{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:D4X3ZYJH4UDYL4OVSJIWN3WTPA","short_pith_number":"pith:D4X3ZYJH","schema_version":"1.0","canonical_sha256":"1f2fbce127e50785f1d5925166eed3780ab94ab13a71c3e3733075d10bab1dd1","source":{"kind":"arxiv","id":"2503.08481","version":2},"attestation_state":"computed","paper":{"title":"PhysVLM: Enabling Visual Language Models to Understand Robotic Physical Reachability","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Chaoyang Zhao, Haiyun Guo, Honghui Dong, Jinqiao Wang, Manli Tao, Ming Tang, Weijie Zhou","submitted_at":"2025-03-11T14:34:41Z","abstract_excerpt":"Understanding the environment and a robot's physical reachability is crucial for task execution. While state-of-the-art vision-language models (VLMs) excel in environmental perception, they often generate inaccurate or impractical responses in embodied visual reasoning tasks due to a lack of understanding of robotic physical reachability. To address this issue, we propose a unified representation of physical reachability across diverse robots, i.e., Space-Physical Reachability Map (S-P Map), and PhysVLM, a vision-language model that integrates this reachability information into visual reasonin"},"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":"2503.08481","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-03-11T14:34:41Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"fd2e00e4aedaf0a92be8ee47d1af7723d1b773d100193f6d22d2723062fee124","abstract_canon_sha256":"add12761a6b55f3199d902dcc0ff3f8b93507e463bd39a14b944f71514b46781"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:33.506926Z","signature_b64":"o4xVqJ6W/PSOkXf+VcoUvxgcJUb5dgCsCWLkNyMWmELBuHCi4TttKS39zei1T/7BplXWIf32i8qSUp36RUtpCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f2fbce127e50785f1d5925166eed3780ab94ab13a71c3e3733075d10bab1dd1","last_reissued_at":"2026-07-05T10:30:33.505925Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:33.505925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PhysVLM: Enabling Visual Language Models to Understand Robotic Physical Reachability","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Chaoyang Zhao, Haiyun Guo, Honghui Dong, Jinqiao Wang, Manli Tao, Ming Tang, Weijie Zhou","submitted_at":"2025-03-11T14:34:41Z","abstract_excerpt":"Understanding the environment and a robot's physical reachability is crucial for task execution. While state-of-the-art vision-language models (VLMs) excel in environmental perception, they often generate inaccurate or impractical responses in embodied visual reasoning tasks due to a lack of understanding of robotic physical reachability. To address this issue, we propose a unified representation of physical reachability across diverse robots, i.e., Space-Physical Reachability Map (S-P Map), and PhysVLM, a vision-language model that integrates this reachability information into visual reasonin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.08481","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/2503.08481/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":"2503.08481","created_at":"2026-07-05T10:30:33.506068+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.08481v2","created_at":"2026-07-05T10:30:33.506068+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.08481","created_at":"2026-07-05T10:30:33.506068+00:00"},{"alias_kind":"pith_short_12","alias_value":"D4X3ZYJH4UDY","created_at":"2026-07-05T10:30:33.506068+00:00"},{"alias_kind":"pith_short_16","alias_value":"D4X3ZYJH4UDYL4OV","created_at":"2026-07-05T10:30:33.506068+00:00"},{"alias_kind":"pith_short_8","alias_value":"D4X3ZYJH","created_at":"2026-07-05T10:30:33.506068+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25212","citing_title":"RigPI: Dynamic Parameter Identification of Rigid Body via VLM-Seeded Differentiable Simulation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.25212","citing_title":"RigPI: Dynamic Parameter Identification of Rigid Body via VLM-Seeded Differentiable Simulation","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D4X3ZYJH4UDYL4OVSJIWN3WTPA","json":"https://pith.science/pith/D4X3ZYJH4UDYL4OVSJIWN3WTPA.json","graph_json":"https://pith.science/api/pith-number/D4X3ZYJH4UDYL4OVSJIWN3WTPA/graph.json","events_json":"https://pith.science/api/pith-number/D4X3ZYJH4UDYL4OVSJIWN3WTPA/events.json","paper":"https://pith.science/paper/D4X3ZYJH"},"agent_actions":{"view_html":"https://pith.science/pith/D4X3ZYJH4UDYL4OVSJIWN3WTPA","download_json":"https://pith.science/pith/D4X3ZYJH4UDYL4OVSJIWN3WTPA.json","view_paper":"https://pith.science/paper/D4X3ZYJH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.08481&json=true","fetch_graph":"https://pith.science/api/pith-number/D4X3ZYJH4UDYL4OVSJIWN3WTPA/graph.json","fetch_events":"https://pith.science/api/pith-number/D4X3ZYJH4UDYL4OVSJIWN3WTPA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D4X3ZYJH4UDYL4OVSJIWN3WTPA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D4X3ZYJH4UDYL4OVSJIWN3WTPA/action/storage_attestation","attest_author":"https://pith.science/pith/D4X3ZYJH4UDYL4OVSJIWN3WTPA/action/author_attestation","sign_citation":"https://pith.science/pith/D4X3ZYJH4UDYL4OVSJIWN3WTPA/action/citation_signature","submit_replication":"https://pith.science/pith/D4X3ZYJH4UDYL4OVSJIWN3WTPA/action/replication_record"}},"created_at":"2026-07-05T10:30:33.506068+00:00","updated_at":"2026-07-05T10:30:33.506068+00:00"}