{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:RRAV4LVIRA672Q5NB72WSF6ARN","short_pith_number":"pith:RRAV4LVI","canonical_record":{"source":{"id":"2606.03335","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-02T08:43:42Z","cross_cats_sorted":[],"title_canon_sha256":"7f382bd44fe881ddd28702d4ca146b0136edadf5cd89a231f0c5b767192ed175","abstract_canon_sha256":"4684e375f49e151bceb48159d78745141cfe8dbc4abf816cc014debdcc619b31"},"schema_version":"1.0"},"canonical_sha256":"8c415e2ea8883dfd43ad0ff56917c08b402e6c3683f6cb817cdf56ec17ca66fe","source":{"kind":"arxiv","id":"2606.03335","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03335","created_at":"2026-06-03T01:05:55Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03335v1","created_at":"2026-06-03T01:05:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03335","created_at":"2026-06-03T01:05:55Z"},{"alias_kind":"pith_short_12","alias_value":"RRAV4LVIRA67","created_at":"2026-06-03T01:05:55Z"},{"alias_kind":"pith_short_16","alias_value":"RRAV4LVIRA672Q5N","created_at":"2026-06-03T01:05:55Z"},{"alias_kind":"pith_short_8","alias_value":"RRAV4LVI","created_at":"2026-06-03T01:05:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:RRAV4LVIRA672Q5NB72WSF6ARN","target":"record","payload":{"canonical_record":{"source":{"id":"2606.03335","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-02T08:43:42Z","cross_cats_sorted":[],"title_canon_sha256":"7f382bd44fe881ddd28702d4ca146b0136edadf5cd89a231f0c5b767192ed175","abstract_canon_sha256":"4684e375f49e151bceb48159d78745141cfe8dbc4abf816cc014debdcc619b31"},"schema_version":"1.0"},"canonical_sha256":"8c415e2ea8883dfd43ad0ff56917c08b402e6c3683f6cb817cdf56ec17ca66fe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:55.308767Z","signature_b64":"2TPFhT6mmvsQBAYyr6gpbaO4UKxwPZm5fjM3fmZtOY3p1+7jXk8XDzTkRXH65TZUhsf3cbvoCxMxpddKKydZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c415e2ea8883dfd43ad0ff56917c08b402e6c3683f6cb817cdf56ec17ca66fe","last_reissued_at":"2026-06-03T01:05:55.308363Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:55.308363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.03335","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":"2026-06-03T01:05:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MXTdNRBCVkx80pwqFbLkCCwYMLoitvPA9rKVopwrpGwzFYLu0tXi7eSGb8/EUX0gxTGDATCxKgOEITmRL4R/AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T23:46:16.588630Z"},"content_sha256":"b668b6181c7c9ca24900528dcdede063c062fa8a34336f8cbca8c6c4ec7351d4","schema_version":"1.0","event_id":"sha256:b668b6181c7c9ca24900528dcdede063c062fa8a34336f8cbca8c6c4ec7351d4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:RRAV4LVIRA672Q5NB72WSF6ARN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GPU-Parallel Multi-Task Reinforcement Learning with Demonstration Guided Policy Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Junjie Lai, Qiwei Wu, Renjing Xu, Rui Zhang, Tao Li, Weihua Zhang, Yunrong Guo, Zhengyu Zhang","submitted_at":"2026-06-02T08:43:42Z","abstract_excerpt":"Large scale GPU-parallel reinforcement learning has changed what can be trained in robot simulation, yet most systems still optimize one specialist policy per task. We propose a construction methodology for turning structured manipulation task families into GPU-parallel multi-task RL benchmarks, and instantiate it as MT-Libero using LIBERO assets and task predicates in Isaac Lab. The resulting benchmark supports simultaneous reinforcement learning over heterogeneous task suites with parallel rendering, physics randomization, and state-input or visual-input policies. To make such training pract"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03335","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/2606.03335/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":"2026-06-03T01:05:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Uqsfd4nf0EOoOojJAjbZIt/ElMiyg4WTasQL8OcIcnivMk+2iTS9cdtTJwLg0f5TeyPvKmf9yYz5AWUWCM5dAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T23:46:16.589002Z"},"content_sha256":"426db2995c8f45703c62b743c3d2a4e38a039fea35b483ccedb990689444fd5d","schema_version":"1.0","event_id":"sha256:426db2995c8f45703c62b743c3d2a4e38a039fea35b483ccedb990689444fd5d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RRAV4LVIRA672Q5NB72WSF6ARN/bundle.json","state_url":"https