{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:M7YHSS75S5RKR6RYSZSNR2JQKX","short_pith_number":"pith:M7YHSS75","canonical_record":{"source":{"id":"2602.07223","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-06T22:12:52Z","cross_cats_sorted":[],"title_canon_sha256":"69513da75e6eab092c07d0104546ef5de286c2dd52ab12db58b5f33fbb610454","abstract_canon_sha256":"f27ad9f7d402b2909dd793545c086e38ad7b3457f72875607d1d34ebccec44ee"},"schema_version":"1.0"},"canonical_sha256":"67f0794bfd9762a8fa389664d8e93055d00e3176b1f9dec408a7b5f6bcb8d853","source":{"kind":"arxiv","id":"2602.07223","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.07223","created_at":"2026-06-02T01:03:42Z"},{"alias_kind":"arxiv_version","alias_value":"2602.07223v2","created_at":"2026-06-02T01:03:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.07223","created_at":"2026-06-02T01:03:42Z"},{"alias_kind":"pith_short_12","alias_value":"M7YHSS75S5RK","created_at":"2026-06-02T01:03:42Z"},{"alias_kind":"pith_short_16","alias_value":"M7YHSS75S5RKR6RY","created_at":"2026-06-02T01:03:42Z"},{"alias_kind":"pith_short_8","alias_value":"M7YHSS75","created_at":"2026-06-02T01:03:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:M7YHSS75S5RKR6RYSZSNR2JQKX","target":"record","payload":{"canonical_record":{"source":{"id":"2602.07223","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-06T22:12:52Z","cross_cats_sorted":[],"title_canon_sha256":"69513da75e6eab092c07d0104546ef5de286c2dd52ab12db58b5f33fbb610454","abstract_canon_sha256":"f27ad9f7d402b2909dd793545c086e38ad7b3457f72875607d1d34ebccec44ee"},"schema_version":"1.0"},"canonical_sha256":"67f0794bfd9762a8fa389664d8e93055d00e3176b1f9dec408a7b5f6bcb8d853","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:42.500408Z","signature_b64":"XYKdLeS2tj9Lt4GMuRj/adKqC+v/nrlfCvTX5eP2mWxtJknsZS2NY/Y+H6WOJwypJovRhiu8xbfkVtSXhSvADw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67f0794bfd9762a8fa389664d8e93055d00e3176b1f9dec408a7b5f6bcb8d853","last_reissued_at":"2026-06-02T01:03:42.499927Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:42.499927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.07223","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T01:03:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZOmY1vjdj2h3rLsrV1OqAJzW1s4FahoiOTruZb6ZGK+5objjE67lNbGAz4pr5jSmqz52qOa7iOtcboZRW3FRCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T15:09:26.944263Z"},"content_sha256":"22e224f7d4b6b0d9cfe4c020b6afa21773e282d639391fcbb607ce5ed4bcb371","schema_version":"1.0","event_id":"sha256:22e224f7d4b6b0d9cfe4c020b6afa21773e282d639391fcbb607ce5ed4bcb371"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:M7YHSS75S5RKR6RYSZSNR2JQKX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Vegas: Self-Speculative Decoding with Verification-Guided Sparse Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jian Huang, Yikang Yue, Yuqi Xue","submitted_at":"2026-02-06T22:12:52Z","abstract_excerpt":"Long-context large language model (LLM) inference has become the norm for today's AI applications. However, it is severely bottlenecked by the increasing memory demands of its KV cache. Previous works have shown that self-speculative decoding with sparse attention, where tokens are drafted using a subset of the KV cache and verified in parallel against the full KV cache, speeds up inference in a lossless manner. However, they rely on a standalone KV selection algorithm to select the KV entries used for drafting and overlook the fact that the criticality of each KV entry is inherently computed "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.07223","kind":"arxiv","version":2},"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/2602.07223/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T01:03:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fq/nhkGwPAizoYRhSXo4g3tuvIMSD+ZlaErDK5afHsOPsDwd9Za8v7f2aPuYkzTj+Qr71oR/q+4C+BURPGhYCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T15:09:26.944634Z"},"content_sha256":"37623792457582e4ca4e87ff3ea17e7109061e9b2688d8de0e75935fee9bf296","schema_version":"1.0","event_id":"sha256:37623792457582e4ca4e87ff3ea17e7109061e9b2688d8de0e75935fee9bf296"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M7YHSS75S5RKR6RYSZSNR2JQKX/bundle.json","state_url":"https://pith.science/pith/M7YHSS75S5RKR6RYSZSNR2JQKX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M7YHSS75S5RKR6RYSZSNR2JQKX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-28T15:09:26Z","links":{"resolver":"https://pith.science/pith/M7YHSS75S5RKR6RYSZSNR2JQKX","bundle":"https://pith.science/pith/M7YHSS75S5RKR6RYSZSNR2JQKX/bundle.json","state":"https://pith.science/pith/M7YHSS75S5RKR6RYSZSNR2JQKX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M7YHSS75S5RKR6RYSZSNR2JQKX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:M7YHSS75S5RKR6RYSZSNR2JQKX","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":"f27ad9f7d402b2909dd793545c086e38ad7b3457f72875607d1d34ebccec44ee","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-06T22:12:52Z","title_canon_sha256":"69513da75e6eab092c07d0104546ef5de286c2dd52ab12db58b5f33fbb610454"},"schema_version":"1.0","source":{"id":"2602.07223","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.07223","created_at":"2026-06-02T01:03:42Z"},{"alias_kind":"arxiv_version","alias_value":"2602.07223v2","created_at":"2026-06-02T01:03:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.07223","created_at":"2026-06-02T01:03:42Z"},{"alias_kind":"pith_short_12","alias_value":"M7YHSS75S5RK","created_at":"2026-06-02T01:03:42Z"},{"alias_kind":"pith_short_16","alias_value":"M7YHSS75S5RKR6RY","created_at":"2026-06-02T01:03:42Z"},{"alias_kind":"pith_short_8","alias_value":"M7YHSS75","created_at":"2026-06-02T01:03:42Z"}],"graph_snapshots":[{"event_id":"sha256:37623792457582e4ca4e87ff3ea17e7109061e9b2688d8de0e75935fee9bf296","target":"graph","created_at":"2026-06-02T01:03:42Z","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/2602.07223/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Long-context large language model (LLM) inference has become the norm for today's AI applications. However, it is severely bottlenecked by the increasing memory demands of its KV cache. Previous works have shown that self-speculative decoding with sparse attention, where tokens are drafted using a subset of the KV cache and verified in parallel against the full KV cache, speeds up inference in a lossless manner. However, they rely on a standalone KV selection algorithm to select the KV entries used for drafting and overlook the fact that the criticality of each KV entry is inherently computed ","authors_text":"Jian Huang, Yikang Yue, Yuqi Xue","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-06T22:12:52Z","title":"Vegas: Self-Speculative Decoding with Verification-Guided Sparse Attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.07223","kind":"arxiv","version":2},"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":"sha256:22e224f7d4b6b0d9cfe4c020b6afa21773e282d639391fcbb607ce5ed4bcb371","target":"record","created_at":"2026-06-02T01:03:42Z","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":"f27ad9f7d402b2909dd793545c086e38ad7b3457f72875607d1d34ebccec44ee","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-06T22:12:52Z","title_canon_sha256":"69513da75e6eab092c07d0104546ef5de286c2dd52ab12db58b5f33fbb610454"},"schema_version":"1.0","source":{"id":"2602.07223","kind":"arxiv","version":2}},"canonical_sha256":"67f0794bfd9762a8fa389664d8e93055d00e3176b1f9dec408a7b5f6bcb8d853","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67f0794bfd9762a8fa389664d8e93055d00e3176b1f9dec408a7b5f6bcb8d853","first_computed_at":"2026-06-02T01:03:42.499927Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:03:42.499927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XYKdLeS2tj9Lt4GMuRj/adKqC+v/nrlfCvTX5eP2mWxtJknsZS2NY/Y+H6WOJwypJovRhiu8xbfkVtSXhSvADw==","signature_status":"signed_v1","signed_at":"2026-06-02T01:03:42.500408Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.07223","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:22e224f7d4b6b0d9cfe4c020b6afa21773e282d639391fcbb607ce5ed4bcb371","sha256:37623792457582e4ca4e87ff3ea17e7109061e9b2688d8de0e75935fee9bf296"],"state_sha256":"8d6489f3ea2b1a9f34c280e8fc6cfe0c9ac4c4a18ff541da9f9f3568468e798a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j3JlfM+i27vX/6sztiq1+oFXsnI0KuuKSuSYMn0WDncSFDP25SCAYQhzJdAiO2LnV7cdX4ZdXkGSw+uC4OHCCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T15:09:26.946611Z","bundle_sha256":"f8855491ecf617fa135c7099f4f890584a607fcfee4114e697084e3291b933b7"}}