{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:HPMFGVY4TBKYE6DAVDZ32GP6UR","short_pith_number":"pith:HPMFGVY4","schema_version":"1.0","canonical_sha256":"3bd853571c9855827860a8f3bd19fea460a60f48a7331fcb2940486be9f175de","source":{"kind":"arxiv","id":"2209.04899","version":3},"attestation_state":"computed","paper":{"title":"Instruction-driven history-aware policies for robotic manipulations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Cordelia Schmid, Ivan Laptev, Makarand Tapaswi, Pierre-Louis Guhur, Ricardo Garcia, Shizhe Chen","submitted_at":"2022-09-11T16:28:25Z","abstract_excerpt":"In human environments, robots are expected to accomplish a variety of manipulation tasks given simple natural language instructions. Yet, robotic manipulation is extremely challenging as it requires fine-grained motor control, long-term memory as well as generalization to previously unseen tasks and environments. To address these challenges, we propose a unified transformer-based approach that takes into account multiple inputs. In particular, our transformer architecture integrates (i) natural language instructions and (ii) multi-view scene observations while (iii) keeping track of the full h"},"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":"2209.04899","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-09-11T16:28:25Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","cs.LG"],"title_canon_sha256":"3ddf2b5ef8d7623450e790e0ac75cbe46e9efcd46949bbbb9aa0cd9506acfae9","abstract_canon_sha256":"1b1420a15708f28ef1df040367aa0cfdc8ebcea624a38b6f02a8ebb45c8ef209"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:26:08.793252Z","signature_b64":"IscZ0x7P+ZCP/VinrRJ0yPPEEsEwXCVR/67S7Cw3ByQQCd8Sb1FNl+lE4my1l2oHJSBI522UhqdrKU/zulmGCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3bd853571c9855827860a8f3bd19fea460a60f48a7331fcb2940486be9f175de","last_reissued_at":"2026-07-05T05:26:08.792750Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:26:08.792750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Instruction-driven history-aware policies for robotic manipulations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Cordelia Schmid, Ivan Laptev, Makarand Tapaswi, Pierre-Louis Guhur, Ricardo Garcia, Shizhe Chen","submitted_at":"2022-09-11T16:28:25Z","abstract_excerpt":"In human environments, robots are expected to accomplish a variety of manipulation tasks given simple natural language instructions. Yet, robotic manipulation is extremely challenging as it requires fine-grained motor control, long-term memory as well as generalization to previously unseen tasks and environments. To address these challenges, we propose a unified transformer-based approach that takes into account multiple inputs. In particular, our transformer architecture integrates (i) natural language instructions and (ii) multi-view scene observations while (iii) keeping track of the full h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.04899","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/2209.04899/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":"2209.04899","created_at":"2026-07-05T05:26:08.792809+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.04899v3","created_at":"2026-07-05T05:26:08.792809+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.04899","created_at":"2026-07-05T05:26:08.792809+00:00"},{"alias_kind":"pith_short_12","alias_value":"HPMFGVY4TBKY","created_at":"2026-07-05T05:26:08.792809+00:00"},{"alias_kind":"pith_short_16","alias_value":"HPMFGVY4TBKYE6DA","created_at":"2026-07-05T05:26:08.792809+00:00"},{"alias_kind":"pith_short_8","alias_value":"HPMFGVY4","created_at":"2026-07-05T05:26:08.792809+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2303.03378","citing_title":"PaLM-E: An Embodied Multimodal Language Model","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HPMFGVY4TBKYE6DAVDZ32GP6UR","json":"https://pith.science/pith/HPMFGVY4TBKYE6DAVDZ32GP6UR.json","graph_json":"https://pith.science/api/pith-number/HPMFGVY4TBKYE6DAVDZ32GP6UR/graph.json","events_json":"https://pith.science/api/pith-number/HPMFGVY4TBKYE6DAVDZ32GP6UR/events.json","paper":"https://pith.science/paper/HPMFGVY4"},"agent_actions":{"view_html":"https://pith.science/pith/HPMFGVY4TBKYE6DAVDZ32GP6UR","download_json":"https://pith.science/pith/HPMFGVY4TBKYE6DAVDZ32GP6UR.json","view_paper":"https://pith.science/paper/HPMFGVY4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.04899&json=true","fetch_graph":"https://pith.science/api/pith-number/HPMFGVY4TBKYE6DAVDZ32GP6UR/graph.json","fetch_events":"https://pith.science/api/pith-number/HPMFGVY4TBKYE6DAVDZ32GP6UR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HPMFGVY4TBKYE6DAVDZ32GP6UR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HPMFGVY4TBKYE6DAVDZ32GP6UR/action/storage_attestation","attest_author":"https://pith.science/pith/HPMFGVY4TBKYE6DAVDZ32GP6UR/action/author_attestation","sign_citation":"https://pith.science/pith/HPMFGVY4TBKYE6DAVDZ32GP6UR/action/citation_signature","submit_replication":"https://pith.science/pith/HPMFGVY4TBKYE6DAVDZ32GP6UR/action/replication_record"}},"created_at":"2026-07-05T05:26:08.792809+00:00","updated_at":"2026-07-05T05:26:08.792809+00:00"}