{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WBSHTHZRQQTBVBFLQB46G2HIFS","short_pith_number":"pith:WBSHTHZR","canonical_record":{"source":{"id":"2508.07626","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-11T05:09:58Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"318d4b98ba214675825afaa442ccaa94ec0738ebe77f0df7c8e802197d3feec7","abstract_canon_sha256":"fce667b7156369cfb515e4026d39aa5be7654da6ae32b919d3205211a21caef9"},"schema_version":"1.0"},"canonical_sha256":"b064799f3184261a84ab8079e368e82c8f5f5cb9b5f7dc6e000be00fb2ad8252","source":{"kind":"arxiv","id":"2508.07626","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.07626","created_at":"2026-07-05T11:51:49Z"},{"alias_kind":"arxiv_version","alias_value":"2508.07626v1","created_at":"2026-07-05T11:51:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.07626","created_at":"2026-07-05T11:51:49Z"},{"alias_kind":"pith_short_12","alias_value":"WBSHTHZRQQTB","created_at":"2026-07-05T11:51:49Z"},{"alias_kind":"pith_short_16","alias_value":"WBSHTHZRQQTBVBFL","created_at":"2026-07-05T11:51:49Z"},{"alias_kind":"pith_short_8","alias_value":"WBSHTHZR","created_at":"2026-07-05T11:51:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WBSHTHZRQQTBVBFLQB46G2HIFS","target":"record","payload":{"canonical_record":{"source":{"id":"2508.07626","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-11T05:09:58Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"318d4b98ba214675825afaa442ccaa94ec0738ebe77f0df7c8e802197d3feec7","abstract_canon_sha256":"fce667b7156369cfb515e4026d39aa5be7654da6ae32b919d3205211a21caef9"},"schema_version":"1.0"},"canonical_sha256":"b064799f3184261a84ab8079e368e82c8f5f5cb9b5f7dc6e000be00fb2ad8252","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:51:49.441444Z","signature_b64":"8NJWVIvzJbNXQQnn/6Zr2P7gnKN/kJK9LC/4DZbQleeYxL3wMLliN62XtD3RM7On7TjMa2TMrN4PaTO1ywvMBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b064799f3184261a84ab8079e368e82c8f5f5cb9b5f7dc6e000be00fb2ad8252","last_reissued_at":"2026-07-05T11:51:49.440955Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:51:49.440955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.07626","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":"2026-07-05T11:51:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5H+i7c0xiboAXoWAr3hiFBXVBTpIoT1D+PO0ixSe1PtmzRV/6I4lkNd6Ti2keDvAsCG2ztI1UTg8RrvfwR5hDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:19:21.241770Z"},"content_sha256":"7105f224e93514fd51016775677ab33b141331ed788fc5c20004f66e93e9bc2b","schema_version":"1.0","event_id":"sha256:7105f224e93514fd51016775677ab33b141331ed788fc5c20004f66e93e9bc2b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WBSHTHZRQQTBVBFLQB46G2HIFS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AR-VRM: Imitating Human Motions for Visual Robot Manipulation with Analogical Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Dejie Yang, Yang Liu, Zijing Zhao","submitted_at":"2025-08-11T05:09:58Z","abstract_excerpt":"Visual Robot Manipulation (VRM) aims to enable a robot to follow natural language instructions based on robot states and visual observations, and therefore requires costly multi-modal data. To compensate for the deficiency of robot data, existing approaches have employed vision-language pretraining with large-scale data. However, they either utilize web data that differs from robotic tasks, or train the model in an implicit way (e.g., predicting future frames at the pixel level), thus showing limited generalization ability under insufficient robot data. In this paper, we propose to learn from "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.07626","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/2508.07626/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":"2026-07-05T11:51:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X/0dq9EnINGrnNEOLsTLnqj2Kqtydg9u4e1rRyuqJ/sFPqs6JUti9CkkI/qehbq4oyCbbziZiBJ+6sf1O8ioDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:19:21.242259Z"},"content_sha256":"ff78612305841d0d8cdb8a44f6a658b4d7b7c1b092cb92be813abaea093ca631","schema_version":"1.0","event_id":"sha256:ff78612305841d0d8cdb8a44f6a658b4d7b7c1b092cb92be813abaea093ca631"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WBSHTHZRQQTBVBFLQB46G2HIFS/bundle.json","state_url":"https://pith