{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OJHYRWXLFEBEWU7C7BAAL727BM","short_pith_number":"pith:OJHYRWXL","canonical_record":{"source":{"id":"2410.07169","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-10-09T17:59:06Z","cross_cats_sorted":[],"title_canon_sha256":"0e60240cb8b9b8f63daee35449ba47b4a49395794156db7ebb43ac1fbe0e21b9","abstract_canon_sha256":"e9fe8b8e356f8db36a798c60f3ae04b6573f75cb36bf5ccd37562b03c33afa49"},"schema_version":"1.0"},"canonical_sha256":"724f88daeb29024b53e2f84005ff5f0b1c6ee0fd7d4308153881dcece100fa32","source":{"kind":"arxiv","id":"2410.07169","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.07169","created_at":"2026-07-05T10:12:49Z"},{"alias_kind":"arxiv_version","alias_value":"2410.07169v2","created_at":"2026-07-05T10:12:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07169","created_at":"2026-07-05T10:12:49Z"},{"alias_kind":"pith_short_12","alias_value":"OJHYRWXLFEBE","created_at":"2026-07-05T10:12:49Z"},{"alias_kind":"pith_short_16","alias_value":"OJHYRWXLFEBEWU7C","created_at":"2026-07-05T10:12:49Z"},{"alias_kind":"pith_short_8","alias_value":"OJHYRWXL","created_at":"2026-07-05T10:12:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OJHYRWXLFEBEWU7C7BAAL727BM","target":"record","payload":{"canonical_record":{"source":{"id":"2410.07169","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-10-09T17:59:06Z","cross_cats_sorted":[],"title_canon_sha256":"0e60240cb8b9b8f63daee35449ba47b4a49395794156db7ebb43ac1fbe0e21b9","abstract_canon_sha256":"e9fe8b8e356f8db36a798c60f3ae04b6573f75cb36bf5ccd37562b03c33afa49"},"schema_version":"1.0"},"canonical_sha256":"724f88daeb29024b53e2f84005ff5f0b1c6ee0fd7d4308153881dcece100fa32","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:49.412687Z","signature_b64":"PHPxl/YuLFoDVsEzw3HY2qP9qQVhK+W17SHpEsPCr3sUcXiIPWaRwBl3eQggemSdG2meei/CrGfH295aOuC7CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"724f88daeb29024b53e2f84005ff5f0b1c6ee0fd7d4308153881dcece100fa32","last_reissued_at":"2026-07-05T10:12:49.412078Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:49.412078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.07169","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:12:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SUsYZ7S/gYv+8z2QLpOO+NPZBvOZmnwxNoer1S+2wVh/uk7wrITP+Nt8dmQBW6de5G6S0wkkfNzUclRdXqG5DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T01:21:22.157672Z"},"content_sha256":"e5fb12194bd89af93e6b2a2e196d00f9df273098de8526d007bc2f34107bec92","schema_version":"1.0","event_id":"sha256:e5fb12194bd89af93e6b2a2e196d00f9df273098de8526d007bc2f34107bec92"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OJHYRWXLFEBEWU7C7BAAL727BM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VIP: Vision Instructed Pre-training for Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Hengshuang Zhao, Jinrong Yang, Liangliang Ren, Xiang Bai, Xiaoyang Wu, Yong Zhao, Zhenhua Xu, Zhuoling Li","submitted_at":"2024-10-09T17:59:06Z","abstract_excerpt":"The effectiveness of scaling up training data in robotic manipulation is still limited. A primary challenge in manipulation is the tasks are diverse, and the trained policy would be confused if the task targets are not specified clearly. Existing works primarily rely on text instruction to describe targets. However, we reveal that current robotic data cannot train policies to understand text instruction effectively, and vision is much more comprehensible. Therefore, we introduce utilizing vision instruction to specify targets. A straightforward implementation is training a policy to predict th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07169","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/2410.07169/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":"2026-07-05T10:12:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"efm81goY7VtYQbRVgm6WJnOI6JL3wY/jcZl9VtVa+b9aCa+oCycxZpcw4CGhzTtlM515E67EsYFlDA0Ewlm+BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T01:21:22.157954Z"},"content_sha256":"a82faa3f5fee808d27fbcc32f35ee3ec8640c0ee904323fec926cc094c7fe5da","schema_version":"1.0","event_id":"sha256:a82faa3f5fee808d27fbcc32f35ee3ec8640c0ee904323fec926cc094c7fe5da"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OJHYRWXLFEBEWU7C7BAAL727BM/bundle.json","state_url":"https://pith.science/pith/OJHYRWXLFEBEWU7C