{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TF2H42PGTNLXBK7W3ZNJ2LOVDS","short_pith_number":"pith:TF2H42PG","canonical_record":{"source":{"id":"2502.20330","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-27T17:59:36Z","cross_cats_sorted":[],"title_canon_sha256":"72bfb3ab87790791437a38a4dbb2121b8bde7e3af9e90198b64a8f0c8f1b7fec","abstract_canon_sha256":"a8e4418943e0a1cc56cd7f7f43b0a4c4459960775a5914c0b02829877f242b07"},"schema_version":"1.0"},"canonical_sha256":"99747e69e69b5770abf6de5a9d2dd51c957d1d373917a537c7f28c5cb21236e9","source":{"kind":"arxiv","id":"2502.20330","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.20330","created_at":"2026-07-05T11:25:42Z"},{"alias_kind":"arxiv_version","alias_value":"2502.20330v2","created_at":"2026-07-05T11:25:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.20330","created_at":"2026-07-05T11:25:42Z"},{"alias_kind":"pith_short_12","alias_value":"TF2H42PGTNLX","created_at":"2026-07-05T11:25:42Z"},{"alias_kind":"pith_short_16","alias_value":"TF2H42PGTNLXBK7W","created_at":"2026-07-05T11:25:42Z"},{"alias_kind":"pith_short_8","alias_value":"TF2H42PG","created_at":"2026-07-05T11:25:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TF2H42PGTNLXBK7W3ZNJ2LOVDS","target":"record","payload":{"canonical_record":{"source":{"id":"2502.20330","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-27T17:59:36Z","cross_cats_sorted":[],"title_canon_sha256":"72bfb3ab87790791437a38a4dbb2121b8bde7e3af9e90198b64a8f0c8f1b7fec","abstract_canon_sha256":"a8e4418943e0a1cc56cd7f7f43b0a4c4459960775a5914c0b02829877f242b07"},"schema_version":"1.0"},"canonical_sha256":"99747e69e69b5770abf6de5a9d2dd51c957d1d373917a537c7f28c5cb21236e9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:42.454341Z","signature_b64":"vwk3R02RX8Iu9yNqDDuahtR37wqQf9WBtkvkLGpejBWvk3KOUjO/qr4PGyTrugbZQ+F3oG+RKoy8VqPGfezjAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99747e69e69b5770abf6de5a9d2dd51c957d1d373917a537c7f28c5cb21236e9","last_reissued_at":"2026-07-05T11:25:42.453923Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:42.453923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.20330","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":"2026-07-05T11:25:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7eohgkTO9oN7ZpB7C+8Z5rYVGvCaRDdQrY8IbRJ7ZLwNG3aZ/EaM+HMmJGlvqetMbkZfvLRHXqQFwnSGTrpcCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:40:00.485747Z"},"content_sha256":"f69c124969711cf1eea58132bdf412aa60cdbf6ca203cb3f1842cfb138efdf8d","schema_version":"1.0","event_id":"sha256:f69c124969711cf1eea58132bdf412aa60cdbf6ca203cb3f1842cfb138efdf8d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TF2H42PGTNLXBK7W3ZNJ2LOVDS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RAPID: Long-Context Inference with Retrieval-Augmented Speculative Decoding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guanzheng Chen, Jinjie Ni, Michael Qizhe Shieh, Qilong Feng, Xin Li","submitted_at":"2025-02-27T17:59:36Z","abstract_excerpt":"The emergence of long-context large language models (LLMs) offers a promising alternative to traditional retrieval-augmented generation (RAG) for processing extensive documents. However, the computational overhead of long-context inference presents significant efficiency challenges. While Speculative Decoding (SD) traditionally accelerates inference using smaller draft models, its effectiveness diminishes substantially in long-context scenarios due to memory-bound KV cache operations. We introduce Retrieval-Augmented Speculative Decoding (RAPID), which leverages RAG for both accelerating and e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.20330","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/2502.20330/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":"2026-07-05T11:25:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vrqhWZLDUW+1Qeo9yBZxFcGbMC0glEHICwd9DLzO8gaZonGPWX3N+Z99UOBHR9h9YYziuFdbgLQ6UkUoPlpDAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:40:00.486679Z"},"content_sha256":"92cf27f0ba6d6fc33c52c550e8b48e0af8521c42c14f43cc657d33b8479f1a41","schema_version":"1.0","event_id":"sha256:92cf27f0ba6d6fc33c52c550e8b48e0af8521c42c14f43cc657d33b8479f1a41"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TF2H42PGTNLXBK7W3ZNJ2LOVDS/bundle.json","state_url":"https://pith.science