{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:INU5PWV3TX4Y3STQXD5SJ7SNOW","short_pith_number":"pith:INU5PWV3","schema_version":"1.0","canonical_sha256":"4369d7dabb9df98dca70b8fb24fe4d75b4e05a27916791edc88bb5da95a20e6a","source":{"kind":"arxiv","id":"2405.19586","version":1},"attestation_state":"computed","paper":{"title":"SAM-E: Leveraging Visual Foundation Model with Sequence Imitation for Embodied Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Bin Zhao, Chenjia Bai, Haoran He, Junjie Zhang, Wenke Xia, Xiu Li, Xuelong Li, Zhigang Wang","submitted_at":"2024-05-30T00:32:51Z","abstract_excerpt":"Acquiring a multi-task imitation policy in 3D manipulation poses challenges in terms of scene understanding and action prediction. Current methods employ both 3D representation and multi-view 2D representation to predict the poses of the robot's end-effector. However, they still require a considerable amount of high-quality robot trajectories, and suffer from limited generalization in unseen tasks and inefficient execution in long-horizon reasoning. In this paper, we propose SAM-E, a novel architecture for robot manipulation by leveraging a vision-foundation model for generalizable scene under"},"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":"2405.19586","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-30T00:32:51Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"c80aaf7fcaa94b36e5bb01b88d8dcb16bc95ed61a3f739c0ffe654f5c24d6bd7","abstract_canon_sha256":"86c533351b589bf667d88923391213fb73a7f6cd198afbf7bc209d3cb93fddc8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:09.581185Z","signature_b64":"fkv9q2F88S3ob6GwJuEbwunYjQG/Eac4qp6HnZIZOyhVRQ4zE7TmfikpG+cLsjQKv7P2SKgO2ZdiigV7SAjBDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4369d7dabb9df98dca70b8fb24fe4d75b4e05a27916791edc88bb5da95a20e6a","last_reissued_at":"2026-07-05T08:25:09.580791Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:09.580791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAM-E: Leveraging Visual Foundation Model with Sequence Imitation for Embodied Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Bin Zhao, Chenjia Bai, Haoran He, Junjie Zhang, Wenke Xia, Xiu Li, Xuelong Li, Zhigang Wang","submitted_at":"2024-05-30T00:32:51Z","abstract_excerpt":"Acquiring a multi-task imitation policy in 3D manipulation poses challenges in terms of scene understanding and action prediction. Current methods employ both 3D representation and multi-view 2D representation to predict the poses of the robot's end-effector. However, they still require a considerable amount of high-quality robot trajectories, and suffer from limited generalization in unseen tasks and inefficient execution in long-horizon reasoning. In this paper, we propose SAM-E, a novel architecture for robot manipulation by leveraging a vision-foundation model for generalizable scene under"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19586","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/2405.19586/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":"2405.19586","created_at":"2026-07-05T08:25:09.580851+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.19586v1","created_at":"2026-07-05T08:25:09.580851+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19586","created_at":"2026-07-05T08:25:09.580851+00:00"},{"alias_kind":"pith_short_12","alias_value":"INU5PWV3TX4Y","created_at":"2026-07-05T08:25:09.580851+00:00"},{"alias_kind":"pith_short_16","alias_value":"INU5PWV3TX4Y3STQ","created_at":"2026-07-05T08:25:09.580851+00:00"},{"alias_kind":"pith_short_8","alias_value":"INU5PWV3","created_at":"2026-07-05T08:25:09.580851+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.02813","citing_title":"LangScene-X: Reconstruct Generalizable 3D Language-Embedded Scenes with TriMap Video Diffusion","ref_index":53,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/INU5PWV3TX4Y3STQXD5SJ7SNOW","json":"https://pith.science/pith/INU5PWV3TX4Y3STQXD5SJ7SNOW.json","graph_json":"https://pith.science/api/pith-number/INU5PWV3TX4Y3STQXD5SJ7SNOW/graph.json","events_json":"https://pith.science/api/pith-number/INU5PWV3TX4Y3STQXD5SJ7SNOW/events.json","paper":"https://pith.science/paper/INU5PWV3"},"agent_actions":{"view_html":"https://pith.science/pith/INU5PWV3TX4Y3STQXD5SJ7SNOW","download_json":"https://pith.science/pith/INU5PWV3TX4Y3STQXD5SJ7SNOW.json","view_paper":"https://pith.science/paper/INU5PWV3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.19586&json=true","fetch_graph":"https://pith.science/api/pith-number/INU5PWV3TX4Y3STQXD5SJ7SNOW/graph.json","fetch_events":"https://pith.science/api/pith-number/INU5PWV3TX4Y3STQXD5SJ7SNOW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/INU5PWV3TX4Y3STQXD5SJ7SNOW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/INU5PWV3TX4Y3STQXD5SJ7SNOW/action/storage_attestation","attest_author":"https://pith.science/pith/INU5PWV3TX4Y3STQXD5SJ7SNOW/action/author_attestation","sign_citation":"https://pith.science/pith/INU5PWV3TX4Y3STQXD5SJ7SNOW/action/citation_signature","submit_replication":"https://pith.science/pith/INU5PWV3TX4Y3STQXD5SJ7SNOW/action/replication_record"}},"created_at":"2026-07-05T08:25:09.580851+00:00","updated_at":"2026-07-05T08:25:09.580851+00:00"}