{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SYOV6MK3KDO3XGPGLDWTVAYO4R","short_pith_number":"pith:SYOV6MK3","canonical_record":{"source":{"id":"2402.13181","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-02-20T17:48:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4b4111b5b95f2761fc2d50ab0ca9874bd02aee865f7751814221d0f1da7d5572","abstract_canon_sha256":"e4748305c933f4c5b3360737d26d62d9734a08559e786e51b7457fb955a510c2"},"schema_version":"1.0"},"canonical_sha256":"961d5f315b50ddbb99e658ed3a830ee47962844d27e31a4007216d595dab9f70","source":{"kind":"arxiv","id":"2402.13181","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.13181","created_at":"2026-07-05T07:47:21Z"},{"alias_kind":"arxiv_version","alias_value":"2402.13181v1","created_at":"2026-07-05T07:47:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13181","created_at":"2026-07-05T07:47:21Z"},{"alias_kind":"pith_short_12","alias_value":"SYOV6MK3KDO3","created_at":"2026-07-05T07:47:21Z"},{"alias_kind":"pith_short_16","alias_value":"SYOV6MK3KDO3XGPG","created_at":"2026-07-05T07:47:21Z"},{"alias_kind":"pith_short_8","alias_value":"SYOV6MK3","created_at":"2026-07-05T07:47:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SYOV6MK3KDO3XGPGLDWTVAYO4R","target":"record","payload":{"canonical_record":{"source":{"id":"2402.13181","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-02-20T17:48:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4b4111b5b95f2761fc2d50ab0ca9874bd02aee865f7751814221d0f1da7d5572","abstract_canon_sha256":"e4748305c933f4c5b3360737d26d62d9734a08559e786e51b7457fb955a510c2"},"schema_version":"1.0"},"canonical_sha256":"961d5f315b50ddbb99e658ed3a830ee47962844d27e31a4007216d595dab9f70","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:47:21.842388Z","signature_b64":"SE8X8aKqDXuEMJCd2WPHp80ROGYHtuBqfCiMm3wejY4QHv2HXphHHMtlD+Hccfw7WTWi/6fOdgBhNdP6+lwOAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"961d5f315b50ddbb99e658ed3a830ee47962844d27e31a4007216d595dab9f70","last_reissued_at":"2026-07-05T07:47:21.841939Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:47:21.841939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.13181","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":"2026-07-05T07:47:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OLIB/Ue1y7cOZtWfzYUeqMSuNoQ9Q8g2LzVDKymqv6v473xKMScyv/jYsI0h5vC4JrNNcKtMmnc1z1uzouzsCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T17:02:49.737456Z"},"content_sha256":"de91052d6849354c039207f23c4326f910d8df4386a4801f5e998f477b651486","schema_version":"1.0","event_id":"sha256:de91052d6849354c039207f23c4326f910d8df4386a4801f5e998f477b651486"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SYOV6MK3KDO3XGPGLDWTVAYO4R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DINOBot: Robot Manipulation via Retrieval and Alignment with Vision Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Edward Johns, Norman Di Palo","submitted_at":"2024-02-20T17:48:11Z","abstract_excerpt":"We propose DINOBot, a novel imitation learning framework for robot manipulation, which leverages the image-level and pixel-level capabilities of features extracted from Vision Transformers trained with DINO. When interacting with a novel object, DINOBot first uses these features to retrieve the most visually similar object experienced during human demonstrations, and then uses this object to align its end-effector with the novel object to enable effective interaction. Through a series of real-world experiments on everyday tasks, we show that exploiting both the image-level and pixel-level prop"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13181","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/2402.13181/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":"2026-07-05T07:47:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ykE8V0mzA6VvBnnN4WXp7ifAyz6wQpY3s7QgJdqZcykBYEhZMX/7ogP2fcB5k3OYGyh3Uf+8N4SOelxISqUOBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T17:02:49.738374Z"},"content_sha256":"373ae0e0d54fc279bab3ef412a6ec739184f70c892b88f03c5e2a6c31af3e4e5","schema_version":"1.0","event_id":"sha256:373ae0e0d54fc279bab3ef412a6ec739184f70c892b88f03c5e2a6c31af3e4e5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SYOV6MK3KDO3XGPGLDWTVAYO4R/bundle.json","state_url":"https://pith