{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6KGRN5URVUCK6F6KERB3CMBVCI","short_pith_number":"pith:6KGRN5UR","schema_version":"1.0","canonical_sha256":"f28d16f691ad04af17ca2443b13035123d21e38b5c8a8e17aaf3857de8d69a60","source":{"kind":"arxiv","id":"2405.19888","version":1},"attestation_state":"computed","paper":{"title":"Parrot: Efficient Serving of LLM-based Applications with Semantic Variable","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chaofan Lin, Chen Chen, Chengruidong Zhang, Fan Yang, Lili Qiu, Yuqing Yang, Zhenhua Han","submitted_at":"2024-05-30T09:46:36Z","abstract_excerpt":"The rise of large language models (LLMs) has enabled LLM-based applications (a.k.a. AI agents or co-pilots), a new software paradigm that combines the strength of LLM and conventional software. Diverse LLM applications from different tenants could design complex workflows using multiple LLM requests to accomplish one task. However, they have to use the over-simplified request-level API provided by today's public LLM services, losing essential application-level information. Public LLM services have to blindly optimize individual LLM requests, leading to sub-optimal end-to-end performance of LLM"},"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":"2405.19888","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-30T09:46:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d2c93caadcdc2acedaf5e69b4c61a402fb566257a50e5d6509db6829cccaeb7a","abstract_canon_sha256":"263b4d066718f2533ce8fc30653c90180ab52ecbad0a8270f4d70821034427a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:23.685679Z","signature_b64":"H5c/eg56HVIGGgbYnNZlXfbWEW7weCIw7yMydUkJaxCT2mviBhn7yNLDCS9lFUSI+fbQti6SWpY3XSd95cl9Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f28d16f691ad04af17ca2443b13035123d21e38b5c8a8e17aaf3857de8d69a60","last_reissued_at":"2026-07-05T08:25:23.685093Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:23.685093Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Parrot: Efficient Serving of LLM-based Applications with Semantic Variable","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chaofan Lin, Chen Chen, Chengruidong Zhang, Fan Yang, Lili Qiu, Yuqing Yang, Zhenhua Han","submitted_at":"2024-05-30T09:46:36Z","abstract_excerpt":"The rise of large language models (LLMs) has enabled LLM-based applications (a.k.a. AI agents or co-pilots), a new software paradigm that combines the strength of LLM and conventional software. Diverse LLM applications from different tenants could design complex workflows using multiple LLM requests to accomplish one task. However, they have to use the over-simplified request-level API provided by today's public LLM services, losing essential application-level information. Public LLM services have to blindly optimize individual LLM requests, leading to sub-optimal end-to-end performance of LLM"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19888","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/2405.19888/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":"2405.19888","created_at":"2026-07-05T08:25:23.685152+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.19888v1","created_at":"2026-07-05T08:25:23.685152+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19888","created_at":"2026-07-05T08:25:23.685152+00:00"},{"alias_kind":"pith_short_12","alias_value":"6KGRN5URVUCK","created_at":"2026-07-05T08:25:23.685152+00:00"},{"alias_kind":"pith_short_16","alias_value":"6KGRN5URVUCK6F6K","created_at":"2026-07-05T08:25:23.685152+00:00"},{"alias_kind":"pith_short_8","alias_value":"6KGRN5UR","created_at":"2026-07-05T08:25:23.685152+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.01481","citing_title":"TSGuard: Automated User-Centric Incident Diagnosis for AI Workloads in the Cloud","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6KGRN5URVUCK6F6KERB3CMBVCI","json":"https://pith.science/pith/6KGRN5URVUCK6F6KERB3CMBVCI.json","graph_json":"https://pith.science/api/pith-number/6KGRN5URVUCK6F6KERB3CMBVCI/graph.json","events_json":"https://pith.science/api/pith-number/6KGRN5URVUCK6F6KERB3CMBVCI/events.json","paper":"https://pith.science/paper/6KGRN5UR"},"agent_actions":{"view_html":"https://pith.science/pith/6KGRN5URVUCK6F6KERB3CMBVCI","download_json":"https://pith.science/pith/6KGRN5URVUCK6F6KERB3CMBVCI.json","view_paper":"https://pith.science/paper/6KGRN5UR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.19888&json=true","fetch_graph":"https://pith.science/api/pith-number/6KGRN5URVUCK6F6KERB3CMBVCI/graph.json","fetch_events":"https://pith.science/api/pith-number/6KGRN5URVUCK6F6KERB3CMBVCI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6KGRN5URVUCK6F6KERB3CMBVCI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6KGRN5URVUCK6F6KERB3CMBVCI/action/storage_attestation","attest_author":"https://pith.science/pith/6KGRN5URVUCK6F6KERB3CMBVCI/action/author_attestation","sign_citation":"https://pith.science/pith/6KGRN5URVUCK6F6KERB3CMBVCI/action/citation_signature","submit_replication":"https://pith.science/pith/6KGRN5URVUCK6F6KERB3CMBVCI/action/replication_record"}},"created_at":"2026-07-05T08:25:23.685152+00:00","updated_at":"2026-07-05T08:25:23.685152+00:00"}