{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6GAPTUKITT6RYOYIGBMHWV4PMR","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":"f096b207691aae984bd0607507618b736f48abc94ab6ddbf04d122da40a445cc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NI","submitted_at":"2026-05-03T22:26:52Z","title_canon_sha256":"bf90d05c95329e37618e5a2be2e3ef2b6cbfa11921357d808a59304245efbfb9"},"schema_version":"1.0","source":{"id":"2605.02075","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.02075","created_at":"2026-05-20T00:03:13Z"},{"alias_kind":"arxiv_version","alias_value":"2605.02075v2","created_at":"2026-05-20T00:03:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.02075","created_at":"2026-05-20T00:03:13Z"},{"alias_kind":"pith_short_12","alias_value":"6GAPTUKITT6R","created_at":"2026-05-20T00:03:13Z"},{"alias_kind":"pith_short_16","alias_value":"6GAPTUKITT6RYOYI","created_at":"2026-05-20T00:03:13Z"},{"alias_kind":"pith_short_8","alias_value":"6GAPTUKI","created_at":"2026-05-20T00:03:13Z"}],"graph_snapshots":[{"event_id":"sha256:70eff4a5540c170cc00c8afabcd1a1f45cd4674514bcbdc02257e13bf95193ca","target":"graph","created_at":"2026-05-20T00:03:13Z","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":"ours is the first RL method to exceed all benchmarks, increasing the supportable traffic load by up to 13%. ... We find up to 4% increased traffic load can be supported at low blocking probability (<0.1%) with our method compared to the best available benchmark algorithm."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The GPU-accelerated simulator faithfully reproduces real optical network dynamics, traffic patterns, and physical-layer impairments, and that the learned policy generalizes to traffic and topologies not seen during training."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Graph transformer RL for dynamic RMSA supports up to 13% more traffic than benchmarks on networks up to 143 nodes and 362 links."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Stabilized reinforcement learning enables the first graph transformer to exceed benchmarks on large-scale dynamic routing and spectrum allocation in optical networks."}],"snapshot_sha256":"d9efd89bb32be56ad323053f49900cde34edc4038111eb0b9058c55886409f62"},"formal_canon":{"evidence_count":3,"snapshot_sha256":"c52e307d776257ed1f7f7f822cdc45a53ffc3d1866c48d4c09828c5a284ba1f3"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T16:42:02.664268Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.02075/integrity.json","findings":[],"snapshot_sha256":"3416f49bb9e01cfadaee5e848b11636e95c2125d990a98b4d641d60560e3a0e2","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has been widely applied to dynamic routing, modulation and spectrum assignment (RMSA) in optical networks, yet no prior work has trained a transformer model for this task. We attribute this to the high data and compute requirements of transformers and potential training instabilities with RL. We address this gap by combining recent advances from the machine learning literature (rotary positional encodings for graph-structured data, off-policy invalid action masking, and valid mass regularization) with GPU-accelerated simulation to achieve, for the first time, stable","authors_text":"Alejandra Beghelli, Laura Toni, Michael Doherty","cross_cats":[],"headline":"Stabilized reinforcement learning enables the first graph transformer to exceed benchmarks on large-scale dynamic routing and spectrum allocation in optical networks.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NI","submitted_at":"2026-05-03T22:26:52Z","title":"Graph Transformers and Stabilized Reinforcement Learning for Large-Scale Dynamic Routing Modulation and Spectrum Allocation in Elastic Optical Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.02075","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-08T18:42:23.601462Z","id":"ae4a62a0-f158-4877-90ef-755cfa029d46","model_set":{"reader":"grok-4.3"},"one_line_summary":"Graph transformer RL for dynamic RMSA supports up to 13% more traffic than benchmarks on networks up to 143 nodes and 362 links.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Stabilized reinforcement learning enables the first graph transformer to exceed benchmarks on large-scale dynamic routing and spectrum allocation in optical networks.","strongest_claim":"ours is the first RL method to exceed all benchmarks, increasing the supportable traffic load by up to 13%. ... We find up to 4% increased traffic load can be supported at low blocking probability (<0.1%) with our method compared to the best available benchmark algorithm.","weakest_assumption":"The GPU-accelerated simulator faithfully reproduces real optical network dynamics, traffic patterns, and physical-layer impairments, and that the learned policy generalizes to traffic and topologies not seen during training."}},"verdict_id":"ae4a62a0-f158-4877-90ef-755cfa029d46"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:568ff850c7a175f36c2832bd950b1075d461dfe7cddf11eeef6cbb33f1c54943","target":"record","created_at":"2026-05-20T00:03:13Z","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":"f096b207691aae984bd0607507618b736f48abc94ab6ddbf04d122da40a445cc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NI","submitted_at":"2026-05-03T22:26:52Z","title_canon_sha256":"bf90d05c95329e37618e5a2be2e3ef2b6cbfa11921357d808a59304245efbfb9"},"schema_version":"1.0","source":{"id":"2605.02075","kind":"arxiv","version":2}},"canonical_sha256":"f180f9d1489cfd1c3b0830587b578f6475a65e7f626cc0e8c1fef422a2132ba5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f180f9d1489cfd1c3b0830587b578f6475a65e7f626cc0e8c1fef422a2132ba5","first_computed_at":"2026-05-20T00:03:13.660916Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:13.660916Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"goi3uhJY5tBbOqv/oRkFuQL7U2jk/RwDJsNcSCg8NJaZUI6+V2UqaRenDxPMi9J5aCUugQK9APLSstaWCjUGAA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:13.661843Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.02075","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:568ff850c7a175f36c2832bd950b1075d461dfe7cddf11eeef6cbb33f1c54943","sha256:70eff4a5540c170cc00c8afabcd1a1f45cd4674514bcbdc02257e13bf95193ca"],"state_sha256":"cba3b715221ecdffb53397d8312c336828a9edfcee7ba64a3514b4e69f805631"}