{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CVRBUXC4YBFSAGP372ZN63HQYX","short_pith_number":"pith:CVRBUXC4","schema_version":"1.0","canonical_sha256":"15621a5c5cc04b2019fbfeb2df6cf0c5ece1b2ddffc73dffa3192579d30128b0","source":{"kind":"arxiv","id":"2607.28560","version":1},"attestation_state":"computed","paper":{"title":"X-NavDP: Generalizing Navigation Diffusion Policy to Novel Behavior and Embodiments with Group Q-score Reweighted Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Hui Cheng, Jiangmiao Pang, Jiaqi Peng, Tai Wang, Tianyu Yang, Wenzhe Cai, Yiming Zeng, Yuqiang Yang","submitted_at":"2026-07-30T17:26:12Z","abstract_excerpt":"Pretraining navigation diffusion policies rely on large-scale expert demonstrations. These data are typically generated by a fully-informed oracle planner suited to a single nominal robot. This limits the policy's generalization to diverse embodiments and challenging scenarios (e.g., escaping dead ends or detouring long obstacles) that demand diverse local reactive behaviors with only onboard local observations. Post-training the policy with reinforcement learning (RL) offers a principled remedy. However, previous RL for diffusion approaches lead to only marginal improvements. This is because "},"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":"2607.28560","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-30T17:26:12Z","cross_cats_sorted":[],"title_canon_sha256":"3b0a795dd5b29deae105d6d2813ee0753f68921a8d8798c7b941fbb872e8c6a1","abstract_canon_sha256":"b23041aefbd9a36526d9b212126e042ac5c632c73237831ca66fed7be470537f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15621a5c5cc04b2019fbfeb2df6cf0c5ece1b2ddffc73dffa3192579d30128b0","last_reissued_at":"2026-07-31T01:38:32.382832Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:38:32.382832Z"},"graph_snapshot":{"paper":{"title":"X-NavDP: Generalizing Navigation Diffusion Policy to Novel Behavior and Embodiments with Group Q-score Reweighted Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Hui Cheng, Jiangmiao Pang, Jiaqi Peng, Tai Wang, Tianyu Yang, Wenzhe Cai, Yiming Zeng, Yuqiang Yang","submitted_at":"2026-07-30T17:26:12Z","abstract_excerpt":"Pretraining navigation diffusion policies rely on large-scale expert demonstrations. These data are typically generated by a fully-informed oracle planner suited to a single nominal robot. This limits the policy's generalization to diverse embodiments and challenging scenarios (e.g., escaping dead ends or detouring long obstacles) that demand diverse local reactive behaviors with only onboard local observations. Post-training the policy with reinforcement learning (RL) offers a principled remedy. However, previous RL for diffusion approaches lead to only marginal improvements. This is because "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28560","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/2607.28560/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":"2607.28560","created_at":"2026-07-31T01:38:32.385991+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.28560v1","created_at":"2026-07-31T01:38:32.385991+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28560","created_at":"2026-07-31T01:38:32.385991+00:00"},{"alias_kind":"pith_short_12","alias_value":"CVRBUXC4YBFS","created_at":"2026-07-31T01:38:32.385991+00:00"},{"alias_kind":"pith_short_16","alias_value":"CVRBUXC4YBFSAGP3","created_at":"2026-07-31T01:38:32.385991+00:00"},{"alias_kind":"pith_short_8","alias_value":"CVRBUXC4","created_at":"2026-07-31T01:38:32.385991+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/CVRBUXC4YBFSAGP372ZN63HQYX","json":"https://pith.science/pith/CVRBUXC4YBFSAGP372ZN63HQYX.json","graph_json":"https://pith.science/api/pith-number/CVRBUXC4YBFSAGP372ZN63HQYX/graph.json","events_json":"https://pith.science/api/pith-number/CVRBUXC4YBFSAGP372ZN63HQYX/events.json","paper":"https://pith.science/paper/CVRBUXC4"},"agent_actions":{"view_html":"https://pith.science/pith/CVRBUXC4YBFSAGP372ZN63HQYX","download_json":"https://pith.science/pith/CVRBUXC4YBFSAGP372ZN63HQYX.json","view_paper":"https://pith.science/paper/CVRBUXC4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.28560&json=true","fetch_graph":"https://pith.science/api/pith-number/CVRBUXC4YBFSAGP372ZN63HQYX/graph.json","fetch_events":"https://pith.science/api/pith-number/CVRBUXC4YBFSAGP372ZN63HQYX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CVRBUXC4YBFSAGP372ZN63HQYX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CVRBUXC4YBFSAGP372ZN63HQYX/action/storage_attestation","attest_author":"https://pith.science/pith/CVRBUXC4YBFSAGP372ZN63HQYX/action/author_attestation","sign_citation":"https://pith.science/pith/CVRBUXC4YBFSAGP372ZN63HQYX/action/citation_signature","submit_replication":"https://pith.science/pith/CVRBUXC4YBFSAGP372ZN63HQYX/action/replication_record"}},"created_at":"2026-07-31T01:38:32.385991+00:00","updated_at":"2026-07-31T01:38:32.385991+00:00"}