{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TEHC4IS4ANSSLFVC2HWJEFMAQM","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":"5c290505fc2f74a47fd5f474c41739489dbaa7e072191823013c9ec4fd0660bb","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-01-23T09:26:36Z","title_canon_sha256":"63c442c584613dfe586e265485ca9b3192cd74aa9a3a927124b2b2d81c453b35"},"schema_version":"1.0","source":{"id":"2601.16578","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.16578","created_at":"2026-05-27T01:05:42Z"},{"alias_kind":"arxiv_version","alias_value":"2601.16578v2","created_at":"2026-05-27T01:05:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.16578","created_at":"2026-05-27T01:05:42Z"},{"alias_kind":"pith_short_12","alias_value":"TEHC4IS4ANSS","created_at":"2026-05-27T01:05:42Z"},{"alias_kind":"pith_short_16","alias_value":"TEHC4IS4ANSSLFVC","created_at":"2026-05-27T01:05:42Z"},{"alias_kind":"pith_short_8","alias_value":"TEHC4IS4","created_at":"2026-05-27T01:05:42Z"}],"graph_snapshots":[{"event_id":"sha256:3fa2980fd6d070d612d7bd35e6b80c9e89f42583c8167b3cbd1c7c9bda89c9ec","target":"graph","created_at":"2026-05-27T01:05:42Z","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":"We demonstrate its use by deploying a SigmaRL-trained policy across all three domains, revealing two complementary sources of performance degradation: architectural differences between simulation and hardware control stacks, and the sim-to-real gap induced by increasing environmental realism."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that the CPM Lab setup and the chosen SigmaRL policy provide a representative test for general MARL sim-to-real challenges in CAVs."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Introduces an open-source benchmark integrating simulation, digital twin, and physical testbed for zero-shot evaluation of MARL policies in CAVs, identifying architectural and realism-induced performance degradations."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A benchmark platform tests MARL policies for vehicles across simulation, digital twin, and physical hardware in zero-shot fashion."}],"snapshot_sha256":"840bf4a9dc6315cc086f3b2b83b8722724247b9186e5dec4db63046c1e4dbbb5"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2601.16578/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a reproducible benchmark for evaluating sim-to-real transfer of Multi-Agent Reinforcement Learning (MARL) policies for Connected and Automated Vehicles (CAVs). The platform, based on the Cyber-Physical Mobility Lab (CPM Lab) [1], integrates simulation, a high-fidelity digital twin, and a physical testbed, enabling structured zero-shot evaluation of MARL motion-planning policies. We demonstrate its use by deploying a SigmaRL-trained policy [2] across all three domains, revealing two complementary sources of performance degradation: architectural differences between simulation and har","authors_text":"Bassam Alrifaee, Fynn Belderink, Jianye Xu, Julius Beerwerth, Simon Sch\\\"afer","cross_cats":["cs.SY","eess.SY"],"headline":"A benchmark platform tests MARL policies for vehicles across simulation, digital twin, and physical hardware in zero-shot fashion.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-01-23T09:26:36Z","title":"Zero-Shot MARL Benchmark in the Cyber-Physical Mobility Lab"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.16578","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-16T12:20:33.824821Z","id":"86f0ec4d-df17-4acd-ab81-5c0b23aaf2a5","model_set":{"reader":"grok-4.3"},"one_line_summary":"Introduces an open-source benchmark integrating simulation, digital twin, and physical testbed for zero-shot evaluation of MARL policies in CAVs, identifying architectural and realism-induced performance degradations.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A benchmark platform tests MARL policies for vehicles across simulation, digital twin, and physical hardware in zero-shot fashion.","strongest_claim":"We demonstrate its use by deploying a SigmaRL-trained policy across all three domains, revealing two complementary sources of performance degradation: architectural differences between simulation and hardware control stacks, and the sim-to-real gap induced by increasing environmental realism.","weakest_assumption":"The assumption that the CPM Lab setup and the chosen SigmaRL policy provide a representative test for general MARL sim-to-real challenges in CAVs."}},"verdict_id":"86f0ec4d-df17-4acd-ab81-5c0b23aaf2a5"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:14799f7f3c0c83fab6437ff11ac3361d7d8627121a6e6f4012181cbdc871c535","target":"record","created_at":"2026-05-27T01:05:42Z","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":"5c290505fc2f74a47fd5f474c41739489dbaa7e072191823013c9ec4fd0660bb","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-01-23T09:26:36Z","title_canon_sha256":"63c442c584613dfe586e265485ca9b3192cd74aa9a3a927124b2b2d81c453b35"},"schema_version":"1.0","source":{"id":"2601.16578","kind":"arxiv","version":2}},"canonical_sha256":"990e2e225c03652596a2d1ec9215808302df1e402109c42074afa589301f2313","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"990e2e225c03652596a2d1ec9215808302df1e402109c42074afa589301f2313","first_computed_at":"2026-05-27T01:05:42.941721Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:05:42.941721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IsQ8oG3X9Y7K7vKQmdRtDtp0K++4clSsOx+Nm+knVqhJboR8PpQy81eTHdu29EN1w3rjSFN5CjZBHl/7bj3KDQ==","signature_status":"signed_v1","signed_at":"2026-05-27T01:05:42.942282Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.16578","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:14799f7f3c0c83fab6437ff11ac3361d7d8627121a6e6f4012181cbdc871c535","sha256:3fa2980fd6d070d612d7bd35e6b80c9e89f42583c8167b3cbd1c7c9bda89c9ec"],"state_sha256":"91b9c9130491c45bbf06ee6a2a442b28f3b34466a092a1b7f8ee5a60cd5e51b1"}