{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:E3GKMRTWMMAUFLQVT7L2PNKEO3","short_pith_number":"pith:E3GKMRTW","canonical_record":{"source":{"id":"2608.13026","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-08-13T09:54:14Z","cross_cats_sorted":[],"title_canon_sha256":"a77512911f3617c30cb81b6060ba4b14af0574f21c3766b39c8dfdceb13dba25","abstract_canon_sha256":"bb294a27ee73cbfcb3efdd229d8f02325e1a3577aa8c4e181c6e6256ed182d66"},"schema_version":"1.0"},"canonical_sha256":"26cca64676630142ae159fd7a7b54476e49c6540e676b03ed3de8a53945b999f","source":{"kind":"arxiv","id":"2608.13026","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.13026","created_at":"2026-08-14T01:00:09Z"},{"alias_kind":"arxiv_version","alias_value":"2608.13026v1","created_at":"2026-08-14T01:00:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.13026","created_at":"2026-08-14T01:00:09Z"},{"alias_kind":"pith_short_12","alias_value":"E3GKMRTWMMAU","created_at":"2026-08-14T01:00:09Z"},{"alias_kind":"pith_short_16","alias_value":"E3GKMRTWMMAUFLQV","created_at":"2026-08-14T01:00:09Z"},{"alias_kind":"pith_short_8","alias_value":"E3GKMRTW","created_at":"2026-08-14T01:00:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:E3GKMRTWMMAUFLQVT7L2PNKEO3","target":"record","payload":{"canonical_record":{"source":{"id":"2608.13026","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-08-13T09:54:14Z","cross_cats_sorted":[],"title_canon_sha256":"a77512911f3617c30cb81b6060ba4b14af0574f21c3766b39c8dfdceb13dba25","abstract_canon_sha256":"bb294a27ee73cbfcb3efdd229d8f02325e1a3577aa8c4e181c6e6256ed182d66"},"schema_version":"1.0"},"canonical_sha256":"26cca64676630142ae159fd7a7b54476e49c6540e676b03ed3de8a53945b999f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-14T01:00:09.326859Z","signature_b64":"+ECAVUFBNrL7whgm2sqW/IxycpZTELCJrP1Xk4odp28ORtmbtmNRdeVafVHbPuopsFoat2DyO0KQ+eVnWwLnBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26cca64676630142ae159fd7a7b54476e49c6540e676b03ed3de8a53945b999f","last_reissued_at":"2026-08-14T01:00:09.324829Z","signature_status":"signed_v1","first_computed_at":"2026-08-14T01:00:09.324829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.13026","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":"2026-08-14T01:00:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jrjPmizTOp+qB9cC4eVs3/oabpJ/YYtUA2V0HU+c1AhqYNIPubpHHPMNYTIpLgbAs+7iBRyL9kTHfOrZudU1AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T22:39:18.517180Z"},"content_sha256":"3d931a78b8f097b2857a779182c40025fb44bdf8a6da41c1d966f97b817132bb","schema_version":"1.0","event_id":"sha256:3d931a78b8f097b2857a779182c40025fb44bdf8a6da41c1d966f97b817132bb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:E3GKMRTWMMAUFLQVT7L2PNKEO3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Temporal GRPO: Beyond Trajectory-Level Credit in Vision-Language-Action Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Changwen Zheng, Fengge Wu, Hang Gao, Wenwen Qiang, Yao Zhou","submitted_at":"2026-08-13T09:54:14Z","abstract_excerpt":"Outcome-driven reinforcement learning offers a scalable way to post-train vision-language-action (VLA) policies from sparse task-success feedback. In common GRPO-based VLA post-training, one rollout-level advantage is applied to every action in the trajectory. A rollout that completes several valid stages but fails later can therefore penalize the actions that produced its earlier progress. We call this trajectory-level credit aliasing. Temporal GRPO addresses this problem by constructing detectable task stages, aligning each rollout with stage-specific action intervals, and comparing only rol"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.13026","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/2608.13026/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":"2026-08-14T01:00:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jsrOao2wpwTzec174dAOVWjfUHt6ji118d5sqAd7oQ5I5l6OMm0TUI/UZPY4COVIZWgkoyF73pHkKahLEwUMDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T22:39:18.517734Z"},"content_sha256":"1b0015c83c6589e7fd96135ea973ef482c32575a844f2c8295cfd55cde81e61e","schema_version":"1.0","event_id":"sha256:1b0015c83c6589e7fd96135ea973ef482c32575a844f2c8295cfd55cde81e61e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E3GKMRTWMMAUFLQVT7L2PNKEO3/bundle.json","state_url":"https://pith