7BAAL727BM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OJHYRWXLFEBEWU7C7BAAL727BM/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":"2026-08-01T01:21:22Z","links":{"resolver":"https://pith.science/pith/OJHYRWXLFEBEWU7C7BAAL727BM","bundle":"https://pith.science/pith/OJHYRWXLFEBEWU7C7BAAL727BM/bundle.json","state":"https://pith.science/pith/OJHYRWXLFEBEWU7C7BAAL727BM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OJHYRWXLFEBEWU7C7BAAL727BM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OJHYRWXLFEBEWU7C7BAAL727BM","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":"e9fe8b8e356f8db36a798c60f3ae04b6573f75cb36bf5ccd37562b03c33afa49","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-10-09T17:59:06Z","title_canon_sha256":"0e60240cb8b9b8f63daee35449ba47b4a49395794156db7ebb43ac1fbe0e21b9"},"schema_version":"1.0","source":{"id":"2410.07169","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.07169","created_at":"2026-07-05T10:12:49Z"},{"alias_kind":"arxiv_version","alias_value":"2410.07169v2","created_at":"2026-07-05T10:12:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07169","created_at":"2026-07-05T10:12:49Z"},{"alias_kind":"pith_short_12","alias_value":"OJHYRWXLFEBE","created_at":"2026-07-05T10:12:49Z"},{"alias_kind":"pith_short_16","alias_value":"OJHYRWXLFEBEWU7C","created_at":"2026-07-05T10:12:49Z"},{"alias_kind":"pith_short_8","alias_value":"OJHYRWXL","created_at":"2026-07-05T10:12:49Z"}],"graph_snapshots":[{"event_id":"sha256:a82faa3f5fee808d27fbcc32f35ee3ec8640c0ee904323fec926cc094c7fe5da","target":"graph","created_at":"2026-07-05T10:12:49Z","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/2410.07169/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The effectiveness of scaling up training data in robotic manipulation is still limited. A primary challenge in manipulation is the tasks are diverse, and the trained policy would be confused if the task targets are not specified clearly. Existing works primarily rely on text instruction to describe targets. However, we reveal that current robotic data cannot train policies to understand text instruction effectively, and vision is much more comprehensible. Therefore, we introduce utilizing vision instruction to specify targets. A straightforward implementation is training a policy to predict th","authors_text":"Hengshuang Zhao, Jinrong Yang, Liangliang Ren, Xiang Bai, Xiaoyang Wu, Yong Zhao, Zhenhua Xu, Zhuoling Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-10-09T17:59:06Z","title":"VIP: Vision Instructed Pre-training for Robotic Manipulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07169","kind":"arxiv","version":2},"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:e5fb12194bd89af93e6b2a2e196d00f9df273098de8526d007bc2f34107bec92","target":"record","created_at":"2026-07-05T10:12:49Z","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":"e9fe8b8e356f8db36a798c60f3ae04b6573f75cb36bf5ccd37562b03c33afa49","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-10-09T17:59:06Z","title_canon_sha256":"0e60240cb8b9b8f63daee35449ba47b4a49395794156db7ebb43ac1fbe0e21b9"},"schema_version":"1.0","source":{"id":"2410.07169","kind":"arxiv","version":2}},"canonical_sha256":"724f88daeb29024b53e2f84005ff5f0b1c6ee0fd7d4308153881dcece100fa32","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"724f88daeb29024b53e2f84005ff5f0b1c6ee0fd7d4308153881dcece100fa32","first_computed_at":"2026-07-05T10:12:49.412078Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:12:49.412078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PHPxl/YuLFoDVsEzw3HY2qP9qQVhK+W17SHpEsPCr3sUcXiIPWaRwBl3eQggemSdG2meei/CrGfH295aOuC7CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:12:49.412687Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.07169","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e5fb12194bd89af93e6b2a2e196d00f9df273098de8526d007bc2f34107bec92","sha256:a82faa3f5fee808d27fbcc32f35ee3ec8640c0ee904323fec926cc094c7fe5da"],"state_sha256":"38b8280b3163f7c9a335befed8632b03e4aa89f415e691f60ec52b9a402dd8e1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3fMXumJnU7mfD8R+nkn3yUDxmk+v8HihqhbQAyr+6gd6Vdbc/obmFfdfeXdkhwa1HRxMRo3TwH0ZVpNnsQ08Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T01:21:22.161192Z","bundle_sha256":"710c6c3c3eb3b8bd1c953df9637ee3fa4bdb6f9972f0f72ec2cbdedc1fc0aa6a"}}