H/action/citation_signature","submit_replication":"https://pith.science/pith/7DKBTABM3WXS5TD2JNVJY7KO4H/action/replication_record"}},"created_at":"2026-07-05T11:38:19.609395+00:00","updated_at":"2026-07-05T11:38:19.609395+00:00"}