{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WILPW6H4K4KIXKRF6ZS3UKJO7N","short_pith_number":"pith:WILPW6H4","schema_version":"1.0","canonical_sha256":"b216fb78fc57148baa25f665ba292efb570f0992924254d82e45aeb355cf74de","source":{"kind":"arxiv","id":"2504.01301","version":2},"attestation_state":"computed","paper":{"title":"Bi-LAT: Bilateral Control-Based Imitation Learning via Natural Language and Action Chunking with Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Masato Kobayashi, Takumi Kobayashi, Thanpimon Buamanee, Yuki Uranishi","submitted_at":"2025-04-02T02:21:30Z","abstract_excerpt":"We present Bi-LAT, a novel imitation learning framework that unifies bilateral control with natural language processing to achieve precise force modulation in robotic manipulation. Bi-LAT leverages joint position, velocity, and torque data from leader-follower teleoperation while also integrating visual and linguistic cues to dynamically adjust applied force. By encoding human instructions such as \"softly grasp the cup\" or \"strongly twist the sponge\" through a multimodal Transformer-based model, Bi-LAT learns to distinguish nuanced force requirements in real-world tasks. We demonstrate Bi-LAT'"},"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":"2504.01301","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-04-02T02:21:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b5e7840bfaa4343aac888092d6d87373c3479d86c97d6bbeea8f1936463d6930","abstract_canon_sha256":"8dd0e6e1172c9cf7bd7a193b20a91a3bacf7ffa683fb691d7c711096d0cac50d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:03.723781Z","signature_b64":"qUmu28+Ri19v+MqZCrTcdOw5v86KeNZGU8qtqYwrFgRcCkhYAC0ShmbtT418/QUPGZMi1DMQ+zocOk9tQY0vBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b216fb78fc57148baa25f665ba292efb570f0992924254d82e45aeb355cf74de","last_reissued_at":"2026-07-05T11:44:03.723224Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:03.723224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bi-LAT: Bilateral Control-Based Imitation Learning via Natural Language and Action Chunking with Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Masato Kobayashi, Takumi Kobayashi, Thanpimon Buamanee, Yuki Uranishi","submitted_at":"2025-04-02T02:21:30Z","abstract_excerpt":"We present Bi-LAT, a novel imitation learning framework that unifies bilateral control with natural language processing to achieve precise force modulation in robotic manipulation. Bi-LAT leverages joint position, velocity, and torque data from leader-follower teleoperation while also integrating visual and linguistic cues to dynamically adjust applied force. By encoding human instructions such as \"softly grasp the cup\" or \"strongly twist the sponge\" through a multimodal Transformer-based model, Bi-LAT learns to distinguish nuanced force requirements in real-world tasks. We demonstrate Bi-LAT'"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.01301","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/2504.01301/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":"2504.01301","created_at":"2026-07-05T11:44:03.723279+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.01301v2","created_at":"2026-07-05T11:44:03.723279+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.01301","created_at":"2026-07-05T11:44:03.723279+00:00"},{"alias_kind":"pith_short_12","alias_value":"WILPW6H4K4KI","created_at":"2026-07-05T11:44:03.723279+00:00"},{"alias_kind":"pith_short_16","alias_value":"WILPW6H4K4KIXKRF","created_at":"2026-07-05T11:44:03.723279+00:00"},{"alias_kind":"pith_short_8","alias_value":"WILPW6H4","created_at":"2026-07-05T11:44:03.723279+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.07962","citing_title":"TA-VLA: Elucidating the Design Space of Torque-aware Vision-Language-Action Models","ref_index":50,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WILPW6H4K4KIXKRF6ZS3UKJO7N","json":"https://pith.science/pith/WILPW6H4K4KIXKRF6ZS3UKJO7N.json","graph_json":"https://pith.science/api/pith-number/WILPW6H4K4KIXKRF6ZS3UKJO7N/graph.json","events_json":"https://pith.science/api/pith-number/WILPW6H4K4KIXKRF6ZS3UKJO7N/events.json","paper":"https://pith.science/paper/WILPW6H4"},"agent_actions":{"view_html":"https://pith.science/pith/WILPW6H4K4KIXKRF6ZS3UKJO7N","download_json":"https://pith.science/pith/WILPW6H4K4KIXKRF6ZS3UKJO7N.json","view_paper":"https://pith.science/paper/WILPW6H4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.01301&json=true","fetch_graph":"https://pith.science/api/pith-number/WILPW6H4K4KIXKRF6ZS3UKJO7N/graph.json","fetch_events":"https://pith.science/api/pith-number/WILPW6H4K4KIXKRF6ZS3UKJO7N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WILPW6H4K4KIXKRF6ZS3UKJO7N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WILPW6H4K4KIXKRF6ZS3UKJO7N/action/storage_attestation","attest_author":"https://pith.science/pith/WILPW6H4K4KIXKRF6ZS3UKJO7N/action/author_attestation","sign_citation":"https://pith.science/pith/WILPW6H4K4KIXKRF6ZS3UKJO7N/action/citation_signature","submit_replication":"https://pith.science/pith/WILPW6H4K4KIXKRF6ZS3UKJO7N/action/replication_record"}},"created_at":"2026-07-05T11:44:03.723279+00:00","updated_at":"2026-07-05T11:44:03.723279+00:00"}