{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OAG76OJZOQLMCNRMFJNGCQDDRR","short_pith_number":"pith:OAG76OJZ","schema_version":"1.0","canonical_sha256":"700dff39397416c1362c2a5a6140638c7dbd28ef15d2ede619dc6a898fc99e99","source":{"kind":"arxiv","id":"2401.03388","version":1},"attestation_state":"computed","paper":{"title":"LLMs for Robotic Object Disambiguation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.RO","authors_text":"Connie Jiang, David Hsu, Yiqing Xu","submitted_at":"2024-01-07T04:46:23Z","abstract_excerpt":"The advantages of pre-trained large language models (LLMs) are apparent in a variety of language processing tasks. But can a language model's knowledge be further harnessed to effectively disambiguate objects and navigate decision-making challenges within the realm of robotics? Our study reveals the LLM's aptitude for solving complex decision making challenges that are often previously modeled by Partially Observable Markov Decision Processes (POMDPs). A pivotal focus of our research is the object disambiguation capability of LLMs. We detail the integration of an LLM into a tabletop environmen"},"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":"2401.03388","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-01-07T04:46:23Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"4d8858e73cb9c8989b255ba025c53f6e6b20dfa644857e9e87cf4e2eb24360fc","abstract_canon_sha256":"cff3fdef8c72652fd2fba6e22dd37e04387775f1d759356fbd349e7bfa92e0ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:31:07.389127Z","signature_b64":"0bBVLOSLiA2SA0nLNSwuWD9yEXIZWMavaL6tLNc14tDImCPRtYOHLKePIhJwJ+qy351Fpy9K1tIaseyTYEAxCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"700dff39397416c1362c2a5a6140638c7dbd28ef15d2ede619dc6a898fc99e99","last_reissued_at":"2026-07-05T07:31:07.388705Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:31:07.388705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLMs for Robotic Object Disambiguation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.RO","authors_text":"Connie Jiang, David Hsu, Yiqing Xu","submitted_at":"2024-01-07T04:46:23Z","abstract_excerpt":"The advantages of pre-trained large language models (LLMs) are apparent in a variety of language processing tasks. But can a language model's knowledge be further harnessed to effectively disambiguate objects and navigate decision-making challenges within the realm of robotics? Our study reveals the LLM's aptitude for solving complex decision making challenges that are often previously modeled by Partially Observable Markov Decision Processes (POMDPs). A pivotal focus of our research is the object disambiguation capability of LLMs. We detail the integration of an LLM into a tabletop environmen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.03388","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/2401.03388/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":"2401.03388","created_at":"2026-07-05T07:31:07.388761+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.03388v1","created_at":"2026-07-05T07:31:07.388761+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.03388","created_at":"2026-07-05T07:31:07.388761+00:00"},{"alias_kind":"pith_short_12","alias_value":"OAG76OJZOQLM","created_at":"2026-07-05T07:31:07.388761+00:00"},{"alias_kind":"pith_short_16","alias_value":"OAG76OJZOQLMCNRM","created_at":"2026-07-05T07:31:07.388761+00:00"},{"alias_kind":"pith_short_8","alias_value":"OAG76OJZ","created_at":"2026-07-05T07:31:07.388761+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.02093","citing_title":"\"Stack It Up!\": 3D Stable Structure Generation from 2D Hand-drawn Sketch","ref_index":44,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OAG76OJZOQLMCNRMFJNGCQDDRR","json":"https://pith.science/pith/OAG76OJZOQLMCNRMFJNGCQDDRR.json","graph_json":"https://pith.science/api/pith-number/OAG76OJZOQLMCNRMFJNGCQDDRR/graph.json","events_json":"https://pith.science/api/pith-number/OAG76OJZOQLMCNRMFJNGCQDDRR/events.json","paper":"https://pith.science/paper/OAG76OJZ"},"agent_actions":{"view_html":"https://pith.science/pith/OAG76OJZOQLMCNRMFJNGCQDDRR","download_json":"https://pith.science/pith/OAG76OJZOQLMCNRMFJNGCQDDRR.json","view_paper":"https://pith.science/paper/OAG76OJZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.03388&json=true","fetch_graph":"https://pith.science/api/pith-number/OAG76OJZOQLMCNRMFJNGCQDDRR/graph.json","fetch_events":"https://pith.science/api/pith-number/OAG76OJZOQLMCNRMFJNGCQDDRR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OAG76OJZOQLMCNRMFJNGCQDDRR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OAG76OJZOQLMCNRMFJNGCQDDRR/action/storage_attestation","attest_author":"https://pith.science/pith/OAG76OJZOQLMCNRMFJNGCQDDRR/action/author_attestation","sign_citation":"https://pith.science/pith/OAG76OJZOQLMCNRMFJNGCQDDRR/action/citation_signature","submit_replication":"https://pith.science/pith/OAG76OJZOQLMCNRMFJNGCQDDRR/action/replication_record"}},"created_at":"2026-07-05T07:31:07.388761+00:00","updated_at":"2026-07-05T07:31:07.388761+00:00"}