{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:IOXQHRDXY6JKAKTVI3DVYRLM3M","short_pith_number":"pith:IOXQHRDX","canonical_record":{"source":{"id":"2410.06158","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-08T16:00:47Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"d45c2ed4dc3abb5959a2ebe5a4347bf2fa470b117ac14181462082c847efe10a","abstract_canon_sha256":"a110930be44633025550a2374ae92975540cf8007deeca20676480b174a0f399"},"schema_version":"1.0"},"canonical_sha256":"43af03c477c792a02a7546c75c456cdb0235385d8234e2440ec2750eba14837d","source":{"kind":"arxiv","id":"2410.06158","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.06158","created_at":"2026-07-05T09:17:56Z"},{"alias_kind":"arxiv_version","alias_value":"2410.06158v1","created_at":"2026-07-05T09:17:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06158","created_at":"2026-07-05T09:17:56Z"},{"alias_kind":"pith_short_12","alias_value":"IOXQHRDXY6JK","created_at":"2026-07-05T09:17:56Z"},{"alias_kind":"pith_short_16","alias_value":"IOXQHRDXY6JKAKTV","created_at":"2026-07-05T09:17:56Z"},{"alias_kind":"pith_short_8","alias_value":"IOXQHRDX","created_at":"2026-07-05T09:17:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:IOXQHRDXY6JKAKTVI3DVYRLM3M","target":"record","payload":{"canonical_record":{"source":{"id":"2410.06158","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-08T16:00:47Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"d45c2ed4dc3abb5959a2ebe5a4347bf2fa470b117ac14181462082c847efe10a","abstract_canon_sha256":"a110930be44633025550a2374ae92975540cf8007deeca20676480b174a0f399"},"schema_version":"1.0"},"canonical_sha256":"43af03c477c792a02a7546c75c456cdb0235385d8234e2440ec2750eba14837d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:17:56.838368Z","signature_b64":"aMx/82qRnKxx2JG9G2l1xr5r5X05EImujV3POW8BaLKu2rLAFQ1kP17o5ykY9kZSLXaJvff3+caBwnXZj/D7Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43af03c477c792a02a7546c75c456cdb0235385d8234e2440ec2750eba14837d","last_reissued_at":"2026-07-05T09:17:56.837885Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:17:56.837885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.06158","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":"2026-07-05T09:17:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sGrJpV0nBGEukuDO+Ys71nChJy/z1f5lS7BucqPJmzgLnzK20agGLu7rQVsVL2nDZUJSenJWREM66nluM7ZyBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T17:48:24.459853Z"},"content_sha256":"c2b133da4f5549c1799547028f8f88e34aad5932893ce1de970a8ff7c97a33ad","schema_version":"1.0","event_id":"sha256:c2b133da4f5549c1799547028f8f88e34aad5932893ce1de970a8ff7c97a33ad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:IOXQHRDXY6JKAKTVI3DVYRLM3M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A robot model pre-trained on 38 million internet videos reaches 97.7 percent success across over 100 manipulation tasks.","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Chi-Lam Cheang, Guangzeng Chen, Hanbo Zhang, Hang Li, Hongtao Wu, Jiafeng Xu, Minzhao Zhu, Tao Kong, Ya Jing, Yichu Yang, Yifeng Li, Yuxiao Liu","submitted_at":"2024-10-08T16:00:47Z","abstract_excerpt":"We present GR-2, a state-of-the-art generalist robot agent for versatile and generalizable robot manipulation. GR-2 is first pre-trained on a vast number of Internet videos to capture the dynamics of the world. This large-scale pre-training, involving 38 million video clips and over 50 billion tokens, equips GR-2 with the ability to generalize across a wide range of robotic tasks and environments during subsequent policy learning. Following this, GR-2 is fine-tuned for both video generation and action prediction using robot trajectories. It exhibits impressive multi-task learning capabilities,"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"GR-2 achieves an average success rate of 97.7% across more than 100 tasks and demonstrates exceptional generalization to new, previously unseen scenarios, including novel backgrounds, environments, objects, and tasks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That large-scale pre-training on internet videos transfers useful dynamics knowledge to robot manipulation without large domain gaps that would require extensive additional robot-specific data or fine-tuning.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"GR-2 pre-trains on web-scale videos then fine-tunes on robot data to reach 97.7% average success across over 100 manipulation tasks with strong generalization to new scenes and objects.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A robot model pre-trained on 38 million internet videos reaches 97.7 percent success across over 100 manipulation tasks.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"dc91662066cfa6d73417d712fa876eb03ac6c41c9b40d7ecd825912ef71c9203"},"source":{"id":"2410.06158","kind":"arxiv","version":1},"verdict":{"id":"547d2794-ac4c-4096-bd30-c26a45e92156","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T01:04:03.376872Z","strongest_claim":"GR-2 achieves an average success rate of 97.7% across more than 100 tasks and demonstrates exceptional generalization to new, previously unseen scenarios, including novel backgrounds, environments, objects, and tasks.","one_line_summary":"GR-2 pre-trains on web-scale videos then fine-tunes on robot data to reach 97.7% average success across over 100 manipulation tasks with strong generalization to new scenes and objects.