{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:S6F5KAB3YFIUQIUVCCBVFMR2WC","short_pith_number":"pith:S6F5KAB3","schema_version":"1.0","canonical_sha256":"978bd5003bc151482295108352b23ab08acea36e7d51bf9822b5520db3b04cdf","source":{"kind":"arxiv","id":"2507.04524","version":1},"attestation_state":"computed","paper":{"title":"VLM-TDP: VLM-guided Trajectory-conditioned Diffusion Policy for Robust Long-Horizon Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Jiankun Wang, Kefeng Huang, Lei Han, Tingguang Li, Yuzhen Liu, Zhe Zhang","submitted_at":"2025-07-06T20:27:11Z","abstract_excerpt":"Diffusion policy has demonstrated promising performance in the field of robotic manipulation. However, its effectiveness has been primarily limited in short-horizon tasks, and its performance significantly degrades in the presence of image noise. To address these limitations, we propose a VLM-guided trajectory-conditioned diffusion policy (VLM-TDP) for robust and long-horizon manipulation. Specifically, the proposed method leverages state-of-the-art vision-language models (VLMs) to decompose long-horizon tasks into concise, manageable sub-tasks, while also innovatively generating voxel-based t"},"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":"2507.04524","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-07-06T20:27:11Z","cross_cats_sorted":[],"title_canon_sha256":"d1df2595b50f79b2f38d5a6481dcc958368459a17f44af7c25fef0eaada56ccd","abstract_canon_sha256":"c47da7501c9898ecd15422718d5e0634b216da5e08260f9fc280780b80825e4c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:49.363793Z","signature_b64":"FNJOeMBhGSOWnxMkt7u4LQXvGjiWSMlFjiMOytnhFYIYQ/a1Uda6XCnn17R/nUHqZJO6zFYrHpdPSamPyap5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"978bd5003bc151482295108352b23ab08acea36e7d51bf9822b5520db3b04cdf","last_reissued_at":"2026-07-05T11:32:49.363289Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:49.363289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VLM-TDP: VLM-guided Trajectory-conditioned Diffusion Policy for Robust Long-Horizon Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Jiankun Wang, Kefeng Huang, Lei Han, Tingguang Li, Yuzhen Liu, Zhe Zhang","submitted_at":"2025-07-06T20:27:11Z","abstract_excerpt":"Diffusion policy has demonstrated promising performance in the field of robotic manipulation. However, its effectiveness has been primarily limited in short-horizon tasks, and its performance significantly degrades in the presence of image noise. To address these limitations, we propose a VLM-guided trajectory-conditioned diffusion policy (VLM-TDP) for robust and long-horizon manipulation. Specifically, the proposed method leverages state-of-the-art vision-language models (VLMs) to decompose long-horizon tasks into concise, manageable sub-tasks, while also innovatively generating voxel-based t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04524","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/2507.04524/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":"2507.04524","created_at":"2026-07-05T11:32:49.363358+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.04524v1","created_at":"2026-07-05T11:32:49.363358+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04524","created_at":"2026-07-05T11:32:49.363358+00:00"},{"alias_kind":"pith_short_12","alias_value":"S6F5KAB3YFIU","created_at":"2026-07-05T11:32:49.363358+00:00"},{"alias_kind":"pith_short_16","alias_value":"S6F5KAB3YFIUQIUV","created_at":"2026-07-05T11:32:49.363358+00:00"},{"alias_kind":"pith_short_8","alias_value":"S6F5KAB3","created_at":"2026-07-05T11:32:49.363358+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.12710","citing_title":"Reflection-Based Task Adaptation for Self-Improving VLA","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S6F5KAB3YFIUQIUVCCBVFMR2WC","json":"https://pith.science/pith/S6F5KAB3YFIUQIUVCCBVFMR2WC.json","graph_json":"https://pith.science/api/pith-number/S6F5KAB3YFIUQIUVCCBVFMR2WC/graph.json","events_json":"https://pith.science/api/pith-number/S6F5KAB3YFIUQIUVCCBVFMR2WC/events.json","paper":"https://pith.science/paper/S6F5KAB3"},"agent_actions":{"view_html":"https://pith.science/pith/S6F5KAB3YFIUQIUVCCBVFMR2WC","download_json":"https://pith.science/pith/S6F5KAB3YFIUQIUVCCBVFMR2WC.json","view_paper":"https://pith.science/paper/S6F5KAB3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.04524&json=true","fetch_graph":"https://pith.science/api/pith-number/S6F5KAB3YFIUQIUVCCBVFMR2WC/graph.json","fetch_events":"https://pith.science/api/pith-number/S6F5KAB3YFIUQIUVCCBVFMR2WC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S6F5KAB3YFIUQIUVCCBVFMR2WC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S6F5KAB3YFIUQIUVCCBVFMR2WC/action/storage_attestation","attest_author":"https://pith.science/pith/S6F5KAB3YFIUQIUVCCBVFMR2WC/action/author_attestation","sign_citation":"https://pith.science/pith/S6F5KAB3YFIUQIUVCCBVFMR2WC/action/citation_signature","submit_replication":"https://pith.science/pith/S6F5KAB3YFIUQIUVCCBVFMR2WC/action/replication_record"}},"created_at":"2026-07-05T11:32:49.363358+00:00","updated_at":"2026-07-05T11:32:49.363358+00:00"}