{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:E4FV4N5N5735N42XPJUKHD6YVZ","short_pith_number":"pith:E4FV4N5N","schema_version":"1.0","canonical_sha256":"270b5e37adeff7d6f3577a68a38fd8ae78361ce6ff597b17129fe1efff2ebe69","source":{"kind":"arxiv","id":"2307.02628","version":1},"attestation_state":"computed","paper":{"title":"SkipDecode: Autoregressive Skip Decoding with Batching and Caching for Efficient LLM Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmed Awadallah, Allie Del Giorno, Bin Yu, Luciano Del Corro, Sahaj Agarwal, Subhabrata Mukherjee","submitted_at":"2023-07-05T19:59:09Z","abstract_excerpt":"Autoregressive large language models (LLMs) have made remarkable progress in various natural language generation tasks. However, they incur high computation cost and latency resulting from the autoregressive token-by-token generation. To address this issue, several approaches have been proposed to reduce computational cost using early-exit strategies. These strategies enable faster text generation using reduced computation without applying the full computation graph to each token. While existing token-level early exit methods show promising results for online inference, they cannot be readily "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2307.02628","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-05T19:59:09Z","cross_cats_sorted":[],"title_canon_sha256":"b8bbd0adeefc28579274765caaaef213b9f953660cde3049dea901ee85c30d9f","abstract_canon_sha256":"50624beba4ce77e85d695aceedf7f8e39d138b789397817f166afadb2145f894"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:28:22.190199Z","signature_b64":"Hbhdvt3O3PBODsu0JRvt5aJEmew1En2DYQ/koc9bkrFGSiHNA/0FRsXb9Vd+sNxC+DSwEZd9hsSXkCnFumrcDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"270b5e37adeff7d6f3577a68a38fd8ae78361ce6ff597b17129fe1efff2ebe69","last_reissued_at":"2026-07-05T06:28:22.189779Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:28:22.189779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SkipDecode: Autoregressive Skip Decoding with Batching and Caching for Efficient LLM Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmed Awadallah, Allie Del Giorno, Bin Yu, Luciano Del Corro, Sahaj Agarwal, Subhabrata Mukherjee","submitted_at":"2023-07-05T19:59:09Z","abstract_excerpt":"Autoregressive large language models (LLMs) have made remarkable progress in various natural language generation tasks. However, they incur high computation cost and latency resulting from the autoregressive token-by-token generation. To address this issue, several approaches have been proposed to reduce computational cost using early-exit strategies. These strategies enable faster text generation using reduced computation without applying the full computation graph to each token. While existing token-level early exit methods show promising results for online inference, they cannot be readily "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.02628","kind":"arxiv","version":1},"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/2307.02628/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2307.02628","created_at":"2026-07-05T06:28:22.189837+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.02628v1","created_at":"2026-07-05T06:28:22.189837+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.02628","created_at":"2026-07-05T06:28:22.189837+00:00"},{"alias_kind":"pith_short_12","alias_value":"E4FV4N5N5735","created_at":"2026-07-05T06:28:22.189837+00:00"},{"alias_kind":"pith_short_16","alias_value":"E4FV4N5N5735N42X","created_at":"2026-07-05T06:28:22.189837+00:00"},{"alias_kind":"pith_short_8","alias_value":"E4FV4N5N","created_at":"2026-07-05T06:28:22.189837+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2408.12935","citing_title":"AI Safety Landscape for Large Language Models: Taxonomy, State-of-the-art, and Future Directions","ref_index":150,"is_internal_anchor":false},{"citing_arxiv_id":"2511.13587","citing_title":"VVS: Accelerating Speculative Decoding for Visual Autoregressive Generation via Partial Verification Skipping","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2404.14294","citing_title":"A Survey on Efficient Inference for Large Language Models","ref_index":111,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13190","citing_title":"N-vium: Mixture-of-Exits Transformer for Accelerated Exact Generation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22906","citing_title":"Network Edge Inference for Large Language Models: Principles, Techniques, and Opportunities","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07857","citing_title":"Networking-Aware Energy Efficiency in Agentic AI Inference: A Survey","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18396","citing_title":"River-LLM: Large Language Model Seamless Exit Based on KV Share","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15764","citing_title":"When Do Early-Exit Networks Generalize? A PAC-Bayesian Theory of Adaptive Depth","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17286","citing_title":"Depth Adaptive Efficient Visual Autoregressive Modeling","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E4FV4N5N5735N42XPJUKHD6YVZ","json":"https://pith.science/pith/E4FV4N5N5735N42XPJUKHD6YVZ.json","graph_json":"https://pith.science/api/pith-number/E4FV4N5N5735N42XPJUKHD6YVZ/graph.json","events_json":"https://pith.science/api/pith-number/E4FV4N5N5735N42XPJUKHD6YVZ/events.json","paper":"https://pith.science/paper/E4FV4N5N"},"agent_actions":{"view_html":"https://pith.science/pith/E4FV4N5N5735N42XPJUKHD6YVZ","download_json":"https://pith.science/pith/E4FV4N5N5735N42XPJUKHD6YVZ.json","view_paper":"https://pith.science/paper/E4FV4N5N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.02628&json=true","fetch_graph":"https://pith.science/api/pith-number/E4FV4N5N5735N42XPJUKHD6YVZ/graph.json","fetch_events":"https://pith.science/api/pith-number/E4FV4N5N5735N42XPJUKHD6YVZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E4FV4N5N5735N42XPJUKHD6YVZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E4FV4N5N5735N42XPJUKHD6YVZ/action/storage_attestation","attest_author":"https://pith.science/pith/E4FV4N5N5735N42XPJUKHD6YVZ/action/author_attestation","sign_citation":"https://pith.science/pith/E4FV4N5N5735N42XPJUKHD6YVZ/action/citation_signature","submit_replication":"https://pith.science/pith/E4FV4N5N5735N42XPJUKHD6YVZ/action/replication_record"}},"created_at":"2026-07-05T06:28:22.189837+00:00","updated_at":"2026-07-05T06:28:22.189837+00:00"}