{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YJPGLGCGOXUHNTLOC67CW35MAZ","short_pith_number":"pith:YJPGLGCG","schema_version":"1.0","canonical_sha256":"c25e65984675e876cd6e17be2b6fac064f425fb68cde5983bf16d041dcb42414","source":{"kind":"arxiv","id":"2504.15263","version":1},"attestation_state":"computed","paper":{"title":"Interpretable Locomotion Prediction in Construction Using a Memory-Driven LLM Agent With Chain-of-Thought Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chao Wang, Ehsan Ahmadi","submitted_at":"2025-04-21T17:45:21Z","abstract_excerpt":"Construction tasks are inherently unpredictable, with dynamic environments and safety-critical demands posing significant risks to workers. Exoskeletons offer potential assistance but falter without accurate intent recognition across diverse locomotion modes. This paper presents a locomotion prediction agent leveraging Large Language Models (LLMs) augmented with memory systems, aimed at improving exoskeleton assistance in such settings. Using multimodal inputs - spoken commands and visual data from smart glasses - the agent integrates a Perception Module, Short-Term Memory (STM), Long-Term Mem"},"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":"2504.15263","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-04-21T17:45:21Z","cross_cats_sorted":[],"title_canon_sha256":"e6b4180b6ae90056d0436fb770574de8666db55c9d2fac4f9b86d1277071d8fc","abstract_canon_sha256":"bb322f41fec3aec48627621528706eed0b008036ba6e44113714ea98d93b4a50"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:58.994096Z","signature_b64":"FENhsRohk9cUe4W2z5TnOOpZsch4ayITWID2H0WiZHY0pJbsEvFXgb5i8RVTWmbUAbdeHIGG31QxAvOXLfqDAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c25e65984675e876cd6e17be2b6fac064f425fb68cde5983bf16d041dcb42414","last_reissued_at":"2026-07-05T10:51:58.993608Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:58.993608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interpretable Locomotion Prediction in Construction Using a Memory-Driven LLM Agent With Chain-of-Thought Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chao Wang, Ehsan Ahmadi","submitted_at":"2025-04-21T17:45:21Z","abstract_excerpt":"Construction tasks are inherently unpredictable, with dynamic environments and safety-critical demands posing significant risks to workers. Exoskeletons offer potential assistance but falter without accurate intent recognition across diverse locomotion modes. This paper presents a locomotion prediction agent leveraging Large Language Models (LLMs) augmented with memory systems, aimed at improving exoskeleton assistance in such settings. Using multimodal inputs - spoken commands and visual data from smart glasses - the agent integrates a Perception Module, Short-Term Memory (STM), Long-Term Mem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15263","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/2504.15263/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":"2504.15263","created_at":"2026-07-05T10:51:58.993668+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.15263v1","created_at":"2026-07-05T10:51:58.993668+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15263","created_at":"2026-07-05T10:51:58.993668+00:00"},{"alias_kind":"pith_short_12","alias_value":"YJPGLGCGOXUH","created_at":"2026-07-05T10:51:58.993668+00:00"},{"alias_kind":"pith_short_16","alias_value":"YJPGLGCGOXUHNTLO","created_at":"2026-07-05T10:51:58.993668+00:00"},{"alias_kind":"pith_short_8","alias_value":"YJPGLGCG","created_at":"2026-07-05T10:51:58.993668+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/YJPGLGCGOXUHNTLOC67CW35MAZ","json":"https://pith.science/pith/YJPGLGCGOXUHNTLOC67CW35MAZ.json","graph_json":"https://pith.science/api/pith-number/YJPGLGCGOXUHNTLOC67CW35MAZ/graph.json","events_json":"https://pith.science/api/pith-number/YJPGLGCGOXUHNTLOC67CW35MAZ/events.json","paper":"https://pith.science/paper/YJPGLGCG"},"agent_actions":{"view_html":"https://pith.science/pith/YJPGLGCGOXUHNTLOC67CW35MAZ","download_json":"https://pith.science/pith/YJPGLGCGOXUHNTLOC67CW35MAZ.json","view_paper":"https://pith.science/paper/YJPGLGCG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.15263&json=true","fetch_graph":"https://pith.science/api/pith-number/YJPGLGCGOXUHNTLOC67CW35MAZ/graph.json","fetch_events":"https://pith.science/api/pith-number/YJPGLGCGOXUHNTLOC67CW35MAZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YJPGLGCGOXUHNTLOC67CW35MAZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YJPGLGCGOXUHNTLOC67CW35MAZ/action/storage_attestation","attest_author":"https://pith.science/pith/YJPGLGCGOXUHNTLOC67CW35MAZ/action/author_attestation","sign_citation":"https://pith.science/pith/YJPGLGCGOXUHNTLOC67CW35MAZ/action/citation_signature","submit_replication":"https://pith.science/pith/YJPGLGCGOXUHNTLOC67CW35MAZ/action/replication_record"}},"created_at":"2026-07-05T10:51:58.993668+00:00","updated_at":"2026-07-05T10:51:58.993668+00:00"}