{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UBMQQEK6OLD5KDM5CKY4YQRJ5D","short_pith_number":"pith:UBMQQEK6","schema_version":"1.0","canonical_sha256":"a05908115e72c7d50d9d12b1cc4229e8f3609b4ffd7917180972a749866a6dd3","source":{"kind":"arxiv","id":"2501.16458","version":2},"attestation_state":"computed","paper":{"title":"BiFold: Bimanual Cloth Folding with Language Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Adri\\`a Colom\\'e, Carme Torras, Oriol Barbany","submitted_at":"2025-01-27T19:37:18Z","abstract_excerpt":"Cloth folding is a complex task due to the inevitable self-occlusions of clothes, their complicated dynamics, and the disparate materials, geometries, and textures that garments can have. In this work, we learn folding actions conditioned on text commands. Translating high-level, abstract instructions into precise robotic actions requires sophisticated language understanding and manipulation capabilities. To do that, we leverage a pre-trained vision-language model and repurpose it to predict manipulation actions. Our model, BiFold, can take context into account and achieves state-of-the-art pe"},"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":"2501.16458","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-01-27T19:37:18Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"1898906d0ad26df39ae14ae9dc387a964391894480b4a9317827cec65435ea86","abstract_canon_sha256":"df2f69f1b62ea30259b8a60e4ba64a436f4155bea8d84cb4a84f7410e59d6fd4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:41.149179Z","signature_b64":"FlgmQyuH+FeF+NY/DkqAYhheEVkBtmUhKkJ7SjF3P0h0Mr4rWITyneOO6NUt2Tj65T066lJUlsfn6tOMLRRLBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a05908115e72c7d50d9d12b1cc4229e8f3609b4ffd7917180972a749866a6dd3","last_reissued_at":"2026-07-05T11:21:41.148564Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:41.148564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BiFold: Bimanual Cloth Folding with Language Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Adri\\`a Colom\\'e, Carme Torras, Oriol Barbany","submitted_at":"2025-01-27T19:37:18Z","abstract_excerpt":"Cloth folding is a complex task due to the inevitable self-occlusions of clothes, their complicated dynamics, and the disparate materials, geometries, and textures that garments can have. In this work, we learn folding actions conditioned on text commands. Translating high-level, abstract instructions into precise robotic actions requires sophisticated language understanding and manipulation capabilities. To do that, we leverage a pre-trained vision-language model and repurpose it to predict manipulation actions. Our model, BiFold, can take context into account and achieves state-of-the-art pe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16458","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/2501.16458/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":"2501.16458","created_at":"2026-07-05T11:21:41.148626+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.16458v2","created_at":"2026-07-05T11:21:41.148626+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16458","created_at":"2026-07-05T11:21:41.148626+00:00"},{"alias_kind":"pith_short_12","alias_value":"UBMQQEK6OLD5","created_at":"2026-07-05T11:21:41.148626+00:00"},{"alias_kind":"pith_short_16","alias_value":"UBMQQEK6OLD5KDM5","created_at":"2026-07-05T11:21:41.148626+00:00"},{"alias_kind":"pith_short_8","alias_value":"UBMQQEK6","created_at":"2026-07-05T11:21:41.148626+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.20239","citing_title":"TouchGuide: Inference-Time Steering of Visuomotor Policies via Touch Guidance","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17513","citing_title":"FLASH: Fast Learning via GPU-Accelerated Simulation for High-Fidelity Deformable Manipulation in Minutes","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UBMQQEK6OLD5KDM5CKY4YQRJ5D","json":"https://pith.science/pith/UBMQQEK6OLD5KDM5CKY4YQRJ5D.json","graph_json":"https://pith.science/api/pith-number/UBMQQEK6OLD5KDM5CKY4YQRJ5D/graph.json","events_json":"https://pith.science/api/pith-number/UBMQQEK6OLD5KDM5CKY4YQRJ5D/events.json","paper":"https://pith.science/paper/UBMQQEK6"},"agent_actions":{"view_html":"https://pith.science/pith/UBMQQEK6OLD5KDM5CKY4YQRJ5D","download_json":"https://pith.science/pith/UBMQQEK6OLD5KDM5CKY4YQRJ5D.json","view_paper":"https://pith.science/paper/UBMQQEK6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.16458&json=true","fetch_graph":"https://pith.science/api/pith-number/UBMQQEK6OLD5KDM5CKY4YQRJ5D/graph.json","fetch_events":"https://pith.science/api/pith-number/UBMQQEK6OLD5KDM5CKY4YQRJ5D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UBMQQEK6OLD5KDM5CKY4YQRJ5D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UBMQQEK6OLD5KDM5CKY4YQRJ5D/action/storage_attestation","attest_author":"https://pith.science/pith/UBMQQEK6OLD5KDM5CKY4YQRJ5D/action/author_attestation","sign_citation":"https://pith.science/pith/UBMQQEK6OLD5KDM5CKY4YQRJ5D/action/citation_signature","submit_replication":"https://pith.science/pith/UBMQQEK6OLD5KDM5CKY4YQRJ5D/action/replication_record"}},"created_at":"2026-07-05T11:21:41.148626+00:00","updated_at":"2026-07-05T11:21:41.148626+00:00"}