.science/pith/E3GKMRTWMMAUFLQVT7L2PNKEO3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E3GKMRTWMMAUFLQVT7L2PNKEO3/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":"2026-08-16T22:39:18Z","links":{"resolver":"https://pith.science/pith/E3GKMRTWMMAUFLQVT7L2PNKEO3","bundle":"https://pith.science/pith/E3GKMRTWMMAUFLQVT7L2PNKEO3/bundle.json","state":"https://pith.science/pith/E3GKMRTWMMAUFLQVT7L2PNKEO3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E3GKMRTWMMAUFLQVT7L2PNKEO3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:E3GKMRTWMMAUFLQVT7L2PNKEO3","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":"bb294a27ee73cbfcb3efdd229d8f02325e1a3577aa8c4e181c6e6256ed182d66","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-08-13T09:54:14Z","title_canon_sha256":"a77512911f3617c30cb81b6060ba4b14af0574f21c3766b39c8dfdceb13dba25"},"schema_version":"1.0","source":{"id":"2608.13026","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.13026","created_at":"2026-08-14T01:00:09Z"},{"alias_kind":"arxiv_version","alias_value":"2608.13026v1","created_at":"2026-08-14T01:00:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.13026","created_at":"2026-08-14T01:00:09Z"},{"alias_kind":"pith_short_12","alias_value":"E3GKMRTWMMAU","created_at":"2026-08-14T01:00:09Z"},{"alias_kind":"pith_short_16","alias_value":"E3GKMRTWMMAUFLQV","created_at":"2026-08-14T01:00:09Z"},{"alias_kind":"pith_short_8","alias_value":"E3GKMRTW","created_at":"2026-08-14T01:00:09Z"}],"graph_snapshots":[{"event_id":"sha256:1b0015c83c6589e7fd96135ea973ef482c32575a844f2c8295cfd55cde81e61e","target":"graph","created_at":"2026-08-14T01:00:09Z","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/2608.13026/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Outcome-driven reinforcement learning offers a scalable way to post-train vision-language-action (VLA) policies from sparse task-success feedback. In common GRPO-based VLA post-training, one rollout-level advantage is applied to every action in the trajectory. A rollout that completes several valid stages but fails later can therefore penalize the actions that produced its earlier progress. We call this trajectory-level credit aliasing. Temporal GRPO addresses this problem by constructing detectable task stages, aligning each rollout with stage-specific action intervals, and comparing only rol","authors_text":"Changwen Zheng, Fengge Wu, Hang Gao, Wenwen Qiang, Yao Zhou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-08-13T09:54:14Z","title":"Temporal GRPO: Beyond Trajectory-Level Credit in Vision-Language-Action Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.13026","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":"sha256:3d931a78b8f097b2857a779182c40025fb44bdf8a6da41c1d966f97b817132bb","target":"record","created_at":"2026-08-14T01:00:09Z","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":"bb294a27ee73cbfcb3efdd229d8f02325e1a3577aa8c4e181c6e6256ed182d66","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-08-13T09:54:14Z","title_canon_sha256":"a77512911f3617c30cb81b6060ba4b14af0574f21c3766b39c8dfdceb13dba25"},"schema_version":"1.0","source":{"id":"2608.13026","kind":"arxiv","version":1}},"canonical_sha256":"26cca64676630142ae159fd7a7b54476e49c6540e676b03ed3de8a53945b999f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"26cca64676630142ae159fd7a7b54476e49c6540e676b03ed3de8a53945b999f","first_computed_at":"2026-08-14T01:00:09.324829Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-14T01:00:09.324829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+ECAVUFBNrL7whgm2sqW/IxycpZTELCJrP1Xk4odp28ORtmbtmNRdeVafVHbPuopsFoat2DyO0KQ+eVnWwLnBw==","signature_status":"signed_v1","signed_at":"2026-08-14T01:00:09.326859Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.13026","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d931a78b8f097b2857a779182c40025fb44bdf8a6da41c1d966f97b817132bb","sha256:1b0015c83c6589e7fd96135ea973ef482c32575a844f2c8295cfd55cde81e61e"],"state_sha256":"06ac8e9a2d1b5ae072755344bd92b08cefb7925ee8f797e8cf114b6b322b44d7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e7yvcbNKboW2haw0Qqz85tJTEiKLVVs69AtM6nRbAYRpVU4x5rczzOfFDkgHgliTmZADL0ly+AQ5I47xVPcNCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T22:39:18.520966Z","bundle_sha256":"f2fd1b148a72b38bb6e3ff470f17643640498418679e65e6eb77bac0f1b5e99d"}}