{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KDUG44MTLTQLOAK6UXH5U5UNLG","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":"72a3a77f2c61d39f23e1820d955c63cbf8bf704db45e2072b84cda2f79ffcabc","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-04T06:13:52Z","title_canon_sha256":"2f9b2fa72d6b6254add972e0f35afa864b5370dd4d9d3466e365ff3818cd0756"},"schema_version":"1.0","source":{"id":"2502.02040","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.02040","created_at":"2026-07-05T10:09:22Z"},{"alias_kind":"arxiv_version","alias_value":"2502.02040v1","created_at":"2026-07-05T10:09:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02040","created_at":"2026-07-05T10:09:22Z"},{"alias_kind":"pith_short_12","alias_value":"KDUG44MTLTQL","created_at":"2026-07-05T10:09:22Z"},{"alias_kind":"pith_short_16","alias_value":"KDUG44MTLTQLOAK6","created_at":"2026-07-05T10:09:22Z"},{"alias_kind":"pith_short_8","alias_value":"KDUG44MT","created_at":"2026-07-05T10:09:22Z"}],"graph_snapshots":[{"event_id":"sha256:3b80e0136cdc5dfb87b27e6377f638b770564d8240c9129f9d1d8e41d9549ec9","target":"graph","created_at":"2026-07-05T10:09:22Z","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/2502.02040/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Residual transformations enhance the representational depth and expressive power of large language models (LLMs). However, applying static residual transformations across all tokens in auto-regressive generation leads to a suboptimal trade-off between inference efficiency and generation fidelity. Existing methods, including Early Exiting, Skip Decoding, and Mixture-of-Depth address this by modulating the residual transformation based on token-level complexity. Nevertheless, these approaches predominantly consider the distance traversed by tokens through the model layers, neglecting the underly","authors_text":"Devang Naik, Irina Belousova, Mahyar Najibi, Nikhil Bhendawade","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-04T06:13:52Z","title":"M2R2: Mixture of Multi-Rate Residuals for Efficient Transformer Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02040","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":"sha256:05594626c6c1d12ba314d25f247320022cf40b40b542589399d28700d58530cf","target":"record","created_at":"2026-07-05T10:09:22Z","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":"72a3a77f2c61d39f23e1820d955c63cbf8bf704db45e2072b84cda2f79ffcabc","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-04T06:13:52Z","title_canon_sha256":"2f9b2fa72d6b6254add972e0f35afa864b5370dd4d9d3466e365ff3818cd0756"},"schema_version":"1.0","source":{"id":"2502.02040","kind":"arxiv","version":1}},"canonical_sha256":"50e86e71935ce0b7015ea5cfda768d59824199b9a8ba1fb7730d3a9cfed97d65","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"50e86e71935ce0b7015ea5cfda768d59824199b9a8ba1fb7730d3a9cfed97d65","first_computed_at":"2026-07-05T10:09:22.660295Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:09:22.660295Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RDW68RCTNPdDR5wfiia8xRwNFwMloYhBrpBGMV+kqrgFxBJau+7ESZAY65Mb2EVYZsj58x3c5KFtmjzE2+exBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:09:22.660817Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.02040","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05594626c6c1d12ba314d25f247320022cf40b40b542589399d28700d58530cf","sha256:3b80e0136cdc5dfb87b27e6377f638b770564d8240c9129f9d1d8e41d9549ec9"],"state_sha256":"0034079915b0b6b64dc41dfb99949f0bfe15119004383d23af68ae5850c4f55d"}