{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:INU5PWV3TX4Y3STQXD5SJ7SNOW","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"86c533351b589bf667d88923391213fb73a7f6cd198afbf7bc209d3cb93fddc8","cross_cats_sorted":["cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-30T00:32:51Z","title_canon_sha256":"c80aaf7fcaa94b36e5bb01b88d8dcb16bc95ed61a3f739c0ffe654f5c24d6bd7"},"schema_version":"1.0","source":{"id":"2405.19586","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.19586","created_at":"2026-07-05T08:25:09Z"},{"alias_kind":"arxiv_version","alias_value":"2405.19586v1","created_at":"2026-07-05T08:25:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19586","created_at":"2026-07-05T08:25:09Z"},{"alias_kind":"pith_short_12","alias_value":"INU5PWV3TX4Y","created_at":"2026-07-05T08:25:09Z"},{"alias_kind":"pith_short_16","alias_value":"INU5PWV3TX4Y3STQ","created_at":"2026-07-05T08:25:09Z"},{"alias_kind":"pith_short_8","alias_value":"INU5PWV3","created_at":"2026-07-05T08:25:09Z"}],"graph_snapshots":[{"event_id":"sha256:8d7f4e10203e650428b45ffba56817c03d2f2996ba7d6449fae092f47437ec78","target":"graph","created_at":"2026-07-05T08:25:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2405.19586/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bin Zhao, Chenjia Bai, Haoran He, Junjie Zhang, Wenke Xia, Xiu Li, Xuelong Li, Zhigang Wang","cross_cats":["cs.LG","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-30T00:32:51Z","title":"SAM-E: Leveraging Visual Foundation Model with Sequence Imitation for Embodied Manipulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19586","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7c7a6d72f317d1bc5bfae5ee661bce47f23825f782c18925f63072bf46ab7d21","target":"record","created_at":"2026-07-05T08:25:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"86c533351b589bf667d88923391213fb73a7f6cd198afbf7bc209d3cb93fddc8","cross_cats_sorted":["cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-30T00:32:51Z","title_canon_sha256":"c80aaf7fcaa94b36e5bb01b88d8dcb16bc95ed61a3f739c0ffe654f5c24d6bd7"},"schema_version":"1.0","source":{"id":"2405.19586","kind":"arxiv","version":1}},"canonical_sha256":"4369d7dabb9df98dca70b8fb24fe4d75b4e05a27916791edc88bb5da95a20e6a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4369d7dabb9df98dca70b8fb24fe4d75b4e05a27916791edc88bb5da95a20e6a","first_computed_at":"2026-07-05T08:25:09.580791Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:25:09.580791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fkv9q2F88S3ob6GwJuEbwunYjQG/Eac4qp6HnZIZOyhVRQ4zE7TmfikpG+cLsjQKv7P2SKgO2ZdiigV7SAjBDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:25:09.581185Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.19586","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7c7a6d72f317d1bc5bfae5ee661bce47f23825f782c18925f63072bf46ab7d21","sha256:8d7f4e10203e650428b45ffba56817c03d2f2996ba7d6449fae092f47437ec78"],"state_sha256":"ec42b42a29c6b56dcdf5bca5955f644e464f51bd6954c15a237c2ced05af7a07"}