.science/pith/SYOV6MK3KDO3XGPGLDWTVAYO4R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SYOV6MK3KDO3XGPGLDWTVAYO4R/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":"2026-08-09T17:02:49Z","links":{"resolver":"https://pith.science/pith/SYOV6MK3KDO3XGPGLDWTVAYO4R","bundle":"https://pith.science/pith/SYOV6MK3KDO3XGPGLDWTVAYO4R/bundle.json","state":"https://pith.science/pith/SYOV6MK3KDO3XGPGLDWTVAYO4R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SYOV6MK3KDO3XGPGLDWTVAYO4R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SYOV6MK3KDO3XGPGLDWTVAYO4R","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":"e4748305c933f4c5b3360737d26d62d9734a08559e786e51b7457fb955a510c2","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-02-20T17:48:11Z","title_canon_sha256":"4b4111b5b95f2761fc2d50ab0ca9874bd02aee865f7751814221d0f1da7d5572"},"schema_version":"1.0","source":{"id":"2402.13181","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.13181","created_at":"2026-07-05T07:47:21Z"},{"alias_kind":"arxiv_version","alias_value":"2402.13181v1","created_at":"2026-07-05T07:47:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13181","created_at":"2026-07-05T07:47:21Z"},{"alias_kind":"pith_short_12","alias_value":"SYOV6MK3KDO3","created_at":"2026-07-05T07:47:21Z"},{"alias_kind":"pith_short_16","alias_value":"SYOV6MK3KDO3XGPG","created_at":"2026-07-05T07:47:21Z"},{"alias_kind":"pith_short_8","alias_value":"SYOV6MK3","created_at":"2026-07-05T07:47:21Z"}],"graph_snapshots":[{"event_id":"sha256:373ae0e0d54fc279bab3ef412a6ec739184f70c892b88f03c5e2a6c31af3e4e5","target":"graph","created_at":"2026-07-05T07:47:21Z","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/2402.13181/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose DINOBot, a novel imitation learning framework for robot manipulation, which leverages the image-level and pixel-level capabilities of features extracted from Vision Transformers trained with DINO. When interacting with a novel object, DINOBot first uses these features to retrieve the most visually similar object experienced during human demonstrations, and then uses this object to align its end-effector with the novel object to enable effective interaction. Through a series of real-world experiments on everyday tasks, we show that exploiting both the image-level and pixel-level prop","authors_text":"Edward Johns, Norman Di Palo","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-02-20T17:48:11Z","title":"DINOBot: Robot Manipulation via Retrieval and Alignment with Vision Foundation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13181","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:de91052d6849354c039207f23c4326f910d8df4386a4801f5e998f477b651486","target":"record","created_at":"2026-07-05T07:47:21Z","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":"e4748305c933f4c5b3360737d26d62d9734a08559e786e51b7457fb955a510c2","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-02-20T17:48:11Z","title_canon_sha256":"4b4111b5b95f2761fc2d50ab0ca9874bd02aee865f7751814221d0f1da7d5572"},"schema_version":"1.0","source":{"id":"2402.13181","kind":"arxiv","version":1}},"canonical_sha256":"961d5f315b50ddbb99e658ed3a830ee47962844d27e31a4007216d595dab9f70","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"961d5f315b50ddbb99e658ed3a830ee47962844d27e31a4007216d595dab9f70","first_computed_at":"2026-07-05T07:47:21.841939Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:47:21.841939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SE8X8aKqDXuEMJCd2WPHp80ROGYHtuBqfCiMm3wejY4QHv2HXphHHMtlD+Hccfw7WTWi/6fOdgBhNdP6+lwOAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:47:21.842388Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.13181","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de91052d6849354c039207f23c4326f910d8df4386a4801f5e998f477b651486","sha256:373ae0e0d54fc279bab3ef412a6ec739184f70c892b88f03c5e2a6c31af3e4e5"],"state_sha256":"cac9727fa1da1efdf0270f5722ec225a3797d2046598d007db66bd4d13608ed9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aokQkfgknu3qybTJEtRSm8bF6ai0xNBBA2UTo12ZXi67egH99Jx03dyNKXW9h9jqKst7FLnKAtSoz1IAU5R8Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T17:02:49.743738Z","bundle_sha256":"73eba9e313d53c4fbbc6268b7fbad2f1a4b379fb35087e1290b912b666708af1"}}