{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VQYAC7O4I2KUVLMAWABJSTYPWE","short_pith_number":"pith:VQYAC7O4","schema_version":"1.0","canonical_sha256":"ac30017ddc46954aad80b002994f0fb11b0b0577a599a9b1203cb77fd0fd439d","source":{"kind":"arxiv","id":"2606.18308","version":1},"attestation_state":"computed","paper":{"title":"TRIDENT: Breaking the Hybrid-Safety-Physics Coupling for Provably Safe Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bingcai Wei, Jiyuan Liu, Miao Zhang, Wenhua Nie, Yufei Liu, Zhiyu Li, Zijie Meng, Ziwei Li","submitted_at":"2026-06-16T07:41:43Z","abstract_excerpt":"Safe coordination in networked cyber-physical systems forces learning algorithms to simultaneously handle hybrid discrete-continuous actions, hard training-time safety constraints, and physics-governed dynamics. We show that these three features form a directed cycle of biases that defeats any naive composition of off-the-shelf modules, and formalize this as a three-way coupling lemma. We then introduce TRIDENT, the first MARL framework whose three components are co-designed to cancel each leak: a Richardson-Romberg gradient correction reducing Gumbel-Softmax bias from O(tau) to O(tau^2), a Ly"},"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":"2606.18308","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-16T07:41:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e8a708abbe3bf759ee6200bb5b900d54f22257b8e18558942414a43ff8d2642a","abstract_canon_sha256":"596632d5afe0facbced2a97960d6982ec6e2eb70f3d2ee7621a50dcb4bde1868"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:57.548656Z","signature_b64":"cb0EhW8Nn0EqQC4uLW3NRJhomqRUhl3kJscBjV96Ur3tPCvKmeZa8jXkOFIWhKQX92+W5axPmzeOrPOJFSG5AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac30017ddc46954aad80b002994f0fb11b0b0577a599a9b1203cb77fd0fd439d","last_reissued_at":"2026-06-19T16:10:57.548298Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:57.548298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TRIDENT: Breaking the Hybrid-Safety-Physics Coupling for Provably Safe Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bingcai Wei, Jiyuan Liu, Miao Zhang, Wenhua Nie, Yufei Liu, Zhiyu Li, Zijie Meng, Ziwei Li","submitted_at":"2026-06-16T07:41:43Z","abstract_excerpt":"Safe coordination in networked cyber-physical systems forces learning algorithms to simultaneously handle hybrid discrete-continuous actions, hard training-time safety constraints, and physics-governed dynamics. We show that these three features form a directed cycle of biases that defeats any naive composition of off-the-shelf modules, and formalize this as a three-way coupling lemma. We then introduce TRIDENT, the first MARL framework whose three components are co-designed to cancel each leak: a Richardson-Romberg gradient correction reducing Gumbel-Softmax bias from O(tau) to O(tau^2), a Ly"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18308","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/2606.18308/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":"2606.18308","created_at":"2026-06-19T16:10:57.548372+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.18308v1","created_at":"2026-06-19T16:10:57.548372+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18308","created_at":"2026-06-19T16:10:57.548372+00:00"},{"alias_kind":"pith_short_12","alias_value":"VQYAC7O4I2KU","created_at":"2026-06-19T16:10:57.548372+00:00"},{"alias_kind":"pith_short_16","alias_value":"VQYAC7O4I2KUVLMA","created_at":"2026-06-19T16:10:57.548372+00:00"},{"alias_kind":"pith_short_8","alias_value":"VQYAC7O4","created_at":"2026-06-19T16:10:57.548372+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/VQYAC7O4I2KUVLMAWABJSTYPWE","json":"https://pith.science/pith/VQYAC7O4I2KUVLMAWABJSTYPWE.json","graph_json":"https://pith.science/api/pith-number/VQYAC7O4I2KUVLMAWABJSTYPWE/graph.json","events_json":"https://pith.science/api/pith-number/VQYAC7O4I2KUVLMAWABJSTYPWE/events.json","paper":"https://pith.science/paper/VQYAC7O4"},"agent_actions":{"view_html":"https://pith.science/pith/VQYAC7O4I2KUVLMAWABJSTYPWE","download_json":"https://pith.science/pith/VQYAC7O4I2KUVLMAWABJSTYPWE.json","view_paper":"https://pith.science/paper/VQYAC7O4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.18308&json=true","fetch_graph":"https://pith.science/api/pith-number/VQYAC7O4I2KUVLMAWABJSTYPWE/graph.json","fetch_events":"https://pith.science/api/pith-number/VQYAC7O4I2KUVLMAWABJSTYPWE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VQYAC7O4I2KUVLMAWABJSTYPWE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VQYAC7O4I2KUVLMAWABJSTYPWE/action/storage_attestation","attest_author":"https://pith.science/pith/VQYAC7O4I2KUVLMAWABJSTYPWE/action/author_attestation","sign_citation":"https://pith.science/pith/VQYAC7O4I2KUVLMAWABJSTYPWE/action/citation_signature","submit_replication":"https://pith.science/pith/VQYAC7O4I2KUVLMAWABJSTYPWE/action/replication_record"}},"created_at":"2026-06-19T16:10:57.548372+00:00","updated_at":"2026-06-19T16:10:57.548372+00:00"}