{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TEHC4IS4ANSSLFVC2HWJEFMAQM","short_pith_number":"pith:TEHC4IS4","schema_version":"1.0","canonical_sha256":"990e2e225c03652596a2d1ec9215808302df1e402109c42074afa589301f2313","source":{"kind":"arxiv","id":"2601.16578","version":2},"attestation_state":"computed","paper":{"title":"Zero-Shot MARL Benchmark in the Cyber-Physical Mobility Lab","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A benchmark platform tests MARL policies for vehicles across simulation, digital twin, and physical hardware in zero-shot fashion.","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Bassam Alrifaee, Fynn Belderink, Jianye Xu, Julius Beerwerth, Simon Sch\\\"afer","submitted_at":"2026-01-23T09:26:36Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2601.16578","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-01-23T09:26:36Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"63c442c584613dfe586e265485ca9b3192cd74aa9a3a927124b2b2d81c453b35","abstract_canon_sha256":"5c290505fc2f74a47fd5f474c41739489dbaa7e072191823013c9ec4fd0660bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:42.942282Z","signature_b64":"IsQ8oG3X9Y7K7vKQmdRtDtp0K++4clSsOx+Nm+knVqhJboR8PpQy81eTHdu29EN1w3rjSFN5CjZBHl/7bj3KDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"990e2e225c03652596a2d1ec9215808302df1e402109c42074afa589301f2313","last_reissued_at":"2026-05-27T01:05:42.941721Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:42.941721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot MARL Benchmark in the Cyber-Physical Mobility Lab","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A benchmark platform tests MARL policies for vehicles across simulation, digital twin, and physical hardware in zero-shot fashion.","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Bassam Alrifaee, Fynn Belderink, Jianye Xu, Julius Beerwerth, Simon Sch\\\"afer","submitted_at":"2026-01-23T09:26:36Z","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"},"claims":{"count":4,"items":[{"kind":"strongest_claim","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.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","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.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","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.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A benchmark platform tests MARL policies for vehicles across simulation, digital twin, and physical hardware in zero-shot fashion.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"840bf4a9dc6315cc086f3b2b83b8722724247b9186e5dec4db63046c1e4dbbb5"},"source":{"id":"2601.16578","kind":"arxiv","version":2},"verdict":{"id":"86f0ec4d-df17-4acd-ab81-5c0b23aaf2a5","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T12:20:33.824821Z","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.","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","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.","pith_extraction_headline":"A benchmark platform tests MARL policies for vehicles across simulation, digital twin, and physical hardware in zero-shot fashion."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2601.16578/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2601.16578","created_at":"2026-05-27T01:05:42.941790+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.16578v2","created_at":"2026-05-27T01:05:42.941790+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.16578","created_at":"2026-05-27T01:05:42.941790+00:00"},{"alias_kind":"pith_short_12","alias_value":"TEHC4IS4ANSS","created_at":"2026-05-27T01:05:42.941790+00:00"},{"alias_kind":"pith_short_16","alias_value":"TEHC4IS4ANSSLFVC","created_at":"2026-05-27T01:05:42.941790+00:00"},{"alias_kind":"pith_short_8","alias_value":"TEHC4IS4","created_at":"2026-05-27T01:05:42.941790+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TEHC4IS4ANSSLFVC2HWJEFMAQM","json":"https://pith.science/pith/TEHC4IS4ANSSLFVC2HWJEFMAQM.json","graph_json":"https://pith.science/api/pith-number/TEHC4IS4ANSSLFVC2HWJEFMAQM/graph.json","events_json":"https://pith.science/api/pith-number/TEHC4IS4ANSSLFVC2HWJEFMAQM/events.json","paper":"https://pith.science/paper/TEHC4IS4"},"agent_actions":{"view_html":"https://pith.science/pith/TEHC4IS4ANSSLFVC2HWJEFMAQM","download_json":"https://pith.science/pith/TEHC4IS4ANSSLFVC2HWJEFMAQM.json","view_paper":"https://pith.science/paper/TEHC4IS4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.16578&json=true","fetch_graph":"https://pith.science/api/pith-number/TEHC4IS4ANSSLFVC2HWJEFMAQM/graph.json","fetch_events":"https://pith.science/api/pith-number/TEHC4IS4ANSSLFVC2HWJEFMAQM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TEHC4IS4ANSSLFVC2HWJEFMAQM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TEHC4IS4ANSSLFVC2HWJEFMAQM/action/storage_attestation","attest_author":"https://pith.science/pith/TEHC4IS4ANSSLFVC2HWJEFMAQM/action/author_attestation","sign_citation":"https://pith.science/pith/TEHC4IS4ANSSLFVC2HWJEFMAQM/action/citation_signature","submit_replication":"https://pith.science/pith/TEHC4IS4ANSSLFVC2HWJEFMAQM/action/replication_record"}},"created_at":"2026-05-27T01:05:42.941790+00:00","updated_at":"2026-05-27T01:05:42.941790+00:00"}