{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:L7J4X3YRCMD5XL6VEMZ7KNTNS4","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":"a094d5c80fd5286647a73ce97f06c953cf00e0c65e4845ad8f29780b521ab35d","cross_cats_sorted":["math.PR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-07T11:12:59Z","title_canon_sha256":"3c943ca4d616f4547e3e7f674fb2b2d2d87fbf47e53ca5cc2ad2ca252ff6a284"},"schema_version":"1.0","source":{"id":"2605.06017","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.06017","created_at":"2026-05-20T00:03:14Z"},{"alias_kind":"arxiv_version","alias_value":"2605.06017v2","created_at":"2026-05-20T00:03:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.06017","created_at":"2026-05-20T00:03:14Z"},{"alias_kind":"pith_short_12","alias_value":"L7J4X3YRCMD5","created_at":"2026-05-20T00:03:14Z"},{"alias_kind":"pith_short_16","alias_value":"L7J4X3YRCMD5XL6V","created_at":"2026-05-20T00:03:14Z"},{"alias_kind":"pith_short_8","alias_value":"L7J4X3YR","created_at":"2026-05-20T00:03:14Z"}],"graph_snapshots":[{"event_id":"sha256:278149319273e792908a8fb6d9ae1a3781bcc8dacc745b8cf8deac08d3928935","target":"graph","created_at":"2026-05-20T00:03:14Z","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 establish a sharp McDiarmid-type inequality for dependent sequences, governed strictly by the exact matrix-vector multiplication of the causal dependency resolvent and the target sensitivity vector. This Matrix-Decoupled Concentration (MDC) framework natively recovers optimal constants for Markov chains and exploits directed d-separation to yield order-optimal bounds for causal trees. Crucially, by exactly preserving the coordinate-wise sparsity of rewards within a strictly causal framework, MDC mathematically prevents scalar collapse, guaranteeing a dimension-free O(1) variance proxy"},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The process admits a strictly causal filtration whose dependency structure can be represented by a well-defined resolvent matrix that exactly decouples the target sensitivity vector while preserving coordinate-wise sparsity of the reward."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Matrix-Decoupled Concentration achieves dimension-free O(1) variance bounds for sparse rewards in strictly causal autoregressive sequences by decoupling via the exact matrix-vector product of the dependency resolvent and sensitivity vector."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Matrix decoupling of causal dependencies yields dimension-free O(1) variance bounds for sparse rewards in autoregressive sequences."}],"snapshot_sha256":"1ccd6b49ab1f01a6acc238b2471dece2cf0e70f3bef4fabf17f18324ac40db77"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T19:31:19.185866Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T13:04:19.359377Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.06017/integrity.json","findings":[],"snapshot_sha256":"022b29305ce0177b831f76e52e1947c57d2010d1e7e605dfed21c5849bdf4990","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sequence-level evaluations in autoregressive Large Language Models (LLMs) rely on highly dependent token generation. Establishing tight concentration bounds for these processes remains a challenge due to two fundamental bottlenecks in existing frameworks: (i) classical inequalities typically separate dependency structures from target sensitivities, leading to a scalar collapse that inflates the variance proxy to a suboptimal $\\mathcal{O}(N)$ for sparse terminal rewards; (ii) conversely, while certain spatial methods achieve tighter bounds, they lack the strictly causal filtration required by s","authors_text":"Pei-Sen Li","cross_cats":["math.PR"],"headline":"Matrix decoupling of causal dependencies yields dimension-free O(1) variance bounds for sparse rewards in autoregressive sequences.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-07T11:12:59Z","title":"Matrix-Decoupled Concentration for Autoregressive Sequences: Dimension-Free Guarantees for Sparse Long-Context Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.06017","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-09T15:26:29.067015Z","id":"eebf5833-054d-45b5-8d30-c01ed6847db6","model_set":{"reader":"grok-4.3"},"one_line_summary":"Matrix-Decoupled Concentration achieves dimension-free O(1) variance bounds for sparse rewards in strictly causal autoregressive sequences by decoupling via the exact matrix-vector product of the dependency resolvent and sensitivity vector.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Matrix decoupling of causal dependencies yields dimension-free O(1) variance bounds for sparse rewards in autoregressive sequences.","strongest_claim":"we establish a sharp McDiarmid-type inequality for dependent sequences, governed strictly by the exact matrix-vector multiplication of the causal dependency resolvent and the target sensitivity vector. This Matrix-Decoupled Concentration (MDC) framework natively recovers optimal constants for Markov chains and exploits directed d-separation to yield order-optimal bounds for causal trees. Crucially, by exactly preserving the coordinate-wise sparsity of rewards within a strictly causal framework, MDC mathematically prevents scalar collapse, guaranteeing a dimension-free O(1) variance proxy","weakest_assumption":"The process admits a strictly causal filtration whose dependency structure can be represented by a well-defined resolvent matrix that exactly decouples the target sensitivity vector while preserving coordinate-wise sparsity of the reward."}},"verdict_id":"eebf5833-054d-45b5-8d30-c01ed6847db6"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0ddf93b1e451958f3ae3e581676c4c137972a9f0d5ea52fa2e188196c425ee8a","target":"record","created_at":"2026-05-20T00:03:14Z","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":"a094d5c80fd5286647a73ce97f06c953cf00e0c65e4845ad8f29780b521ab35d","cross_cats_sorted":["math.PR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-07T11:12:59Z","title_canon_sha256":"3c943ca4d616f4547e3e7f674fb2b2d2d87fbf47e53ca5cc2ad2ca252ff6a284"},"schema_version":"1.0","source":{"id":"2605.06017","kind":"arxiv","version":2}},"canonical_sha256":"5fd3cbef111307dbafd52333f5366d9703651ef387605453fd0f7b08b9b136b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5fd3cbef111307dbafd52333f5366d9703651ef387605453fd0f7b08b9b136b0","first_computed_at":"2026-05-20T00:03:14.397270Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:14.397270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X8WybKab8jBmLJ36C/Bs5Q7kfaw2hzIsh5ixvrLRWn8GjRJjL7RwKy/KDxTNYR2Zl0t4qCRYuFfG8nUoHzSSAA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:14.398438Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.06017","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0ddf93b1e451958f3ae3e581676c4c137972a9f0d5ea52fa2e188196c425ee8a","sha256:278149319273e792908a8fb6d9ae1a3781bcc8dacc745b8cf8deac08d3928935"],"state_sha256":"264894f9df6a2da97873b34092c354cdec029e5d6dd60a1eae1e5366981d9747"}