{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XN6OBJCYJT7RETA4KLMS5HSPGG","short_pith_number":"pith:XN6OBJCY","schema_version":"1.0","canonical_sha256":"bb7ce0a4584cff124c1c52d92e9e4f31b0bbdbde32c3d045467c47a3e417648f","source":{"kind":"arxiv","id":"2410.14974","version":2},"attestation_state":"computed","paper":{"title":"CAGE: Causal Attention Enables Data-Efficient Generalizable Robotic Manipulation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Cewu Lu, Hao-Shu Fang, Hongjie Fang, Shangning Xia","submitted_at":"2024-10-19T04:37:01Z","abstract_excerpt":"Generalization in robotic manipulation remains a critical challenge, particularly when scaling to new environments with limited demonstrations. This paper introduces CAGE, a novel robotic manipulation policy designed to overcome these generalization barriers by integrating a causal attention mechanism. CAGE utilizes the powerful feature extraction capabilities of the vision foundation model DINOv2, combined with LoRA fine-tuning for robust environment understanding. The policy further employs a causal Perceiver for effective token compression and a diffusion-based action prediction head with a"},"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":"2410.14974","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-19T04:37:01Z","cross_cats_sorted":[],"title_canon_sha256":"abe07aafb4238d2f5500e743a556f8f8a135ab7bbb0147efe747b73680647421","abstract_canon_sha256":"d37e1316f2cd711c92e6a37715d022c6e84263ffe21d64c5fb156e24f65b36d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:15.574210Z","signature_b64":"eM0hS4yewsE1ldBhqGugHuQSbRtfLPeESlz1ItK3EJ1NdcygQCBSPdmYK12Wq2GH9II2HItzMVxOC3DjdtmuAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb7ce0a4584cff124c1c52d92e9e4f31b0bbdbde32c3d045467c47a3e417648f","last_reissued_at":"2026-07-05T09:45:15.573744Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:15.573744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CAGE: Causal Attention Enables Data-Efficient Generalizable Robotic Manipulation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Cewu Lu, Hao-Shu Fang, Hongjie Fang, Shangning Xia","submitted_at":"2024-10-19T04:37:01Z","abstract_excerpt":"Generalization in robotic manipulation remains a critical challenge, particularly when scaling to new environments with limited demonstrations. This paper introduces CAGE, a novel robotic manipulation policy designed to overcome these generalization barriers by integrating a causal attention mechanism. CAGE utilizes the powerful feature extraction capabilities of the vision foundation model DINOv2, combined with LoRA fine-tuning for robust environment understanding. The policy further employs a causal Perceiver for effective token compression and a diffusion-based action prediction head with a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.14974","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/2410.14974/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":"2410.14974","created_at":"2026-07-05T09:45:15.573798+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.14974v2","created_at":"2026-07-05T09:45:15.573798+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.14974","created_at":"2026-07-05T09:45:15.573798+00:00"},{"alias_kind":"pith_short_12","alias_value":"XN6OBJCYJT7R","created_at":"2026-07-05T09:45:15.573798+00:00"},{"alias_kind":"pith_short_16","alias_value":"XN6OBJCYJT7RETA4","created_at":"2026-07-05T09:45:15.573798+00:00"},{"alias_kind":"pith_short_8","alias_value":"XN6OBJCY","created_at":"2026-07-05T09:45:15.573798+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.13428","citing_title":"SID: Sliding into Distribution for Robust Few-Demonstration Manipulation","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XN6OBJCYJT7RETA4KLMS5HSPGG","json":"https://pith.science/pith/XN6OBJCYJT7RETA4KLMS5HSPGG.json","graph_json":"https://pith.science/api/pith-number/XN6OBJCYJT7RETA4KLMS5HSPGG/graph.json","events_json":"https://pith.science/api/pith-number/XN6OBJCYJT7RETA4KLMS5HSPGG/events.json","paper":"https://pith.science/paper/XN6OBJCY"},"agent_actions":{"view_html":"https://pith.science/pith/XN6OBJCYJT7RETA4KLMS5HSPGG","download_json":"https://pith.science/pith/XN6OBJCYJT7RETA4KLMS5HSPGG.json","view_paper":"https://pith.science/paper/XN6OBJCY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.14974&json=true","fetch_graph":"https://pith.science/api/pith-number/XN6OBJCYJT7RETA4KLMS5HSPGG/graph.json","fetch_events":"https://pith.science/api/pith-number/XN6OBJCYJT7RETA4KLMS5HSPGG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XN6OBJCYJT7RETA4KLMS5HSPGG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XN6OBJCYJT7RETA4KLMS5HSPGG/action/storage_attestation","attest_author":"https://pith.science/pith/XN6OBJCYJT7RETA4KLMS5HSPGG/action/author_attestation","sign_citation":"https://pith.science/pith/XN6OBJCYJT7RETA4KLMS5HSPGG/action/citation_signature","submit_replication":"https://pith.science/pith/XN6OBJCYJT7RETA4KLMS5HSPGG/action/replication_record"}},"created_at":"2026-07-05T09:45:15.573798+00:00","updated_at":"2026-07-05T09:45:15.573798+00:00"}