{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RRZPK7RTCK2USAJBY2NPK6FHYE","short_pith_number":"pith:RRZPK7RT","schema_version":"1.0","canonical_sha256":"8c72f57e3312b5490121c69af578a7c135bc4bcd3a9f47ec1d0b88e81db05bc3","source":{"kind":"arxiv","id":"2409.03256","version":2},"attestation_state":"computed","paper":{"title":"E2CL: Exploration-based Error Correction Learning for Embodied Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chak Tou Leong, Hanlin Wang, Jian Wang, Wenjie Li","submitted_at":"2024-09-05T05:22:27Z","abstract_excerpt":"Language models are exhibiting increasing capability in knowledge utilization and reasoning. However, when applied as agents in embodied environments, they often suffer from misalignment between their intrinsic knowledge and environmental knowledge, leading to infeasible actions. Traditional environment alignment methods, such as supervised learning on expert trajectories and reinforcement learning, encounter limitations in covering environmental knowledge and achieving efficient convergence, respectively. Inspired by human learning, we propose Exploration-based Error Correction Learning (E2CL"},"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":"2409.03256","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-05T05:22:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f900d423230f923bcf3b2f6d15e5285a9fe20a3037d1680702283fa2aba4de29","abstract_canon_sha256":"cf38fc2d855a4d69785ad348642ceb2688700093ef324413a45c4073980d354d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:07.157760Z","signature_b64":"VuRziNh6GDHXp/7KpO5mUHy3anA0oCYy9lEC0jaQgaePEc1lOQWUeFUB0lngGlGGkrzugIqpv6qnCt7nrnjMAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c72f57e3312b5490121c69af578a7c135bc4bcd3a9f47ec1d0b88e81db05bc3","last_reissued_at":"2026-07-05T09:13:07.157269Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:07.157269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"E2CL: Exploration-based Error Correction Learning for Embodied Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chak Tou Leong, Hanlin Wang, Jian Wang, Wenjie Li","submitted_at":"2024-09-05T05:22:27Z","abstract_excerpt":"Language models are exhibiting increasing capability in knowledge utilization and reasoning. However, when applied as agents in embodied environments, they often suffer from misalignment between their intrinsic knowledge and environmental knowledge, leading to infeasible actions. Traditional environment alignment methods, such as supervised learning on expert trajectories and reinforcement learning, encounter limitations in covering environmental knowledge and achieving efficient convergence, respectively. Inspired by human learning, we propose Exploration-based Error Correction Learning (E2CL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.03256","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/2409.03256/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":"2409.03256","created_at":"2026-07-05T09:13:07.157336+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.03256v2","created_at":"2026-07-05T09:13:07.157336+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.03256","created_at":"2026-07-05T09:13:07.157336+00:00"},{"alias_kind":"pith_short_12","alias_value":"RRZPK7RTCK2U","created_at":"2026-07-05T09:13:07.157336+00:00"},{"alias_kind":"pith_short_16","alias_value":"RRZPK7RTCK2USAJB","created_at":"2026-07-05T09:13:07.157336+00:00"},{"alias_kind":"pith_short_8","alias_value":"RRZPK7RT","created_at":"2026-07-05T09:13:07.157336+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.19839","citing_title":"Environmental Understanding Vision-Language Model for Embodied Agent","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RRZPK7RTCK2USAJBY2NPK6FHYE","json":"https://pith.science/pith/RRZPK7RTCK2USAJBY2NPK6FHYE.json","graph_json":"https://pith.science/api/pith-number/RRZPK7RTCK2USAJBY2NPK6FHYE/graph.json","events_json":"https://pith.science/api/pith-number/RRZPK7RTCK2USAJBY2NPK6FHYE/events.json","paper":"https://pith.science/paper/RRZPK7RT"},"agent_actions":{"view_html":"https://pith.science/pith/RRZPK7RTCK2USAJBY2NPK6FHYE","download_json":"https://pith.science/pith/RRZPK7RTCK2USAJBY2NPK6FHYE.json","view_paper":"https://pith.science/paper/RRZPK7RT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.03256&json=true","fetch_graph":"https://pith.science/api/pith-number/RRZPK7RTCK2USAJBY2NPK6FHYE/graph.json","fetch_events":"https://pith.science/api/pith-number/RRZPK7RTCK2USAJBY2NPK6FHYE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RRZPK7RTCK2USAJBY2NPK6FHYE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RRZPK7RTCK2USAJBY2NPK6FHYE/action/storage_attestation","attest_author":"https://pith.science/pith/RRZPK7RTCK2USAJBY2NPK6FHYE/action/author_attestation","sign_citation":"https://pith.science/pith/RRZPK7RTCK2USAJBY2NPK6FHYE/action/citation_signature","submit_replication":"https://pith.science/pith/RRZPK7RTCK2USAJBY2NPK6FHYE/action/replication_record"}},"created_at":"2026-07-05T09:13:07.157336+00:00","updated_at":"2026-07-05T09:13:07.157336+00:00"}