{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PHHWFOE5CANLENT2L7CUB4KTBY","short_pith_number":"pith:PHHWFOE5","schema_version":"1.0","canonical_sha256":"79cf62b89d101ab2367a5fc540f1530e3bc13017b286cbfc25ba27bdd6e39523","source":{"kind":"arxiv","id":"2402.01869","version":2},"attestation_state":"computed","paper":{"title":"InferCept: Efficient Intercept Support for Augmented Large Language Model Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.DC"],"primary_cat":"cs.LG","authors_text":"Hao Zhang, Reyna Abhyankar, Vikranth Srivatsa, Yiying Zhang, Zijian He","submitted_at":"2024-02-02T19:47:57Z","abstract_excerpt":"Large language models are increasingly integrated with external environments, tools, and agents like ChatGPT plugins to extend their capability beyond language-centric tasks. However, today's LLM inference systems are designed for standalone LLMs. They treat each external interaction as the end of LLM generation and form a new request when the interaction finishes, causing unnecessary recomputation of already computed contexts, which accounts for 37-40% of total model forwarding time. This paper presents InferCept, the first LLM inference framework targeting augmented LLMs and supporting the e"},"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":"2402.01869","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-02T19:47:57Z","cross_cats_sorted":["cs.CL","cs.DC"],"title_canon_sha256":"6ff9859b367b4ef439b4416959062ec119c2694cd0bb5e637c6ca867cd60b621","abstract_canon_sha256":"d8b4831b1979f488b5d69a4ecf3008a08e73ee474aa3d14ee3a99dd4dd7e6d00"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:59.951920Z","signature_b64":"3KU2R1UTn9ZAUYSRrqJgjWxA+InJ2IKlwsSo/AvLx2nmOYPX+EoPTEH8/VwU1gr4h6YP3tn3XVHRj5PmqcFOCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79cf62b89d101ab2367a5fc540f1530e3bc13017b286cbfc25ba27bdd6e39523","last_reissued_at":"2026-07-05T08:24:59.951466Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:59.951466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InferCept: Efficient Intercept Support for Augmented Large Language Model Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.DC"],"primary_cat":"cs.LG","authors_text":"Hao Zhang, Reyna Abhyankar, Vikranth Srivatsa, Yiying Zhang, Zijian He","submitted_at":"2024-02-02T19:47:57Z","abstract_excerpt":"Large language models are increasingly integrated with external environments, tools, and agents like ChatGPT plugins to extend their capability beyond language-centric tasks. However, today's LLM inference systems are designed for standalone LLMs. They treat each external interaction as the end of LLM generation and form a new request when the interaction finishes, causing unnecessary recomputation of already computed contexts, which accounts for 37-40% of total model forwarding time. This paper presents InferCept, the first LLM inference framework targeting augmented LLMs and supporting the e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01869","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/2402.01869/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":"2402.01869","created_at":"2026-07-05T08:24:59.951521+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.01869v2","created_at":"2026-07-05T08:24:59.951521+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01869","created_at":"2026-07-05T08:24:59.951521+00:00"},{"alias_kind":"pith_short_12","alias_value":"PHHWFOE5CANL","created_at":"2026-07-05T08:24:59.951521+00:00"},{"alias_kind":"pith_short_16","alias_value":"PHHWFOE5CANLENT2","created_at":"2026-07-05T08:24:59.951521+00:00"},{"alias_kind":"pith_short_8","alias_value":"PHHWFOE5","created_at":"2026-07-05T08:24:59.951521+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00151","citing_title":"SmoothAgent: Efficient Long-Horizon LLM-Based Agent Serving with Lookahead Context Engineering","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02964","citing_title":"Multi-Segment Attention: Enabling Efficient KV-Cache Management for Faster Large Language Model Serving","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00866","citing_title":"Idleness is Relative: Exploiting Tool-Call Idle Windows for Offloading in Agentic Systems with MORI","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27744","citing_title":"A Policy-Driven Runtime Layer for Agentic LLM Serving","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2312.07104","citing_title":"SGLang: Efficient Execution of Structured Language Model Programs","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24351","citing_title":"Diffusion Templates: A Unified Plugin Framework for Controllable Diffusion","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06296","citing_title":"AgentOpt v0.1 Technical Report: Client-Side Optimization for LLM-Based Agent","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PHHWFOE5CANLENT2L7CUB4KTBY","json":"https://pith.science/pith/PHHWFOE5CANLENT2L7CUB4KTBY.json","graph_json":"https://pith.science/api/pith-number/PHHWFOE5CANLENT2L7CUB4KTBY/graph.json","events_json":"https://pith.science/api/pith-number/PHHWFOE5CANLENT2L7CUB4KTBY/events.json","paper":"https://pith.science/paper/PHHWFOE5"},"agent_actions":{"view_html":"https://pith.science/pith/PHHWFOE5CANLENT2L7CUB4KTBY","download_json":"https://pith.science/pith/PHHWFOE5CANLENT2L7CUB4KTBY.json","view_paper":"https://pith.science/paper/PHHWFOE5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.01869&json=true","fetch_graph":"https://pith.science/api/pith-number/PHHWFOE5CANLENT2L7CUB4KTBY/graph.json","fetch_events":"https://pith.science/api/pith-number/PHHWFOE5CANLENT2L7CUB4KTBY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PHHWFOE5CANLENT2L7CUB4KTBY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PHHWFOE5CANLENT2L7CUB4KTBY/action/storage_attestation","attest_author":"https://pith.science/pith/PHHWFOE5CANLENT2L7CUB4KTBY/action/author_attestation","sign_citation":"https://pith.science/pith/PHHWFOE5CANLENT2L7CUB4KTBY/action/citation_signature","submit_replication":"https://pith.science/pith/PHHWFOE5CANLENT2L7CUB4KTBY/action/replication_record"}},"created_at":"2026-07-05T08:24:59.951521+00:00","updated_at":"2026-07-05T08:24:59.951521+00:00"}