{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:SD5PMN2AV256OUMZKWHEKWPTGP","short_pith_number":"pith:SD5PMN2A","schema_version":"1.0","canonical_sha256":"90faf63740aebbe75199558e4559f333e565b57f817cadf11fd7862e689250bf","source":{"kind":"arxiv","id":"2210.01911","version":3},"attestation_state":"computed","paper":{"title":"Grounding Language with Visual Affordances over Unstructured Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Jessica Borja-Diaz, Oier Mees, Wolfram Burgard","submitted_at":"2022-10-04T21:16:48Z","abstract_excerpt":"Recent works have shown that Large Language Models (LLMs) can be applied to ground natural language to a wide variety of robot skills. However, in practice, learning multi-task, language-conditioned robotic skills typically requires large-scale data collection and frequent human intervention to reset the environment or help correcting the current policies. In this work, we propose a novel approach to efficiently learn general-purpose language-conditioned robot skills from unstructured, offline and reset-free data in the real world by exploiting a self-supervised visuo-lingual affordance model,"},"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":"2210.01911","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-10-04T21:16:48Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","cs.LG"],"title_canon_sha256":"1ca6c1c8bf22bb4a6093a8615a415cf4cf7d85025ea90047d29982bf0fc24bcd","abstract_canon_sha256":"022798acccd01d022c674b9cc0e5ab6b0431913c9fc05eeba69731c6324edd75"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:49:14.804889Z","signature_b64":"SLbk+iXfQ9updOltEJ9C743l+GnnSOQtQ/PCKRG5mRxleHeApJM0NDNSO4J4PLBNbbgE6rnAs/7irI+YhjWBAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90faf63740aebbe75199558e4559f333e565b57f817cadf11fd7862e689250bf","last_reissued_at":"2026-07-05T05:49:14.804537Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:49:14.804537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Grounding Language with Visual Affordances over Unstructured Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Jessica Borja-Diaz, Oier Mees, Wolfram Burgard","submitted_at":"2022-10-04T21:16:48Z","abstract_excerpt":"Recent works have shown that Large Language Models (LLMs) can be applied to ground natural language to a wide variety of robot skills. However, in practice, learning multi-task, language-conditioned robotic skills typically requires large-scale data collection and frequent human intervention to reset the environment or help correcting the current policies. In this work, we propose a novel approach to efficiently learn general-purpose language-conditioned robot skills from unstructured, offline and reset-free data in the real world by exploiting a self-supervised visuo-lingual affordance model,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.01911","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/2210.01911/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":"2210.01911","created_at":"2026-07-05T05:49:14.804594+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.01911v3","created_at":"2026-07-05T05:49:14.804594+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.01911","created_at":"2026-07-05T05:49:14.804594+00:00"},{"alias_kind":"pith_short_12","alias_value":"SD5PMN2AV256","created_at":"2026-07-05T05:49:14.804594+00:00"},{"alias_kind":"pith_short_16","alias_value":"SD5PMN2AV256OUMZ","created_at":"2026-07-05T05:49:14.804594+00:00"},{"alias_kind":"pith_short_8","alias_value":"SD5PMN2A","created_at":"2026-07-05T05:49:14.804594+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.13403","citing_title":"RotVLA: Rotational Latent Action for Vision-Language-Action Model","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2312.13139","citing_title":"Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation","ref_index":92,"is_internal_anchor":false},{"citing_arxiv_id":"2307.05973","citing_title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24622","citing_title":"CF-VLA: Efficient Coarse-to-Fine Action Generation for Vision-Language-Action Policies","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SD5PMN2AV256OUMZKWHEKWPTGP","json":"https://pith.science/pith/SD5PMN2AV256OUMZKWHEKWPTGP.json","graph_json":"https://pith.science/api/pith-number/SD5PMN2AV256OUMZKWHEKWPTGP/graph.json","events_json":"https://pith.science/api/pith-number/SD5PMN2AV256OUMZKWHEKWPTGP/events.json","paper":"https://pith.science/paper/SD5PMN2A"},"agent_actions":{"view_html":"https://pith.science/pith/SD5PMN2AV256OUMZKWHEKWPTGP","download_json":"https://pith.science/pith/SD5PMN2AV256OUMZKWHEKWPTGP.json","view_paper":"https://pith.science/paper/SD5PMN2A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.01911&json=true","fetch_graph":"https://pith.science/api/pith-number/SD5PMN2AV256OUMZKWHEKWPTGP/graph.json","fetch_events":"https://pith.science/api/pith-number/SD5PMN2AV256OUMZKWHEKWPTGP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SD5PMN2AV256OUMZKWHEKWPTGP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SD5PMN2AV256OUMZKWHEKWPTGP/action/storage_attestation","attest_author":"https://pith.science/pith/SD5PMN2AV256OUMZKWHEKWPTGP/action/author_attestation","sign_citation":"https://pith.science/pith/SD5PMN2AV256OUMZKWHEKWPTGP/action/citation_signature","submit_replication":"https://pith.science/pith/SD5PMN2AV256OUMZKWHEKWPTGP/action/replication_record"}},"created_at":"2026-07-05T05:49:14.804594+00:00","updated_at":"2026-07-05T05:49:14.804594+00:00"}