{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7XSEZBLPF4HJ3ECWAF4GRVLHLP","short_pith_number":"pith:7XSEZBLP","schema_version":"1.0","canonical_sha256":"fde44c856f2f0e9d9056017868d5675bc595dab848d3cc6fd7e2ac571b8b5d32","source":{"kind":"arxiv","id":"2406.09767","version":3},"attestation_state":"computed","paper":{"title":"DISCO: Language-Guided Manipulation with Diffusion Policies and Constrained Inpainting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ce Hao, Harold Soh, Kelvin Lin, Siyuan Luo, Zhiwei Xue","submitted_at":"2024-06-14T07:12:15Z","abstract_excerpt":"Diffusion policies have demonstrated strong performance in generative modeling, making them promising for robotic manipulation guided by natural language instructions. However, generalizing language-conditioned diffusion policies to open-vocabulary instructions in everyday scenarios remains challenging due to the scarcity and cost of robot demonstration datasets. To address this, we propose DISCO, a framework that leverages off-the-shelf vision-language models (VLMs) to bridge natural language understanding with high-performance diffusion policies. DISCO translates linguistic task descriptions"},"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":"2406.09767","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-06-14T07:12:15Z","cross_cats_sorted":[],"title_canon_sha256":"e5a080788372d034989d770da462664f265bdecf2be7c2ceef0d4ed2568f8d48","abstract_canon_sha256":"cc67cce33526e384e7e32fcf5282f3121a762bb2b64a46cd91e8d71dd678fcf6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:35.689281Z","signature_b64":"NUx2b021vPRK/dxUJvkaT+TrndwxnAJA9pzz61eF4ZBd5jmRI2w5LSLLYGykznbYlU8uOrMxDSwAP8dfWBO0AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fde44c856f2f0e9d9056017868d5675bc595dab848d3cc6fd7e2ac571b8b5d32","last_reissued_at":"2026-07-05T11:55:35.688807Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:35.688807Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DISCO: Language-Guided Manipulation with Diffusion Policies and Constrained Inpainting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ce Hao, Harold Soh, Kelvin Lin, Siyuan Luo, Zhiwei Xue","submitted_at":"2024-06-14T07:12:15Z","abstract_excerpt":"Diffusion policies have demonstrated strong performance in generative modeling, making them promising for robotic manipulation guided by natural language instructions. However, generalizing language-conditioned diffusion policies to open-vocabulary instructions in everyday scenarios remains challenging due to the scarcity and cost of robot demonstration datasets. To address this, we propose DISCO, a framework that leverages off-the-shelf vision-language models (VLMs) to bridge natural language understanding with high-performance diffusion policies. DISCO translates linguistic task descriptions"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09767","kind":"arxiv","version":3},"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/2406.09767/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":"2406.09767","created_at":"2026-07-05T11:55:35.688872+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.09767v3","created_at":"2026-07-05T11:55:35.688872+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09767","created_at":"2026-07-05T11:55:35.688872+00:00"},{"alias_kind":"pith_short_12","alias_value":"7XSEZBLPF4HJ","created_at":"2026-07-05T11:55:35.688872+00:00"},{"alias_kind":"pith_short_16","alias_value":"7XSEZBLPF4HJ3ECW","created_at":"2026-07-05T11:55:35.688872+00:00"},{"alias_kind":"pith_short_8","alias_value":"7XSEZBLP","created_at":"2026-07-05T11:55:35.688872+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.09444","citing_title":"DAgger Diffusion Navigation: DAgger Boosted Diffusion Policy for Vision-Language Navigation","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7XSEZBLPF4HJ3ECWAF4GRVLHLP","json":"https://pith.science/pith/7XSEZBLPF4HJ3ECWAF4GRVLHLP.json","graph_json":"https://pith.science/api/pith-number/7XSEZBLPF4HJ3ECWAF4GRVLHLP/graph.json","events_json":"https://pith.science/api/pith-number/7XSEZBLPF4HJ3ECWAF4GRVLHLP/events.json","paper":"https://pith.science/paper/7XSEZBLP"},"agent_actions":{"view_html":"https://pith.science/pith/7XSEZBLPF4HJ3ECWAF4GRVLHLP","download_json":"https://pith.science/pith/7XSEZBLPF4HJ3ECWAF4GRVLHLP.json","view_paper":"https://pith.science/paper/7XSEZBLP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.09767&json=true","fetch_graph":"https://pith.science/api/pith-number/7XSEZBLPF4HJ3ECWAF4GRVLHLP/graph.json","fetch_events":"https://pith.science/api/pith-number/7XSEZBLPF4HJ3ECWAF4GRVLHLP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7XSEZBLPF4HJ3ECWAF4GRVLHLP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7XSEZBLPF4HJ3ECWAF4GRVLHLP/action/storage_attestation","attest_author":"https://pith.science/pith/7XSEZBLPF4HJ3ECWAF4GRVLHLP/action/author_attestation","sign_citation":"https://pith.science/pith/7XSEZBLPF4HJ3ECWAF4GRVLHLP/action/citation_signature","submit_replication":"https://pith.science/pith/7XSEZBLPF4HJ3ECWAF4GRVLHLP/action/replication_record"}},"created_at":"2026-07-05T11:55:35.688872+00:00","updated_at":"2026-07-05T11:55:35.688872+00:00"}