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That large-scale pre-training on internet videos transfers useful dynamics knowledge to robot manipulation without large domain gaps that would require extensive additional robot-specific data or fine-tuning.","pith_extraction_headline":"A robot model pre-trained on 38 million internet videos reaches 97.7 percent success across over 100 manipulation tasks."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.06158/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":71,"sample":[{"doi":"","year":2023,"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","ref_index":1,"cited_arxiv_id":"2303.08774","is_internal_anchor":true},{"doi":"","year":2024,"title":"SAM 2: Segment Anything in Images and Videos","work_id":"acc13f66-d814-44f9-9688-375688bf2d4a","ref_index":2,"cited_arxiv_id":"2408.00714","is_internal_anchor":true},{"doi":"","year":2024,"title":"Video generation models as world simulators","work_id":"d274a5e4-174c-445f-b42d-b4f55cdfb2f5","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2005,"title":"Language Models are Few-Shot Learners","work_id":"214732c0-2edd-44a0-af9e-28184a2b8279","ref_index":4,"cited_arxiv_id":"2005.14165","is_internal_anchor":true},{"doi":"","year":2023,"title":"Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation","work_id":"e92c2c13-4330-45fe-8231-34a6002626bd","ref_index":5,"cited_arxiv_id":"2312.13139","is_internal_anchor":true}],"resolved_work":71,"snapshot_sha256":"d092f73f2eef7fe3539989608be031c5c05f45d8717007dba59bb86ad0648c47","internal_anchors":22},"formal_canon":{"evidence_count":3,"snapshot_sha256":"6f2e1a5f3dd08f202f55641a0711d0f774f031b3bdf6fd23b40aae244fac3043"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"547d2794-ac4c-4096-bd30-c26a45e92156"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:17:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WOx7Z3ffXykS48mUR3E1i2TSeiYMAZlqcgQFv6UqJPTCLfSNYwtSjQBAxO3uF/xOPQ5w2v5w1ej/Qh0iICbeCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T17:48:24.460711Z"},"content_sha256":"cc879878db0b979932fa185c7b5089119c7c7795c39994424da6ec816a57b67e","schema_version":"1.0","event_id":"sha256:cc879878db0b979932fa185c7b5089119c7c7795c39994424da6ec816a57b67e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IOXQHRDXY6JKAKTVI3DVYRLM3M/bundle.json","state_url":"https://pith.science/pith/IOXQHRDXY6JKAKTVI3DVYRLM3M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IOXQHRDXY6JKAKTVI3DVYRLM3M/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":"2026-08-11T17:48:24Z","links":{"resolver":"https://pith.science/pith/IOXQHRDXY6JKAKTVI3DVYRLM3M","bundle":"https://pith.science/pith/IOXQHRDXY6JKAKTVI3DVYRLM3M/bundle.json","state":"https://pith.science/pith/IOXQHRDXY6JKAKTVI3DVYRLM3M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IOXQHRDXY6JKAKTVI3DVYRLM3M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IOXQHRDXY6JKAKTVI3DVYRLM3M","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":"a110930be44633025550a2374ae92975540cf8007deeca20676480b174a0f399","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-08T16:00:47Z","title_canon_sha256":"d45c2ed4dc3abb5959a2ebe5a4347bf2fa470b117ac14181462082c847efe10a"},"schema_version":"1.0","source":{"id":"2410.06158","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.06158","created_at":"2026-07-05T09:17:56Z"},{"alias_kind":"arxiv_version","alias_value":"2410.06158v1","created_at":"2026-07-05T09:17:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06158","created_at":"2026-07-05T09:17:56Z"},{"alias_kind":"pith_short_12","alias_value":"IOXQHRDXY6JK","created_at":"2026-07-05T09:17:56Z"},{"alias_kind":"pith_short_16","alias_value":"IOXQHRDXY6JKAKTV","created_at":"2026-07-05T09:17:56Z"},{"alias_kind":"pith_short_8","alias_value":"IOXQHRDX","created_at":"2026-07-05T09:17:56Z"}],"graph_snapshots":[{"event_id":"sha256:cc879878db0b979932fa185c7b5089119c7c7795c39994424da6ec816a57b67e","target":"graph","created_at":"2026-07-05T09:17:56Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"GR-2 achieves an average success rate of 97.7% across more than 100 tasks and demonstrates exceptional generalization to new, previously unseen scenarios, including novel backgrounds, environments, objects, and tasks."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That large-scale pre-training on internet videos transfers useful dynamics knowledge to robot manipulation without large domain gaps that would require extensive additional robot-specific data or fine-tuning."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"GR-2 pre-trains on web-scale videos then fine-tunes on robot data to reach 97.7% average success across over 100 manipulation tasks with strong generalization to new scenes and objects."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A robot model pre-trained on 38 million internet videos reaches 97.7 percent success across over 100 manipulation tasks."