{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:52GU2W47JA4LS6N33AY5F6J7OU","short_pith_number":"pith:52GU2W47","schema_version":"1.0","canonical_sha256":"ee8d4d5b9f4838b979bbd831d2f93f75240d3ccbef8b37fe15b6efc0f5c48337","source":{"kind":"arxiv","id":"2411.14519","version":2},"attestation_state":"computed","paper":{"title":"Tra-MoE: Learning Trajectory Prediction Model from Multiple Domains for Adaptive Policy Conditioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Gangshan Wu, Haoyi Zhu, Jiange Yang, Limin Wang, Tong He, Yating Wang","submitted_at":"2024-11-21T16:45:43Z","abstract_excerpt":"Learning from multiple domains is a primary factor that influences the generalization of a single unified robot system. In this paper, we aim to learn the trajectory prediction model by using broad out-of-domain data to improve its performance and generalization ability. Trajectory model is designed to predict any-point trajectories in the current frame given an instruction and can provide detailed control guidance for robotic policy learning. To handle the diverse out-of-domain data distribution, we propose a sparsely-gated MoE (\\textbf{Top-1} gating strategy) architecture for trajectory mode"},"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":"2411.14519","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-11-21T16:45:43Z","cross_cats_sorted":[],"title_canon_sha256":"6f3f413aaf887de97f33fabaf4deda6fb605a57880e6122323c1258f2a6ba8a1","abstract_canon_sha256":"7a78ef16944fffad6d3f2216ed44e3baa56236db85b20e9596a70b32edff59ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:42:39.318832Z","signature_b64":"CORvZURFeMKmubhyttMLXEROsbkQEjNA2DuTNwWIM0YtXa9nEEu+QomNb7lLrU5k5EtDAWBC/chMpBFmixrFBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee8d4d5b9f4838b979bbd831d2f93f75240d3ccbef8b37fe15b6efc0f5c48337","last_reissued_at":"2026-07-05T10:42:39.318337Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:42:39.318337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tra-MoE: Learning Trajectory Prediction Model from Multiple Domains for Adaptive Policy Conditioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Gangshan Wu, Haoyi Zhu, Jiange Yang, Limin Wang, Tong He, Yating Wang","submitted_at":"2024-11-21T16:45:43Z","abstract_excerpt":"Learning from multiple domains is a primary factor that influences the generalization of a single unified robot system. In this paper, we aim to learn the trajectory prediction model by using broad out-of-domain data to improve its performance and generalization ability. Trajectory model is designed to predict any-point trajectories in the current frame given an instruction and can provide detailed control guidance for robotic policy learning. To handle the diverse out-of-domain data distribution, we propose a sparsely-gated MoE (\\textbf{Top-1} gating strategy) architecture for trajectory mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14519","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/2411.14519/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":"2411.14519","created_at":"2026-07-05T10:42:39.318397+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.14519v2","created_at":"2026-07-05T10:42:39.318397+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14519","created_at":"2026-07-05T10:42:39.318397+00:00"},{"alias_kind":"pith_short_12","alias_value":"52GU2W47JA4L","created_at":"2026-07-05T10:42:39.318397+00:00"},{"alias_kind":"pith_short_16","alias_value":"52GU2W47JA4LS6N3","created_at":"2026-07-05T10:42:39.318397+00:00"},{"alias_kind":"pith_short_8","alias_value":"52GU2W47","created_at":"2026-07-05T10:42:39.318397+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.04447","citing_title":"DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge","ref_index":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/52GU2W47JA4LS6N33AY5F6J7OU","json":"https://pith.science/pith/52GU2W47JA4LS6N33AY5F6J7OU.json","graph_json":"https://pith.science/api/pith-number/52GU2W47JA4LS6N33AY5F6J7OU/graph.json","events_json":"https://pith.science/api/pith-number/52GU2W47JA4LS6N33AY5F6J7OU/events.json","paper":"https://pith.science/paper/52GU2W47"},"agent_actions":{"view_html":"https://pith.science/pith/52GU2W47JA4LS6N33AY5F6J7OU","download_json":"https://pith.science/pith/52GU2W47JA4LS6N33AY5F6J7OU.json","view_paper":"https://pith.science/paper/52GU2W47","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.14519&json=true","fetch_graph":"https://pith.science/api/pith-number/52GU2W47JA4LS6N33AY5F6J7OU/graph.json","fetch_events":"https://pith.science/api/pith-number/52GU2W47JA4LS6N33AY5F6J7OU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/52GU2W47JA4LS6N33AY5F6J7OU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/52GU2W47JA4LS6N33AY5F6J7OU/action/storage_attestation","attest_author":"https://pith.science/pith/52GU2W47JA4LS6N33AY5F6J7OU/action/author_attestation","sign_citation":"https://pith.science/pith/52GU2W47JA4LS6N33AY5F6J7OU/action/citation_signature","submit_replication":"https://pith.science/pith/52GU2W47JA4LS6N33AY5F6J7OU/action/replication_record"}},"created_at":"2026-07-05T10:42:39.318397+00:00","updated_at":"2026-07-05T10:42:39.318397+00:00"}