{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OJNHTXKGLVNROB6RAOZ4UI4TFY","short_pith_number":"pith:OJNHTXKG","schema_version":"1.0","canonical_sha256":"725a79dd465d5b1707d103b3ca23932e1283c621763fd3708ed19f55ba97c3d3","source":{"kind":"arxiv","id":"2409.14277","version":1},"attestation_state":"computed","paper":{"title":"Can-Do! A Dataset and Neuro-Symbolic Grounded Framework for Embodied Planning with Large Multimodal Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.RO"],"primary_cat":"cs.AI","authors_text":"Lidong Bing, Qi Sun, Soujanya Poria, Yew Ken Chia","submitted_at":"2024-09-22T00:30:11Z","abstract_excerpt":"Large multimodal models have demonstrated impressive problem-solving abilities in vision and language tasks, and have the potential to encode extensive world knowledge. However, it remains an open challenge for these models to perceive, reason, plan, and act in realistic environments. In this work, we introduce Can-Do, a benchmark dataset designed to evaluate embodied planning abilities through more diverse and complex scenarios than previous datasets. Our dataset includes 400 multimodal samples, each consisting of natural language user instructions, visual images depicting the environment, st"},"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":"2409.14277","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-09-22T00:30:11Z","cross_cats_sorted":["cs.CL","cs.CV","cs.RO"],"title_canon_sha256":"7181f8af8bc60dbb192353d6475cff7a5223d5868f720f58030d4e035e29ca38","abstract_canon_sha256":"d4b0c1a7b8b2f205000f4f4ad39dbf6a2a861745b5faf8f69b417d3caae7505f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:14.177325Z","signature_b64":"mfl/Nk+kj0Pc5q42q4XtW/VHG73xt+LYNSmHkX3zB2B9+Uo+vldMjFthNtwijj05d+mCty9u8JeFiBHqu5XoBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"725a79dd465d5b1707d103b3ca23932e1283c621763fd3708ed19f55ba97c3d3","last_reissued_at":"2026-07-05T09:10:14.176941Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:14.176941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can-Do! A Dataset and Neuro-Symbolic Grounded Framework for Embodied Planning with Large Multimodal Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.RO"],"primary_cat":"cs.AI","authors_text":"Lidong Bing, Qi Sun, Soujanya Poria, Yew Ken Chia","submitted_at":"2024-09-22T00:30:11Z","abstract_excerpt":"Large multimodal models have demonstrated impressive problem-solving abilities in vision and language tasks, and have the potential to encode extensive world knowledge. However, it remains an open challenge for these models to perceive, reason, plan, and act in realistic environments. In this work, we introduce Can-Do, a benchmark dataset designed to evaluate embodied planning abilities through more diverse and complex scenarios than previous datasets. Our dataset includes 400 multimodal samples, each consisting of natural language user instructions, visual images depicting the environment, st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.14277","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/2409.14277/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":"2409.14277","created_at":"2026-07-05T09:10:14.176995+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.14277v1","created_at":"2026-07-05T09:10:14.176995+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.14277","created_at":"2026-07-05T09:10:14.176995+00:00"},{"alias_kind":"pith_short_12","alias_value":"OJNHTXKGLVNR","created_at":"2026-07-05T09:10:14.176995+00:00"},{"alias_kind":"pith_short_16","alias_value":"OJNHTXKGLVNROB6R","created_at":"2026-07-05T09:10:14.176995+00:00"},{"alias_kind":"pith_short_8","alias_value":"OJNHTXKG","created_at":"2026-07-05T09:10:14.176995+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/OJNHTXKGLVNROB6RAOZ4UI4TFY","json":"https://pith.science/pith/OJNHTXKGLVNROB6RAOZ4UI4TFY.json","graph_json":"https://pith.science/api/pith-number/OJNHTXKGLVNROB6RAOZ4UI4TFY/graph.json","events_json":"https://pith.science/api/pith-number/OJNHTXKGLVNROB6RAOZ4UI4TFY/events.json","paper":"https://pith.science/paper/OJNHTXKG"},"agent_actions":{"view_html":"https://pith.science/pith/OJNHTXKGLVNROB6RAOZ4UI4TFY","download_json":"https://pith.science/pith/OJNHTXKGLVNROB6RAOZ4UI4TFY.json","view_paper":"https://pith.science/paper/OJNHTXKG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.14277&json=true","fetch_graph":"https://pith.science/api/pith-number/OJNHTXKGLVNROB6RAOZ4UI4TFY/graph.json","fetch_events":"https://pith.science/api/pith-number/OJNHTXKGLVNROB6RAOZ4UI4TFY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OJNHTXKGLVNROB6RAOZ4UI4TFY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OJNHTXKGLVNROB6RAOZ4UI4TFY/action/storage_attestation","attest_author":"https://pith.science/pith/OJNHTXKGLVNROB6RAOZ4UI4TFY/action/author_attestation","sign_citation":"https://pith.science/pith/OJNHTXKGLVNROB6RAOZ4UI4TFY/action/citation_signature","submit_replication":"https://pith.science/pith/OJNHTXKGLVNROB6RAOZ4UI4TFY/action/replication_record"}},"created_at":"2026-07-05T09:10:14.176995+00:00","updated_at":"2026-07-05T09:10:14.176995+00:00"}