{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FX636LE5KPMIPEMP7LHSF2CXG4","short_pith_number":"pith:FX636LE5","schema_version":"1.0","canonical_sha256":"2dfdbf2c9d53d887918ffacf22e85737377e5d7e8477c4c417457245e51d705c","source":{"kind":"arxiv","id":"2503.13082","version":2},"attestation_state":"computed","paper":{"title":"Free-form language-based robotic reasoning and grasping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Alice Fasoli, Fabio Poiesi, Francesco Giuliari, Guofeng Mei, Matteo Bortolon, Runyu Jiao, Sergio Povoli, Yiming Wang","submitted_at":"2025-03-17T11:41:16Z","abstract_excerpt":"Performing robotic grasping from a cluttered bin based on human instructions is a challenging task, as it requires understanding both the nuances of free-form language and the spatial relationships between objects. Vision-Language Models (VLMs) trained on web-scale data, such as GPT-4o, have demonstrated remarkable reasoning capabilities across both text and images. But can they truly be used for this task in a zero-shot setting? And what are their limitations? In this paper, we explore these research questions via the free-form language-based robotic grasping task, and propose a novel method,"},"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":"2503.13082","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-03-17T11:41:16Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"36fc961132cde4079400c21873ad7fd8935c0aad6682a03c121571b2a80bd26c","abstract_canon_sha256":"eeb9fdf718356db03b4a1fe714f4f8c8e1c8977bf5a79be7c73a692ab9cbfa18"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:02.831875Z","signature_b64":"0RCDkqLu9Id07KHMyx+XWjSXiACfWhi5kHE5ycb7LByaPGZD42XuDFfFBXtP66ObT2YZ5mkR6j+QxGYiIQ8vAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2dfdbf2c9d53d887918ffacf22e85737377e5d7e8477c4c417457245e51d705c","last_reissued_at":"2026-07-05T11:44:02.831444Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:02.831444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Free-form language-based robotic reasoning and grasping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Alice Fasoli, Fabio Poiesi, Francesco Giuliari, Guofeng Mei, Matteo Bortolon, Runyu Jiao, Sergio Povoli, Yiming Wang","submitted_at":"2025-03-17T11:41:16Z","abstract_excerpt":"Performing robotic grasping from a cluttered bin based on human instructions is a challenging task, as it requires understanding both the nuances of free-form language and the spatial relationships between objects. Vision-Language Models (VLMs) trained on web-scale data, such as GPT-4o, have demonstrated remarkable reasoning capabilities across both text and images. But can they truly be used for this task in a zero-shot setting? And what are their limitations? In this paper, we explore these research questions via the free-form language-based robotic grasping task, and propose a novel method,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.13082","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/2503.13082/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":"2503.13082","created_at":"2026-07-05T11:44:02.831500+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.13082v2","created_at":"2026-07-05T11:44:02.831500+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.13082","created_at":"2026-07-05T11:44:02.831500+00:00"},{"alias_kind":"pith_short_12","alias_value":"FX636LE5KPMI","created_at":"2026-07-05T11:44:02.831500+00:00"},{"alias_kind":"pith_short_16","alias_value":"FX636LE5KPMIPEMP","created_at":"2026-07-05T11:44:02.831500+00:00"},{"alias_kind":"pith_short_8","alias_value":"FX636LE5","created_at":"2026-07-05T11:44:02.831500+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.12370","citing_title":"Beyond Single Models: Enhancing LLM Detection of Ambiguity in Requests through Debate","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FX636LE5KPMIPEMP7LHSF2CXG4","json":"https://pith.science/pith/FX636LE5KPMIPEMP7LHSF2CXG4.json","graph_json":"https://pith.science/api/pith-number/FX636LE5KPMIPEMP7LHSF2CXG4/graph.json","events_json":"https://pith.science/api/pith-number/FX636LE5KPMIPEMP7LHSF2CXG4/events.json","paper":"https://pith.science/paper/FX636LE5"},"agent_actions":{"view_html":"https://pith.science/pith/FX636LE5KPMIPEMP7LHSF2CXG4","download_json":"https://pith.science/pith/FX636LE5KPMIPEMP7LHSF2CXG4.json","view_paper":"https://pith.science/paper/FX636LE5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.13082&json=true","fetch_graph":"https://pith.science/api/pith-number/FX636LE5KPMIPEMP7LHSF2CXG4/graph.json","fetch_events":"https://pith.science/api/pith-number/FX636LE5KPMIPEMP7LHSF2CXG4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FX636LE5KPMIPEMP7LHSF2CXG4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FX636LE5KPMIPEMP7LHSF2CXG4/action/storage_attestation","attest_author":"https://pith.science/pith/FX636LE5KPMIPEMP7LHSF2CXG4/action/author_attestation","sign_citation":"https://pith.science/pith/FX636LE5KPMIPEMP7LHSF2CXG4/action/citation_signature","submit_replication":"https://pith.science/pith/FX636LE5KPMIPEMP7LHSF2CXG4/action/replication_record"}},"created_at":"2026-07-05T11:44:02.831500+00:00","updated_at":"2026-07-05T11:44:02.831500+00:00"}