}],"snapshot_sha256":"dc91662066cfa6d73417d712fa876eb03ac6c41c9b40d7ecd825912ef71c9203"},"formal_canon":{"evidence_count":3,"snapshot_sha256":"6f2e1a5f3dd08f202f55641a0711d0f774f031b3bdf6fd23b40aae244fac3043"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.06158/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present GR-2, a state-of-the-art generalist robot agent for versatile and generalizable robot manipulation. GR-2 is first pre-trained on a vast number of Internet videos to capture the dynamics of the world. This large-scale pre-training, involving 38 million video clips and over 50 billion tokens, equips GR-2 with the ability to generalize across a wide range of robotic tasks and environments during subsequent policy learning. Following this, GR-2 is fine-tuned for both video generation and action prediction using robot trajectories. It exhibits impressive multi-task learning capabilities,","authors_text":"Chi-Lam Cheang, Guangzeng Chen, Hanbo Zhang, Hang Li, Hongtao Wu, Jiafeng Xu, Minzhao Zhu, Tao Kong, Ya Jing, Yichu Yang, Yifeng Li, Yuxiao Liu","cross_cats":["cs.CV","cs.LG"],"headline":"A robot model pre-trained on 38 million internet videos reaches 97.7 percent success across over 100 manipulation tasks.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-08T16:00:47Z","title":"GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation"},"references":{"count":71,"internal_anchors":22,"resolved_work":71,"sample":[{"cited_arxiv_id":"2303.08774","doi":"","is_internal_anchor":true,"ref_index":1,"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","year":2023},{"cited_arxiv_id":"2408.00714","doi":"","is_internal_anchor":true,"ref_index":2,"title":"SAM 2: Segment Anything in Images and Videos","work_id":"acc13f66-d814-44f9-9688-375688bf2d4a","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Video generation models as world simulators","work_id":"d274a5e4-174c-445f-b42d-b4f55cdfb2f5","year":2024},{"cited_arxiv_id":"2005.14165","doi":"","is_internal_anchor":true,"ref_index":4,"title":"Language Models are Few-Shot Learners","work_id":"214732c0-2edd-44a0-af9e-28184a2b8279","year":2005},{"cited_arxiv_id":"2312.13139","doi":"","is_internal_anchor":true,"ref_index":5,"title":"Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation","work_id":"e92c2c13-4330-45fe-8231-34a6002626bd","year":2023}],"snapshot_sha256":"d092f73f2eef7fe3539989608be031c5c05f45d8717007dba59bb86ad0648c47"},"source":{"id":"2410.06158","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-12T01:04:03.376872Z","id":"547d2794-ac4c-4096-bd30-c26a45e92156","model_set":{"reader":"grok-4.3"},"one_line_summary":"GR-2 pre-trains on web-scale videos then fine-tunes on robot data to reach 97.7% average success across over 100 manipulation tasks with strong generalization to new scenes and objects.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A robot model pre-trained on 38 million internet videos reaches 97.7 percent success across over 100 manipulation tasks.","strongest_claim":"GR-2 achieves an average success rate of 97.7% across more than 100 tasks and demonstrates exceptional generalization to new, previously unseen scenarios, including novel backgrounds, environments, objects, and tasks.","weakest_assumption":"That large-scale pre-training on internet videos transfers useful dynamics knowledge to robot manipulation without large domain gaps that would require extensive additional robot-specific data or fine-tuning."}},"verdict_id":"547d2794-ac4c-4096-bd30-c26a45e92156"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c2b133da4f5549c1799547028f8f88e34aad5932893ce1de970a8ff7c97a33ad","target":"record","created_at":"2026-07-05T09:17:56Z","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":"a110930be44633025550a2374ae92975540cf8007deeca20676480b174a0f399","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-10-08T16:00:47Z","title_canon_sha256":"d45c2ed4dc3abb5959a2ebe5a4347bf2fa470b117ac14181462082c847efe10a"},"schema_version":"1.0","source":{"id":"2410.06158","kind":"arxiv","version":1}},"canonical_sha256":"43af03c477c792a02a7546c75c456cdb0235385d8234e2440ec2750eba14837d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"43af03c477c792a02a7546c75c456cdb0235385d8234e2440ec2750eba14837d","first_computed_at":"2026-07-05T09:17:56.837885Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:17:56.837885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aMx/82qRnKxx2JG9G2l1xr5r5X05EImujV3POW8BaLKu2rLAFQ1kP17o5ykY9kZSLXaJvff3+caBwnXZj/D7Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:17:56.838368Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.06158","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c2b133da4f5549c1799547028f8f88e34aad5932893ce1de970a8ff7c97a33ad","sha256:cc879878db0b979932fa185c7b5089119c7c7795c39994424da6ec816a57b67e"],"state_sha256":"ac8834b2d93485226a4d16bd578163da77cf63ecca390d6e75300e7ee13bb5be"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gszdFdMGRVeW8p5QxVZjQXIQu41vdPI1DE3m2FysTfY0oYq8W9b/OsH19gnor2tVvXhdmnZL7b0+voksXRwTCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T17:48:24.464837Z","bundle_sha256":"8bed47a1762744af60372919efe5710d146e6d059cc542bca91525ea8cd98584"}}