.science/pith/WBSHTHZRQQTBVBFLQB46G2HIFS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WBSHTHZRQQTBVBFLQB46G2HIFS/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":"2026-08-06T06:19:21Z","links":{"resolver":"https://pith.science/pith/WBSHTHZRQQTBVBFLQB46G2HIFS","bundle":"https://pith.science/pith/WBSHTHZRQQTBVBFLQB46G2HIFS/bundle.json","state":"https://pith.science/pith/WBSHTHZRQQTBVBFLQB46G2HIFS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WBSHTHZRQQTBVBFLQB46G2HIFS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WBSHTHZRQQTBVBFLQB46G2HIFS","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":"fce667b7156369cfb515e4026d39aa5be7654da6ae32b919d3205211a21caef9","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-11T05:09:58Z","title_canon_sha256":"318d4b98ba214675825afaa442ccaa94ec0738ebe77f0df7c8e802197d3feec7"},"schema_version":"1.0","source":{"id":"2508.07626","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.07626","created_at":"2026-07-05T11:51:49Z"},{"alias_kind":"arxiv_version","alias_value":"2508.07626v1","created_at":"2026-07-05T11:51:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.07626","created_at":"2026-07-05T11:51:49Z"},{"alias_kind":"pith_short_12","alias_value":"WBSHTHZRQQTB","created_at":"2026-07-05T11:51:49Z"},{"alias_kind":"pith_short_16","alias_value":"WBSHTHZRQQTBVBFL","created_at":"2026-07-05T11:51:49Z"},{"alias_kind":"pith_short_8","alias_value":"WBSHTHZR","created_at":"2026-07-05T11:51:49Z"}],"graph_snapshots":[{"event_id":"sha256:ff78612305841d0d8cdb8a44f6a658b4d7b7c1b092cb92be813abaea093ca631","target":"graph","created_at":"2026-07-05T11:51:49Z","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/2508.07626/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual Robot Manipulation (VRM) aims to enable a robot to follow natural language instructions based on robot states and visual observations, and therefore requires costly multi-modal data. To compensate for the deficiency of robot data, existing approaches have employed vision-language pretraining with large-scale data. However, they either utilize web data that differs from robotic tasks, or train the model in an implicit way (e.g., predicting future frames at the pixel level), thus showing limited generalization ability under insufficient robot data. In this paper, we propose to learn from ","authors_text":"Dejie Yang, Yang Liu, Zijing Zhao","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-11T05:09:58Z","title":"AR-VRM: Imitating Human Motions for Visual Robot Manipulation with Analogical Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.07626","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":"sha256:7105f224e93514fd51016775677ab33b141331ed788fc5c20004f66e93e9bc2b","target":"record","created_at":"2026-07-05T11:51:49Z","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":"fce667b7156369cfb515e4026d39aa5be7654da6ae32b919d3205211a21caef9","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-11T05:09:58Z","title_canon_sha256":"318d4b98ba214675825afaa442ccaa94ec0738ebe77f0df7c8e802197d3feec7"},"schema_version":"1.0","source":{"id":"2508.07626","kind":"arxiv","version":1}},"canonical_sha256":"b064799f3184261a84ab8079e368e82c8f5f5cb9b5f7dc6e000be00fb2ad8252","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b064799f3184261a84ab8079e368e82c8f5f5cb9b5f7dc6e000be00fb2ad8252","first_computed_at":"2026-07-05T11:51:49.440955Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:51:49.440955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8NJWVIvzJbNXQQnn/6Zr2P7gnKN/kJK9LC/4DZbQleeYxL3wMLliN62XtD3RM7On7TjMa2TMrN4PaTO1ywvMBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:51:49.441444Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.07626","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7105f224e93514fd51016775677ab33b141331ed788fc5c20004f66e93e9bc2b","sha256:ff78612305841d0d8cdb8a44f6a658b4d7b7c1b092cb92be813abaea093ca631"],"state_sha256":"91c43abb41551c6558715a7c83e3a990608af8a3237a258abbe86a55cbe364a7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4Yfjy/kV5s3Qnn0ihRYSQuzJBuQIOKD/CtOYQnnWjdHPmcH0/duep4H6pB5N29SZFqcQa5tDa9UTdo6jGc/iCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T06:19:21.245740Z","bundle_sha256":"1f36f0f25f7b7a22a494c2e61aca4347d41b049db3cbcdd603b4087d311b1998"}}