{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:3R4VRVQLMTIBYGZUV3REKKC7CF","short_pith_number":"pith:3R4VRVQL","canonical_record":{"source":{"id":"2605.23415","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T09:24:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"02c3d8093bf1cce53fed0eacbf4d9a3d8cc94cfecd5666b566bcdd4a04f27507","abstract_canon_sha256":"7d2a08785640580dac4f8961d633878ea098a052d8194dc8e0ba6bdf5dc62c6e"},"schema_version":"1.0"},"canonical_sha256":"dc7958d60b64d01c1b34aee245285f1163aaa403bb21777a4922cf46d606188d","source":{"kind":"arxiv","id":"2605.23415","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.23415","created_at":"2026-05-25T02:01:53Z"},{"alias_kind":"arxiv_version","alias_value":"2605.23415v1","created_at":"2026-05-25T02:01:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23415","created_at":"2026-05-25T02:01:53Z"},{"alias_kind":"pith_short_12","alias_value":"3R4VRVQLMTIB","created_at":"2026-05-25T02:01:53Z"},{"alias_kind":"pith_short_16","alias_value":"3R4VRVQLMTIBYGZU","created_at":"2026-05-25T02:01:53Z"},{"alias_kind":"pith_short_8","alias_value":"3R4VRVQL","created_at":"2026-05-25T02:01:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:3R4VRVQLMTIBYGZUV3REKKC7CF","target":"record","payload":{"canonical_record":{"source":{"id":"2605.23415","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T09:24:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"02c3d8093bf1cce53fed0eacbf4d9a3d8cc94cfecd5666b566bcdd4a04f27507","abstract_canon_sha256":"7d2a08785640580dac4f8961d633878ea098a052d8194dc8e0ba6bdf5dc62c6e"},"schema_version":"1.0"},"canonical_sha256":"dc7958d60b64d01c1b34aee245285f1163aaa403bb21777a4922cf46d606188d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:53.312648Z","signature_b64":"/g2LE199RgysySYAYoI1llEtLo4BvWTQo33/IHKMa6bLvo0nlQdXkzUo5oUfKcUjT9IyEUInVOYW2713lcvWCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc7958d60b64d01c1b34aee245285f1163aaa403bb21777a4922cf46d606188d","last_reissued_at":"2026-05-25T02:01:53.312056Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:53.312056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.23415","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":"2026-05-25T02:01:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wne2jTV26OgKnWo15epVxtL7WT7CrndOPZBkCuAMGrLSbpMW1b2MS01y6mSJL3dOrrZr3mcCY3E8UlgJQZVTDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T10:12:51.614725Z"},"content_sha256":"14d71a4a87d77fd36066d2bff9fe1265ff3035bb9713fc38291506deb4112ce7","schema_version":"1.0","event_id":"sha256:14d71a4a87d77fd36066d2bff9fe1265ff3035bb9713fc38291506deb4112ce7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:3R4VRVQLMTIBYGZUV3REKKC7CF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reflex: Reinforcement Learning with Reflection Symmetry Exploitation in State-Based Continuous Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Shuai Zhen, Yanhua Yu, Yifan Zhang, Yuling Wang","submitted_at":"2026-05-22T09:24:44Z","abstract_excerpt":"Reinforcement learning has long struggled with poor sample efficiency. One promising approach to mitigate this problem is leveraging group-invariant Markov Decision Processes ($G$-invariant MDPs). Existing works in this direction have primarily focused on image-based RL and rotational symmetry such as $\\mathrm{SO(2)}$, leaving state-based RL and reflection symmetry largely underexplored. In this work, we focus on state-based continuous control tasks and exploit reflection symmetry by introducing Reflex, a paradigm that seamlessly integrates with both on-policy and off-policy RL algorithms. We "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23415","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/2605.23415/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":"2026-05-25T02:01:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JiJRdQQrrq9tN9Dz65K7NA5yB9+eb9WEw2z1vGp2CU1lfF1YHAsU8y2pA6veLx3o8DGU+wNw05DLZupOPY0RDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T10:12:51.615290Z"},"content_sha256":"212aca3380c18f889ed0e221b2244341de99131fa2f4aeecb38dd2b9695de43e","schema_version":"1.0","event_id":"sha256:212aca3380c18f889ed0e221b2244341de99131fa2f4aeecb38dd2b9695de43e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3R4VRVQLMTIBYGZUV3REKKC7CF/bundle.json","state_url":"https