{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:347QROCAX6CIVKSY4FN77OMT6F","short_pith_number":"pith:347QROCA","schema_version":"1.0","canonical_sha256":"df3f08b840bf848aaa58e15bffb993f14e87ab817f7edb943e840d3a39e7b677","source":{"kind":"arxiv","id":"2406.09738","version":1},"attestation_state":"computed","paper":{"title":"Contrastive Imitation Learning for Language-guided Multi-Task Robotic Manipulation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Jiaming Zhou, Junwei Liang, Ronghe Qiu, Teli Ma, Zifan Wang","submitted_at":"2024-06-14T05:53:00Z","abstract_excerpt":"Developing robots capable of executing various manipulation tasks, guided by natural language instructions and visual observations of intricate real-world environments, remains a significant challenge in robotics. Such robot agents need to understand linguistic commands and distinguish between the requirements of different tasks. In this work, we present Sigma-Agent, an end-to-end imitation learning agent for multi-task robotic manipulation. Sigma-Agent incorporates contrastive Imitation Learning (contrastive IL) modules to strengthen vision-language and current-future representations. An effe"},"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":"2406.09738","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2024-06-14T05:53:00Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e0358f7fdc642400f0f727ecd656c6856ae43b488ca5ef229861f6cdd3b1fb28","abstract_canon_sha256":"4aadd469603f1c8084dc791a0a4704f6132ed15d8a94fd40b126dc4e0d77ea7a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:59.114240Z","signature_b64":"ciKJE55XqVpckjiQOPwjs6o+vNlLBo4ii+S9WMwL3ah2RJ68JK7Zx6Ui+qx40gjd+4RF8nnPEAwlmaH1Nfq8Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df3f08b840bf848aaa58e15bffb993f14e87ab817f7edb943e840d3a39e7b677","last_reissued_at":"2026-07-05T08:31:59.113730Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:59.113730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contrastive Imitation Learning for Language-guided Multi-Task Robotic Manipulation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Jiaming Zhou, Junwei Liang, Ronghe Qiu, Teli Ma, Zifan Wang","submitted_at":"2024-06-14T05:53:00Z","abstract_excerpt":"Developing robots capable of executing various manipulation tasks, guided by natural language instructions and visual observations of intricate real-world environments, remains a significant challenge in robotics. Such robot agents need to understand linguistic commands and distinguish between the requirements of different tasks. In this work, we present Sigma-Agent, an end-to-end imitation learning agent for multi-task robotic manipulation. Sigma-Agent incorporates contrastive Imitation Learning (contrastive IL) modules to strengthen vision-language and current-future representations. An effe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09738","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/2406.09738/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":"2406.09738","created_at":"2026-07-05T08:31:59.113798+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.09738v1","created_at":"2026-07-05T08:31:59.113798+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09738","created_at":"2026-07-05T08:31:59.113798+00:00"},{"alias_kind":"pith_short_12","alias_value":"347QROCAX6CI","created_at":"2026-07-05T08:31:59.113798+00:00"},{"alias_kind":"pith_short_16","alias_value":"347QROCAX6CIVKSY","created_at":"2026-07-05T08:31:59.113798+00:00"},{"alias_kind":"pith_short_8","alias_value":"347QROCA","created_at":"2026-07-05T08:31:59.113798+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26801","citing_title":"Improving Vision-Language-Action Model Fine-Tuning with Structured Stage and Keyframe Supervision","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09215","citing_title":"MotionWAM: Towards Foundation World Action Models for Real-Time Humanoid Loco-Manipulation","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/347QROCAX6CIVKSY4FN77OMT6F","json":"https://pith.science/pith/347QROCAX6CIVKSY4FN77OMT6F.json","graph_json":"https://pith.science/api/pith-number/347QROCAX6CIVKSY4FN77OMT6F/graph.json","events_json":"https://pith.science/api/pith-number/347QROCAX6CIVKSY4FN77OMT6F/events.json","paper":"https://pith.science/paper/347QROCA"},"agent_actions":{"view_html":"https://pith.science/pith/347QROCAX6CIVKSY4FN77OMT6F","download_json":"https://pith.science/pith/347QROCAX6CIVKSY4FN77OMT6F.json","view_paper":"https://pith.science/paper/347QROCA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.09738&json=true","fetch_graph":"https://pith.science/api/pith-number/347QROCAX6CIVKSY4FN77OMT6F/graph.json","fetch_events":"https://pith.science/api/pith-number/347QROCAX6CIVKSY4FN77OMT6F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/347QROCAX6CIVKSY4FN77OMT6F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/347QROCAX6CIVKSY4FN77OMT6F/action/storage_attestation","attest_author":"https://pith.science/pith/347QROCAX6CIVKSY4FN77OMT6F/action/author_attestation","sign_citation":"https://pith.science/pith/347QROCAX6CIVKSY4FN77OMT6F/action/citation_signature","submit_replication":"https://pith.science/pith/347QROCAX6CIVKSY4FN77OMT6F/action/replication_record"}},"created_at":"2026-07-05T08:31:59.113798+00:00","updated_at":"2026-07-05T08:31:59.113798+00:00"}