/pith/TF2H42PGTNLXBK7W3ZNJ2LOVDS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TF2H42PGTNLXBK7W3ZNJ2LOVDS/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":"2026-08-04T22:40:00Z","links":{"resolver":"https://pith.science/pith/TF2H42PGTNLXBK7W3ZNJ2LOVDS","bundle":"https://pith.science/pith/TF2H42PGTNLXBK7W3ZNJ2LOVDS/bundle.json","state":"https://pith.science/pith/TF2H42PGTNLXBK7W3ZNJ2LOVDS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TF2H42PGTNLXBK7W3ZNJ2LOVDS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TF2H42PGTNLXBK7W3ZNJ2LOVDS","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":"a8e4418943e0a1cc56cd7f7f43b0a4c4459960775a5914c0b02829877f242b07","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-27T17:59:36Z","title_canon_sha256":"72bfb3ab87790791437a38a4dbb2121b8bde7e3af9e90198b64a8f0c8f1b7fec"},"schema_version":"1.0","source":{"id":"2502.20330","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.20330","created_at":"2026-07-05T11:25:42Z"},{"alias_kind":"arxiv_version","alias_value":"2502.20330v2","created_at":"2026-07-05T11:25:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.20330","created_at":"2026-07-05T11:25:42Z"},{"alias_kind":"pith_short_12","alias_value":"TF2H42PGTNLX","created_at":"2026-07-05T11:25:42Z"},{"alias_kind":"pith_short_16","alias_value":"TF2H42PGTNLXBK7W","created_at":"2026-07-05T11:25:42Z"},{"alias_kind":"pith_short_8","alias_value":"TF2H42PG","created_at":"2026-07-05T11:25:42Z"}],"graph_snapshots":[{"event_id":"sha256:92cf27f0ba6d6fc33c52c550e8b48e0af8521c42c14f43cc657d33b8479f1a41","target":"graph","created_at":"2026-07-05T11:25:42Z","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/2502.20330/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The emergence of long-context large language models (LLMs) offers a promising alternative to traditional retrieval-augmented generation (RAG) for processing extensive documents. However, the computational overhead of long-context inference presents significant efficiency challenges. While Speculative Decoding (SD) traditionally accelerates inference using smaller draft models, its effectiveness diminishes substantially in long-context scenarios due to memory-bound KV cache operations. We introduce Retrieval-Augmented Speculative Decoding (RAPID), which leverages RAG for both accelerating and e","authors_text":"Guanzheng Chen, Jinjie Ni, Michael Qizhe Shieh, Qilong Feng, Xin Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-27T17:59:36Z","title":"RAPID: Long-Context Inference with Retrieval-Augmented Speculative Decoding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.20330","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:f69c124969711cf1eea58132bdf412aa60cdbf6ca203cb3f1842cfb138efdf8d","target":"record","created_at":"2026-07-05T11:25:42Z","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":"a8e4418943e0a1cc56cd7f7f43b0a4c4459960775a5914c0b02829877f242b07","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-27T17:59:36Z","title_canon_sha256":"72bfb3ab87790791437a38a4dbb2121b8bde7e3af9e90198b64a8f0c8f1b7fec"},"schema_version":"1.0","source":{"id":"2502.20330","kind":"arxiv","version":2}},"canonical_sha256":"99747e69e69b5770abf6de5a9d2dd51c957d1d373917a537c7f28c5cb21236e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"99747e69e69b5770abf6de5a9d2dd51c957d1d373917a537c7f28c5cb21236e9","first_computed_at":"2026-07-05T11:25:42.453923Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:25:42.453923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vwk3R02RX8Iu9yNqDDuahtR37wqQf9WBtkvkLGpejBWvk3KOUjO/qr4PGyTrugbZQ+F3oG+RKoy8VqPGfezjAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:25:42.454341Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.20330","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f69c124969711cf1eea58132bdf412aa60cdbf6ca203cb3f1842cfb138efdf8d","sha256:92cf27f0ba6d6fc33c52c550e8b48e0af8521c42c14f43cc657d33b8479f1a41"],"state_sha256":"15ec6dad7af6415688360f7398b8e35fd46606237eec2ca262accfb4d0e08331"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Nml7mFGB4D4EGiHq2kC2AR0lB83spMDwTFIbt+ojhwuvjxFxl1EQ5O6EvLJ5HgN2Dos6t8nU3wWANFEM+FWyDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T22:40:00.491808Z","bundle_sha256":"315d537deac859fa1d55d54c479bfee38f2e355d45549151625a0c36b7b3b49b"}}