://pith.science/pith/3R4VRVQLMTIBYGZUV3REKKC7CF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3R4VRVQLMTIBYGZUV3REKKC7CF/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":"2026-05-30T10:12:51Z","links":{"resolver":"https://pith.science/pith/3R4VRVQLMTIBYGZUV3REKKC7CF","bundle":"https://pith.science/pith/3R4VRVQLMTIBYGZUV3REKKC7CF/bundle.json","state":"https://pith.science/pith/3R4VRVQLMTIBYGZUV3REKKC7CF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3R4VRVQLMTIBYGZUV3REKKC7CF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3R4VRVQLMTIBYGZUV3REKKC7CF","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":"7d2a08785640580dac4f8961d633878ea098a052d8194dc8e0ba6bdf5dc62c6e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T09:24:44Z","title_canon_sha256":"02c3d8093bf1cce53fed0eacbf4d9a3d8cc94cfecd5666b566bcdd4a04f27507"},"schema_version":"1.0","source":{"id":"2605.23415","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.23415","created_at":"2026-05-25T02:01:53Z"},{"alias_kind":"arxiv_version","alias_value":"2605.23415v1","created_at":"2026-05-25T02:01:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23415","created_at":"2026-05-25T02:01:53Z"},{"alias_kind":"pith_short_12","alias_value":"3R4VRVQLMTIB","created_at":"2026-05-25T02:01:53Z"},{"alias_kind":"pith_short_16","alias_value":"3R4VRVQLMTIBYGZU","created_at":"2026-05-25T02:01:53Z"},{"alias_kind":"pith_short_8","alias_value":"3R4VRVQL","created_at":"2026-05-25T02:01:53Z"}],"graph_snapshots":[{"event_id":"sha256:212aca3380c18f889ed0e221b2244341de99131fa2f4aeecb38dd2b9695de43e","target":"graph","created_at":"2026-05-25T02:01:53Z","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/2605.23415/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning has long struggled with poor sample efficiency. One promising approach to mitigate this problem is leveraging group-invariant Markov Decision Processes ($G$-invariant MDPs). Existing works in this direction have primarily focused on image-based RL and rotational symmetry such as $\\mathrm{SO(2)}$, leaving state-based RL and reflection symmetry largely underexplored. In this work, we focus on state-based continuous control tasks and exploit reflection symmetry by introducing Reflex, a paradigm that seamlessly integrates with both on-policy and off-policy RL algorithms. We ","authors_text":"Shuai Zhen, Yanhua Yu, Yifan Zhang, Yuling Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T09:24:44Z","title":"Reflex: Reinforcement Learning with Reflection Symmetry Exploitation in State-Based Continuous Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23415","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":"sha256:14d71a4a87d77fd36066d2bff9fe1265ff3035bb9713fc38291506deb4112ce7","target":"record","created_at":"2026-05-25T02:01:53Z","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":"7d2a08785640580dac4f8961d633878ea098a052d8194dc8e0ba6bdf5dc62c6e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T09:24:44Z","title_canon_sha256":"02c3d8093bf1cce53fed0eacbf4d9a3d8cc94cfecd5666b566bcdd4a04f27507"},"schema_version":"1.0","source":{"id":"2605.23415","kind":"arxiv","version":1}},"canonical_sha256":"dc7958d60b64d01c1b34aee245285f1163aaa403bb21777a4922cf46d606188d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc7958d60b64d01c1b34aee245285f1163aaa403bb21777a4922cf46d606188d","first_computed_at":"2026-05-25T02:01:53.312056Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:01:53.312056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/g2LE199RgysySYAYoI1llEtLo4BvWTQo33/IHKMa6bLvo0nlQdXkzUo5oUfKcUjT9IyEUInVOYW2713lcvWCg==","signature_status":"signed_v1","signed_at":"2026-05-25T02:01:53.312648Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.23415","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:14d71a4a87d77fd36066d2bff9fe1265ff3035bb9713fc38291506deb4112ce7","sha256:212aca3380c18f889ed0e221b2244341de99131fa2f4aeecb38dd2b9695de43e"],"state_sha256":"2a43f93b2dc351826f7b43e1568307cd871bc1d4fd34c71736e6468b6fc5e605"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NMpaqhcMvT30ERWgMznIkdImQB1d3NJSCkVG+e8buxnwJo3C6P3WQ3oKhRUDZ+IQ6Hr0XPV2AFhBPLfU3wCdDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T10:12:51.618457Z","bundle_sha256":"7810a407ea216abc88a6e8e7d4ec6ba5eec7ef2e773dde16a5949c9c647c7c89"}}