{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WWWGXGGNDNROVH2D4ECJ4WYLP6","short_pith_number":"pith:WWWGXGGN","schema_version":"1.0","canonical_sha256":"b5ac6b98cd1b62ea9f43e1049e5b0b7fa489b88d01a89e98b1c4d4771ec03655","source":{"kind":"arxiv","id":"2403.03017","version":1},"attestation_state":"computed","paper":{"title":"OPEx: A Component-Wise Analysis of LLM-Centric Agents in Embodied Instruction Following","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bang Liu, Haochen Shi, Marc-Alexandre C\\^ot\\'e, Xingdi Yuan, Zhiyuan Sun","submitted_at":"2024-03-05T14:53:53Z","abstract_excerpt":"Embodied Instruction Following (EIF) is a crucial task in embodied learning, requiring agents to interact with their environment through egocentric observations to fulfill natural language instructions. Recent advancements have seen a surge in employing large language models (LLMs) within a framework-centric approach to enhance performance in embodied learning tasks, including EIF. Despite these efforts, there exists a lack of a unified understanding regarding the impact of various components-ranging from visual perception to action execution-on task performance. To address this gap, we introd"},"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":"2403.03017","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-03-05T14:53:53Z","cross_cats_sorted":[],"title_canon_sha256":"15f08d9cc6095b4b2d67f1ddc6d228226cc1c43b2cf84b1d618195a9e6c4e791","abstract_canon_sha256":"e53bebd209e0ad52021834cc43862a4ab5a7a8706c87ae4b3f5e4719529bf83c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:52:35.238890Z","signature_b64":"mtwmz3WVsex1RdFyDw5g9YLW97JsVwITsbYMuOdE3A4J1vNwgDqw5g69Q/dB6ZFUIT3iWv+TOr5RWdpfEY4MDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5ac6b98cd1b62ea9f43e1049e5b0b7fa489b88d01a89e98b1c4d4771ec03655","last_reissued_at":"2026-07-05T07:52:35.238395Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:52:35.238395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OPEx: A Component-Wise Analysis of LLM-Centric Agents in Embodied Instruction Following","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bang Liu, Haochen Shi, Marc-Alexandre C\\^ot\\'e, Xingdi Yuan, Zhiyuan Sun","submitted_at":"2024-03-05T14:53:53Z","abstract_excerpt":"Embodied Instruction Following (EIF) is a crucial task in embodied learning, requiring agents to interact with their environment through egocentric observations to fulfill natural language instructions. Recent advancements have seen a surge in employing large language models (LLMs) within a framework-centric approach to enhance performance in embodied learning tasks, including EIF. Despite these efforts, there exists a lack of a unified understanding regarding the impact of various components-ranging from visual perception to action execution-on task performance. To address this gap, we introd"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03017","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/2403.03017/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":"2403.03017","created_at":"2026-07-05T07:52:35.238460+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.03017v1","created_at":"2026-07-05T07:52:35.238460+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03017","created_at":"2026-07-05T07:52:35.238460+00:00"},{"alias_kind":"pith_short_12","alias_value":"WWWGXGGNDNRO","created_at":"2026-07-05T07:52:35.238460+00:00"},{"alias_kind":"pith_short_16","alias_value":"WWWGXGGNDNROVH2D","created_at":"2026-07-05T07:52:35.238460+00:00"},{"alias_kind":"pith_short_8","alias_value":"WWWGXGGN","created_at":"2026-07-05T07:52:35.238460+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08330","citing_title":"Hierarchical Prompting with Dual LLM Modules for Robotic Task and Motion Planning","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WWWGXGGNDNROVH2D4ECJ4WYLP6","json":"https://pith.science/pith/WWWGXGGNDNROVH2D4ECJ4WYLP6.json","graph_json":"https://pith.science/api/pith-number/WWWGXGGNDNROVH2D4ECJ4WYLP6/graph.json","events_json":"https://pith.science/api/pith-number/WWWGXGGNDNROVH2D4ECJ4WYLP6/events.json","paper":"https://pith.science/paper/WWWGXGGN"},"agent_actions":{"view_html":"https://pith.science/pith/WWWGXGGNDNROVH2D4ECJ4WYLP6","download_json":"https://pith.science/pith/WWWGXGGNDNROVH2D4ECJ4WYLP6.json","view_paper":"https://pith.science/paper/WWWGXGGN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.03017&json=true","fetch_graph":"https://pith.science/api/pith-number/WWWGXGGNDNROVH2D4ECJ4WYLP6/graph.json","fetch_events":"https://pith.science/api/pith-number/WWWGXGGNDNROVH2D4ECJ4WYLP6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WWWGXGGNDNROVH2D4ECJ4WYLP6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WWWGXGGNDNROVH2D4ECJ4WYLP6/action/storage_attestation","attest_author":"https://pith.science/pith/WWWGXGGNDNROVH2D4ECJ4WYLP6/action/author_attestation","sign_citation":"https://pith.science/pith/WWWGXGGNDNROVH2D4ECJ4WYLP6/action/citation_signature","submit_replication":"https://pith.science/pith/WWWGXGGNDNROVH2D4ECJ4WYLP6/action/replication_record"}},"created_at":"2026-07-05T07:52:35.238460+00:00","updated_at":"2026-07-05T07:52:35.238460+00:00"}