://pith.science/pith/RRAV4LVIRA672Q5NB72WSF6ARN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RRAV4LVIRA672Q5NB72WSF6ARN/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":"2026-06-27T23:46:16Z","links":{"resolver":"https://pith.science/pith/RRAV4LVIRA672Q5NB72WSF6ARN","bundle":"https://pith.science/pith/RRAV4LVIRA672Q5NB72WSF6ARN/bundle.json","state":"https://pith.science/pith/RRAV4LVIRA672Q5NB72WSF6ARN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RRAV4LVIRA672Q5NB72WSF6ARN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RRAV4LVIRA672Q5NB72WSF6ARN","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":"4684e375f49e151bceb48159d78745141cfe8dbc4abf816cc014debdcc619b31","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-02T08:43:42Z","title_canon_sha256":"7f382bd44fe881ddd28702d4ca146b0136edadf5cd89a231f0c5b767192ed175"},"schema_version":"1.0","source":{"id":"2606.03335","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03335","created_at":"2026-06-03T01:05:55Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03335v1","created_at":"2026-06-03T01:05:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03335","created_at":"2026-06-03T01:05:55Z"},{"alias_kind":"pith_short_12","alias_value":"RRAV4LVIRA67","created_at":"2026-06-03T01:05:55Z"},{"alias_kind":"pith_short_16","alias_value":"RRAV4LVIRA672Q5N","created_at":"2026-06-03T01:05:55Z"},{"alias_kind":"pith_short_8","alias_value":"RRAV4LVI","created_at":"2026-06-03T01:05:55Z"}],"graph_snapshots":[{"event_id":"sha256:426db2995c8f45703c62b743c3d2a4e38a039fea35b483ccedb990689444fd5d","target":"graph","created_at":"2026-06-03T01:05:55Z","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/2606.03335/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large scale GPU-parallel reinforcement learning has changed what can be trained in robot simulation, yet most systems still optimize one specialist policy per task. We propose a construction methodology for turning structured manipulation task families into GPU-parallel multi-task RL benchmarks, and instantiate it as MT-Libero using LIBERO assets and task predicates in Isaac Lab. The resulting benchmark supports simultaneous reinforcement learning over heterogeneous task suites with parallel rendering, physics randomization, and state-input or visual-input policies. To make such training pract","authors_text":"Junjie Lai, Qiwei Wu, Renjing Xu, Rui Zhang, Tao Li, Weihua Zhang, Yunrong Guo, Zhengyu Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-02T08:43:42Z","title":"GPU-Parallel Multi-Task Reinforcement Learning with Demonstration Guided Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03335","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:b668b6181c7c9ca24900528dcdede063c062fa8a34336f8cbca8c6c4ec7351d4","target":"record","created_at":"2026-06-03T01:05:55Z","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":"4684e375f49e151bceb48159d78745141cfe8dbc4abf816cc014debdcc619b31","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-02T08:43:42Z","title_canon_sha256":"7f382bd44fe881ddd28702d4ca146b0136edadf5cd89a231f0c5b767192ed175"},"schema_version":"1.0","source":{"id":"2606.03335","kind":"arxiv","version":1}},"canonical_sha256":"8c415e2ea8883dfd43ad0ff56917c08b402e6c3683f6cb817cdf56ec17ca66fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c415e2ea8883dfd43ad0ff56917c08b402e6c3683f6cb817cdf56ec17ca66fe","first_computed_at":"2026-06-03T01:05:55.308363Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:55.308363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2TPFhT6mmvsQBAYyr6gpbaO4UKxwPZm5fjM3fmZtOY3p1+7jXk8XDzTkRXH65TZUhsf3cbvoCxMxpddKKydZCA==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:55.308767Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.03335","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b668b6181c7c9ca24900528dcdede063c062fa8a34336f8cbca8c6c4ec7351d4","sha256:426db2995c8f45703c62b743c3d2a4e38a039fea35b483ccedb990689444fd5d"],"state_sha256":"8633bc0bd28970f75b6b312c4d99cfceec834f911c41c80ca1eee1b07569e8b8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vimgzDnOp0DgJxZX7HXF4izZFsdvhtjiRnikv0PQardWzcx9DpgcxT4kH3NwxRLXDbCl9w0p/OTj4dt0Fmw1Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T23:46:16.590951Z","bundle_sha256":"37541c46f61d915644c088aa126969d430db2743ade1be07f7babdf53b2c2b22"}}