{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2W44YYABH6TP43L2TN442JLHFZ","short_pith_number":"pith:2W44YYAB","schema_version":"1.0","canonical_sha256":"d5b9cc60013fa6fe6d7a9b79cd25672e7dd689ca9479ce0f287398ea1e8a3e00","source":{"kind":"arxiv","id":"2407.15660","version":2},"attestation_state":"computed","paper":{"title":"MuTT: A Multimodal Trajectory Transformer for Robot Skills","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Benjamin Alt, Claudius Kienle, Darko Katic, Gerhard Neumann, Onur Celik, Philipp Becker, Rainer J\\\"akel","submitted_at":"2024-07-22T14:18:52Z","abstract_excerpt":"High-level robot skills represent an increasingly popular paradigm in robot programming. However, configuring the skills' parameters for a specific task remains a manual and time-consuming endeavor. Existing approaches for learning or optimizing these parameters often require numerous real-world executions or do not work in dynamic environments. To address these challenges, we propose MuTT, a novel encoder-decoder transformer architecture designed to predict environment-aware executions of robot skills by integrating vision, trajectory, and robot skill parameters. Notably, we pioneer the fusio"},"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":"2407.15660","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2024-07-22T14:18:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d308e307f222c360fe2289ab1cca0cf7cffb366672ddb1cd8e99406d4bccc824","abstract_canon_sha256":"e8da6e93eae8847fbb3ecb17a06223fdfb61f0664c6d87b18b3c42e438047a89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:57.911541Z","signature_b64":"ppTXC5u1qIA3gITenooJzubBRkeKogxOiQ1+JD03mU8drV4OnHVGd4muN/U4u6dyfHVFm/6PHxxsrBeRMOLlAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5b9cc60013fa6fe6d7a9b79cd25672e7dd689ca9479ce0f287398ea1e8a3e00","last_reissued_at":"2026-07-05T08:57:57.911192Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:57.911192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MuTT: A Multimodal Trajectory Transformer for Robot Skills","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Benjamin Alt, Claudius Kienle, Darko Katic, Gerhard Neumann, Onur Celik, Philipp Becker, Rainer J\\\"akel","submitted_at":"2024-07-22T14:18:52Z","abstract_excerpt":"High-level robot skills represent an increasingly popular paradigm in robot programming. However, configuring the skills' parameters for a specific task remains a manual and time-consuming endeavor. Existing approaches for learning or optimizing these parameters often require numerous real-world executions or do not work in dynamic environments. To address these challenges, we propose MuTT, a novel encoder-decoder transformer architecture designed to predict environment-aware executions of robot skills by integrating vision, trajectory, and robot skill parameters. Notably, we pioneer the fusio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15660","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/2407.15660/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":"2407.15660","created_at":"2026-07-05T08:57:57.911240+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.15660v2","created_at":"2026-07-05T08:57:57.911240+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15660","created_at":"2026-07-05T08:57:57.911240+00:00"},{"alias_kind":"pith_short_12","alias_value":"2W44YYABH6TP","created_at":"2026-07-05T08:57:57.911240+00:00"},{"alias_kind":"pith_short_16","alias_value":"2W44YYABH6TP43L2","created_at":"2026-07-05T08:57:57.911240+00:00"},{"alias_kind":"pith_short_8","alias_value":"2W44YYAB","created_at":"2026-07-05T08:57:57.911240+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/2W44YYABH6TP43L2TN442JLHFZ","json":"https://pith.science/pith/2W44YYABH6TP43L2TN442JLHFZ.json","graph_json":"https://pith.science/api/pith-number/2W44YYABH6TP43L2TN442JLHFZ/graph.json","events_json":"https://pith.science/api/pith-number/2W44YYABH6TP43L2TN442JLHFZ/events.json","paper":"https://pith.science/paper/2W44YYAB"},"agent_actions":{"view_html":"https://pith.science/pith/2W44YYABH6TP43L2TN442JLHFZ","download_json":"https://pith.science/pith/2W44YYABH6TP43L2TN442JLHFZ.json","view_paper":"https://pith.science/paper/2W44YYAB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.15660&json=true","fetch_graph":"https://pith.science/api/pith-number/2W44YYABH6TP43L2TN442JLHFZ/graph.json","fetch_events":"https://pith.science/api/pith-number/2W44YYABH6TP43L2TN442JLHFZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2W44YYABH6TP43L2TN442JLHFZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2W44YYABH6TP43L2TN442JLHFZ/action/storage_attestation","attest_author":"https://pith.science/pith/2W44YYABH6TP43L2TN442JLHFZ/action/author_attestation","sign_citation":"https://pith.science/pith/2W44YYABH6TP43L2TN442JLHFZ/action/citation_signature","submit_replication":"https://pith.science/pith/2W44YYABH6TP43L2TN442JLHFZ/action/replication_record"}},"created_at":"2026-07-05T08:57:57.911240+00:00","updated_at":"2026-07-05T08:57:57.911240+00:00"}