{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QFMTYWN7NPNNS5RS46HYTUFL4S","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":"62dde882873bf92ff2c194b241da3d4658989fa68751ecb2934bbb0c419a8dea","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T04:27:45Z","title_canon_sha256":"e0648e9156edcec9db51b4165254d133bbb3d2b7d602bba90c01294ffb6529d9"},"schema_version":"1.0","source":{"id":"2606.22840","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.22840","created_at":"2026-06-23T02:14:00Z"},{"alias_kind":"arxiv_version","alias_value":"2606.22840v1","created_at":"2026-06-23T02:14:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22840","created_at":"2026-06-23T02:14:00Z"},{"alias_kind":"pith_short_12","alias_value":"QFMTYWN7NPNN","created_at":"2026-06-23T02:14:00Z"},{"alias_kind":"pith_short_16","alias_value":"QFMTYWN7NPNNS5RS","created_at":"2026-06-23T02:14:00Z"},{"alias_kind":"pith_short_8","alias_value":"QFMTYWN7","created_at":"2026-06-23T02:14:00Z"}],"graph_snapshots":[{"event_id":"sha256:009ba22a1ead317c1ddb9bf02374592f03e2a535e3bed8b47b0f430b6976b680","target":"graph","created_at":"2026-06-23T02:14:00Z","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/2606.22840/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present RLM-Cascade, a proxy-layer system that applies speculative decoding at the response level to reduce LLM API costs without requiring model architecture access or a shared vocabulary. A fast, inexpensive draft model generates a candidate response; a capable verify model accepts, enhances, or is bypassed entirely depending on a lightweight complexity router. On a real-world agentic coding workload (Claude Code), RLM-Cascade achieves a draft-use rate of 88.8% across 125 production requests, reducing API cost by 45.8% relative to a direct Opus baseline. Counter-intuitively, the proxy als","authors_text":"Fangbo Tu, Haifeng Wu, Jian Wan, Junhua Zhao, Srinivasan Manoharan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T04:27:45Z","title":"RLM-Cascade: Response-Level Speculative Decoding for Cost-Efficient LLM API Serving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22840","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":"sha256:84e26bb7bbf26deed0be9f7dc2263d432cb25e87bf35aeb6c0a32dbffa643ca1","target":"record","created_at":"2026-06-23T02:14:00Z","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":"62dde882873bf92ff2c194b241da3d4658989fa68751ecb2934bbb0c419a8dea","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T04:27:45Z","title_canon_sha256":"e0648e9156edcec9db51b4165254d133bbb3d2b7d602bba90c01294ffb6529d9"},"schema_version":"1.0","source":{"id":"2606.22840","kind":"arxiv","version":1}},"canonical_sha256":"81593c59bf6bdad97632e78f89d0abe48a1864cdc6201d296d62e4ed5e9fc67c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81593c59bf6bdad97632e78f89d0abe48a1864cdc6201d296d62e4ed5e9fc67c","first_computed_at":"2026-06-23T02:14:00.825622Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:14:00.825622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dyy7k99IO8XeY95qy7BtXOBonTzx0utg+DarFskcVpO0Czn1XqUQufdUl4aH6r1vMNaQMQ38Dxe77suQaOpIBQ==","signature_status":"signed_v1","signed_at":"2026-06-23T02:14:00.826008Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.22840","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:84e26bb7bbf26deed0be9f7dc2263d432cb25e87bf35aeb6c0a32dbffa643ca1","sha256:009ba22a1ead317c1ddb9bf02374592f03e2a535e3bed8b47b0f430b6976b680"],"state_sha256":"3f0991ac75a73d295fc1044fdfa0156b59e65beeed3070666ea9267357388b56"}