{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5QXRITSOMTOKTVKOEF7PEDQZRL","short_pith_number":"pith:5QXRITSO","schema_version":"1.0","canonical_sha256":"ec2f144e4e64dca9d54e217ef20e198ae30a5eb7413fe96b11c2a3b2d450e45c","source":{"kind":"arxiv","id":"2607.22621","version":1},"attestation_state":"computed","paper":{"title":"Opti-Q: A Constraint-Based Optimization Framework for Multi-LLM Question Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aamir Hamid, Bharg Barot, Primal Pappachan, Roberto Yus, Satvik Racharla, Tim Finin","submitted_at":"2026-06-17T02:43:58Z","abstract_excerpt":"While large language models (LLMs) enable strong question answering (QA), budgeted deployment is complicated by nondeterminism and heterogeneous resource profiles (cost, latency, and energy). We present OPTI-Q, a database-inspired, cost-based optimizer that implements a plan-before-execute paradigm for multi-LLM orchestration. OPTI-Q models LLM invocations as physical operators in an execution DAG and, for each question, searches for plans that optimize answer quality (QoA) while trading off financial cost, latency, and energy under user-specified resource constraints. Plans can include sequen"},"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":"2607.22621","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-17T02:43:58Z","cross_cats_sorted":[],"title_canon_sha256":"5dc2fb73adafa2819d722a73329382b36474a32e0393718d2eff8b2027dbf6b9","abstract_canon_sha256":"7d48ad374dae2eff8c2248abc16b26b0155495198386394e56e812b9d9991b0c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T00:21:45.530005Z","signature_b64":"G+67qfALB0/I5ICiXbtCPUisEK65d0TxpVIoaQUWbW7mUChEmVCSkpG5Je3GtxLG0gwRNUFawO1Usw1Mx4tzBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec2f144e4e64dca9d54e217ef20e198ae30a5eb7413fe96b11c2a3b2d450e45c","last_reissued_at":"2026-07-28T00:21:45.529078Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T00:21:45.529078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Opti-Q: A Constraint-Based Optimization Framework for Multi-LLM Question Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aamir Hamid, Bharg Barot, Primal Pappachan, Roberto Yus, Satvik Racharla, Tim Finin","submitted_at":"2026-06-17T02:43:58Z","abstract_excerpt":"While large language models (LLMs) enable strong question answering (QA), budgeted deployment is complicated by nondeterminism and heterogeneous resource profiles (cost, latency, and energy). We present OPTI-Q, a database-inspired, cost-based optimizer that implements a plan-before-execute paradigm for multi-LLM orchestration. OPTI-Q models LLM invocations as physical operators in an execution DAG and, for each question, searches for plans that optimize answer quality (QoA) while trading off financial cost, latency, and energy under user-specified resource constraints. Plans can include sequen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22621","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/2607.22621/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":"2607.22621","created_at":"2026-07-28T00:21:45.529539+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.22621v1","created_at":"2026-07-28T00:21:45.529539+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22621","created_at":"2026-07-28T00:21:45.529539+00:00"},{"alias_kind":"pith_short_12","alias_value":"5QXRITSOMTOK","created_at":"2026-07-28T00:21:45.529539+00:00"},{"alias_kind":"pith_short_16","alias_value":"5QXRITSOMTOKTVKO","created_at":"2026-07-28T00:21:45.529539+00:00"},{"alias_kind":"pith_short_8","alias_value":"5QXRITSO","created_at":"2026-07-28T00:21:45.529539+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/5QXRITSOMTOKTVKOEF7PEDQZRL","json":"https://pith.science/pith/5QXRITSOMTOKTVKOEF7PEDQZRL.json","graph_json":"https://pith.science/api/pith-number/5QXRITSOMTOKTVKOEF7PEDQZRL/graph.json","events_json":"https://pith.science/api/pith-number/5QXRITSOMTOKTVKOEF7PEDQZRL/events.json","paper":"https://pith.science/paper/5QXRITSO"},"agent_actions":{"view_html":"https://pith.science/pith/5QXRITSOMTOKTVKOEF7PEDQZRL","download_json":"https://pith.science/pith/5QXRITSOMTOKTVKOEF7PEDQZRL.json","view_paper":"https://pith.science/paper/5QXRITSO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.22621&json=true","fetch_graph":"https://pith.science/api/pith-number/5QXRITSOMTOKTVKOEF7PEDQZRL/graph.json","fetch_events":"https://pith.science/api/pith-number/5QXRITSOMTOKTVKOEF7PEDQZRL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5QXRITSOMTOKTVKOEF7PEDQZRL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5QXRITSOMTOKTVKOEF7PEDQZRL/action/storage_attestation","attest_author":"https://pith.science/pith/5QXRITSOMTOKTVKOEF7PEDQZRL/action/author_attestation","sign_citation":"https://pith.science/pith/5QXRITSOMTOKTVKOEF7PEDQZRL/action/citation_signature","submit_replication":"https://pith.science/pith/5QXRITSOMTOKTVKOEF7PEDQZRL/action/replication_record"}},"created_at":"2026-07-28T00:21:45.529539+00:00","updated_at":"2026-07-28T00:21:45.529539+00:00"}