{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MGXDZVC7DSGCZCVFBKISIHXRZG","short_pith_number":"pith:MGXDZVC7","schema_version":"1.0","canonical_sha256":"61ae3cd45f1c8c2c8aa50a91241ef1c9948683f4ef22f18173ea3748dc951236","source":{"kind":"arxiv","id":"2606.11290","version":1},"attestation_state":"computed","paper":{"title":"FlowBank: Query-Adaptive Agentic Workflows Optimization through Precompute-and-Reuse","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Chenghao Deng, Fangxu Yu, Furong Huang, Lingzhi Yuan, Mohammad Rostami, Souradip Chakraborty","submitted_at":"2026-06-09T17:58:21Z","abstract_excerpt":"Large Language Model (LLM)-based multi-agent systems are increasingly powerful, but current agentic workflow optimization paradigms make an unsatisfying trade-off. Task-level methods spend substantial offline compute yet deploy only a single workflow, leaving complementary candidates unused, while query-level methods synthesize a new workflow per query at substantial inference cost. Our motivating analysis shows these paradigms are more complementary than competing: workflows discovered during offline search often solve different subsets of queries, and many queries handled by expensive query-"},"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":"2606.11290","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-09T17:58:21Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"476d4597ddb5d5cd2202fa7c96ca4f7450b7bf9d4785bd33542fff2877cb842d","abstract_canon_sha256":"dec19db2d5aead6452aa9b777d67b64ff1654d3ad45e7bda1e38d3dc19422ae3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T00:08:16.972989Z","signature_b64":"k+GIS9vhjVzorbC5j4LvCmusSCy6NirKOvA8G7G9Dv1xsuJ6oCebZa44hRx5780JdKQ30GlazB92ecNbZSszBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61ae3cd45f1c8c2c8aa50a91241ef1c9948683f4ef22f18173ea3748dc951236","last_reissued_at":"2026-06-11T00:08:16.972173Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T00:08:16.972173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FlowBank: Query-Adaptive Agentic Workflows Optimization through Precompute-and-Reuse","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Chenghao Deng, Fangxu Yu, Furong Huang, Lingzhi Yuan, Mohammad Rostami, Souradip Chakraborty","submitted_at":"2026-06-09T17:58:21Z","abstract_excerpt":"Large Language Model (LLM)-based multi-agent systems are increasingly powerful, but current agentic workflow optimization paradigms make an unsatisfying trade-off. Task-level methods spend substantial offline compute yet deploy only a single workflow, leaving complementary candidates unused, while query-level methods synthesize a new workflow per query at substantial inference cost. Our motivating analysis shows these paradigms are more complementary than competing: workflows discovered during offline search often solve different subsets of queries, and many queries handled by expensive query-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11290","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/2606.11290/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":"2606.11290","created_at":"2026-06-11T00:08:16.972299+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.11290v1","created_at":"2026-06-11T00:08:16.972299+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11290","created_at":"2026-06-11T00:08:16.972299+00:00"},{"alias_kind":"pith_short_12","alias_value":"MGXDZVC7DSGC","created_at":"2026-06-11T00:08:16.972299+00:00"},{"alias_kind":"pith_short_16","alias_value":"MGXDZVC7DSGCZCVF","created_at":"2026-06-11T00:08:16.972299+00:00"},{"alias_kind":"pith_short_8","alias_value":"MGXDZVC7","created_at":"2026-06-11T00:08:16.972299+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MGXDZVC7DSGCZCVFBKISIHXRZG","json":"https://pith.science/pith/MGXDZVC7DSGCZCVFBKISIHXRZG.json","graph_json":"https://pith.science/api/pith-number/MGXDZVC7DSGCZCVFBKISIHXRZG/graph.json","events_json":"https://pith.science/api/pith-number/MGXDZVC7DSGCZCVFBKISIHXRZG/events.json","paper":"https://pith.science/paper/MGXDZVC7"},"agent_actions":{"view_html":"https://pith.science/pith/MGXDZVC7DSGCZCVFBKISIHXRZG","download_json":"https://pith.science/pith/MGXDZVC7DSGCZCVFBKISIHXRZG.json","view_paper":"https://pith.science/paper/MGXDZVC7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.11290&json=true","fetch_graph":"https://pith.science/api/pith-number/MGXDZVC7DSGCZCVFBKISIHXRZG/graph.json","fetch_events":"https://pith.science/api/pith-number/MGXDZVC7DSGCZCVFBKISIHXRZG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MGXDZVC7DSGCZCVFBKISIHXRZG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MGXDZVC7DSGCZCVFBKISIHXRZG/action/storage_attestation","attest_author":"https://pith.science/pith/MGXDZVC7DSGCZCVFBKISIHXRZG/action/author_attestation","sign_citation":"https://pith.science/pith/MGXDZVC7DSGCZCVFBKISIHXRZG/action/citation_signature","submit_replication":"https://pith.science/pith/MGXDZVC7DSGCZCVFBKISIHXRZG/action/replication_record"}},"created_at":"2026-06-11T00:08:16.972299+00:00","updated_at":"2026-06-11T00:08:16.972299+00:00"}