{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FSMOC5B4SIUNY2JHMXLY57M73Q","short_pith_number":"pith:FSMOC5B4","schema_version":"1.0","canonical_sha256":"2c98e1743c9228dc692765d78efd9fdc1b258925db97bc5303e135079f967305","source":{"kind":"arxiv","id":"2509.08222","version":1},"attestation_state":"computed","paper":{"title":"Exploratory Retrieval-Augmented Planning For Continual Embodied Instruction Following","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Honguk Woo, Jinwoo Jang, Minjong Yoo, Wei-Jin Park","submitted_at":"2025-09-10T01:39:51Z","abstract_excerpt":"This study presents an Exploratory Retrieval-Augmented Planning (ExRAP) framework, designed to tackle continual instruction following tasks of embodied agents in dynamic, non-stationary environments. The framework enhances Large Language Models' (LLMs) embodied reasoning capabilities by efficiently exploring the physical environment and establishing the environmental context memory, thereby effectively grounding the task planning process in time-varying environment contexts. In ExRAP, given multiple continual instruction following tasks, each instruction is decomposed into queries on the envir"},"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":"2509.08222","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-09-10T01:39:51Z","cross_cats_sorted":[],"title_canon_sha256":"7d3c2a7f54784fc9c72f5ec1433d708bcc48e3dafd692f92a2f5aac06a23f128","abstract_canon_sha256":"8ab1e3bbb00e0388ed7ecfa490975413671e22607e6d5f22974e35f07f3c427a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:08:25.379860Z","signature_b64":"2hdDkTV9llBYJeCGqfLLU+9wwkVatCtfkA2uw0p2mezTK+GixuQL5hBak2SZl/vJ9oXGPff7jziJ82IIaP4OAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c98e1743c9228dc692765d78efd9fdc1b258925db97bc5303e135079f967305","last_reissued_at":"2026-07-05T12:08:25.379286Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:08:25.379286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploratory Retrieval-Augmented Planning For Continual Embodied Instruction Following","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Honguk Woo, Jinwoo Jang, Minjong Yoo, Wei-Jin Park","submitted_at":"2025-09-10T01:39:51Z","abstract_excerpt":"This study presents an Exploratory Retrieval-Augmented Planning (ExRAP) framework, designed to tackle continual instruction following tasks of embodied agents in dynamic, non-stationary environments. The framework enhances Large Language Models' (LLMs) embodied reasoning capabilities by efficiently exploring the physical environment and establishing the environmental context memory, thereby effectively grounding the task planning process in time-varying environment contexts. In ExRAP, given multiple continual instruction following tasks, each instruction is decomposed into queries on the envir"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.08222","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/2509.08222/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":"2509.08222","created_at":"2026-07-05T12:08:25.379362+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.08222v1","created_at":"2026-07-05T12:08:25.379362+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.08222","created_at":"2026-07-05T12:08:25.379362+00:00"},{"alias_kind":"pith_short_12","alias_value":"FSMOC5B4SIUN","created_at":"2026-07-05T12:08:25.379362+00:00"},{"alias_kind":"pith_short_16","alias_value":"FSMOC5B4SIUNY2JH","created_at":"2026-07-05T12:08:25.379362+00:00"},{"alias_kind":"pith_short_8","alias_value":"FSMOC5B4","created_at":"2026-07-05T12:08:25.379362+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/FSMOC5B4SIUNY2JHMXLY57M73Q","json":"https://pith.science/pith/FSMOC5B4SIUNY2JHMXLY57M73Q.json","graph_json":"https://pith.science/api/pith-number/FSMOC5B4SIUNY2JHMXLY57M73Q/graph.json","events_json":"https://pith.science/api/pith-number/FSMOC5B4SIUNY2JHMXLY57M73Q/events.json","paper":"https://pith.science/paper/FSMOC5B4"},"agent_actions":{"view_html":"https://pith.science/pith/FSMOC5B4SIUNY2JHMXLY57M73Q","download_json":"https://pith.science/pith/FSMOC5B4SIUNY2JHMXLY57M73Q.json","view_paper":"https://pith.science/paper/FSMOC5B4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.08222&json=true","fetch_graph":"https://pith.science/api/pith-number/FSMOC5B4SIUNY2JHMXLY57M73Q/graph.json","fetch_events":"https://pith.science/api/pith-number/FSMOC5B4SIUNY2JHMXLY57M73Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FSMOC5B4SIUNY2JHMXLY57M73Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FSMOC5B4SIUNY2JHMXLY57M73Q/action/storage_attestation","attest_author":"https://pith.science/pith/FSMOC5B4SIUNY2JHMXLY57M73Q/action/author_attestation","sign_citation":"https://pith.science/pith/FSMOC5B4SIUNY2JHMXLY57M73Q/action/citation_signature","submit_replication":"https://pith.science/pith/FSMOC5B4SIUNY2JHMXLY57M73Q/action/replication_record"}},"created_at":"2026-07-05T12:08:25.379362+00:00","updated_at":"2026-07-05T12:08:25.379362+00:00"}