{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:INU5PWV3TX4Y3STQXD5SJ7SNOW","short_pith_number":"pith:INU5PWV3","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"},"canonical_sha256":"4369d7dabb9df98dca70b8fb24fe4d75b4e05a27916791edc88bb5da95a20e6a","source":{"kind":"arxiv","id":"2405.19586","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:INU5PWV3TX4Y3STQXD5SJ7SNOW","target":"record","payload":{"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"},"canonical_sha256":"4369d7dabb9df98dca70b8fb24fe4d75b4e05a27916791edc88bb5da95a20e6a","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"},"source_kind":"arxiv","source_id":"2405.19586","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:25:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eiWmxfpFIg+k//ah+nUiAjOERMjZk6yxEh1Rq8N8Y+8JenG/hK7ycunsLalE506W+/iSGbl/wn3rsNTnd9XSCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T21:01:23.917867Z"},"content_sha256":"7c7a6d72f317d1bc5bfae5ee661bce47f23825f782c18925f63072bf46ab7d21","schema_version":"1.0","event_id":"sha256:7c7a6d72f317d1bc5bfae5ee661bce47f23825f782c18925f63072bf46ab7d21"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:INU5PWV3TX4Y3STQXD5SJ7SNOW","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:25:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QezNlaV0ZQmUGYcLOBjKCmSjFsMdfJmkX20orjx6TTf0tY2ZfgPCcvFe3kJ2Yyq9jkX9z3/zJrWZywF+UdCICw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T21:01:23.918363Z"},"content_sha256":"8d7f4e10203e650428b45ffba56817c03d2f2996ba7d6449fae092f47437ec78","schema_version":"1.0","event_id":"sha256:8d7f4e10203e650428b45ffba56817c03d2f2996ba7d6449fae092f47437ec78"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/INU5PWV3TX4Y3STQXD5SJ7SNOW/bundle.json","state_url":"https://pith.science/pith/INU5PWV3TX4Y3STQXD5SJ7SNOW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/INU5PWV3TX4Y3STQXD5SJ7SNOW/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T21:01:23Z","links":{"resolver":"https://pith.science/pith/INU5PWV3TX4Y3STQXD5SJ7SNOW","bundle":"https://pith.science/pith/INU5PWV3TX4Y3STQXD5SJ7SNOW/bundle.json","state":"https://pith.science/pith/INU5PWV3TX4Y3STQXD5SJ7SNOW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/INU5PWV3TX4Y3STQXD5SJ7SNOW/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BjESYcCzi57x2TThG06OSgAXKk9ai+Wjs1IZzdS0z6mbni4QisYb/+jilK6S/Oxh0WxaJQ0BLHzkf5LZ6pFoCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T21:01:23.922665Z","bundle_sha256":"50a623c1c2e4aaf3e10ac429f8581ce76226fd4c2ea8806caf2a128c537b608c"}}