{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6I5Y2JTVZSL5UERZPDCHU3ET6W","short_pith_number":"pith:6I5Y2JTV","schema_version":"1.0","canonical_sha256":"f23b8d2675cc97da123978c47a6c93f5bc561b8a47279b3da7837ada379d4ada","source":{"kind":"arxiv","id":"2607.19794","version":1},"attestation_state":"computed","paper":{"title":"TriAgent: Divergence-Aware Multi-Agent Committees for Cost-Efficient Financial Sentiment Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CE","cs.DB","cs.LG"],"primary_cat":"cs.CL","authors_text":"Isabel Xu (The Overlake School) Cynthia Xu (The Overlake School) Rachel Ren (Edwards Vacuum Inc.) Cong Guo (The University of Memphis) Jiacheng Ding (The University of Memphis)","submitted_at":"2026-07-22T06:20:32Z","abstract_excerpt":"Production LLM-based financial sentiment analysis faces a structural cost trap: most queries are trivially classifiable, yet expensive cloud reasoners process them all, and the bill scales linearly with user count. We present TriAgent, a multi-agent committee stratified by contextual granularity -- a word-level lexicon (VADER), a sentence-level domain transformer (FinBERT), and a cross-sentence reasoner (Qwen2.5, 0.5B-14B-4bit, with Mistral-7B and Phi-3.5-mini cross-family checks). A three-way Semantic Divergence Index (SDI) measures pairwise disagreement across granularities and routes each q"},"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":"2607.19794","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-22T06:20:32Z","cross_cats_sorted":["cs.CE","cs.DB","cs.LG"],"title_canon_sha256":"38c1823df685dee146871bc1f68608ca880e167b8d09da0ad1e58501a13d52f7","abstract_canon_sha256":"d53cdc64f9ced555f2e51f88acdd045a5b6ffb769867a578c89f825ada5388cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-23T01:23:59.655726Z","signature_b64":"qFYe/dS/kd75tdJtiY/jY4d825XLPZohaciWOvVl/gtkmgg2/4kiAfG5Bgc+NMT/FR+zd3nltJaebNhTWfB8DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f23b8d2675cc97da123978c47a6c93f5bc561b8a47279b3da7837ada379d4ada","last_reissued_at":"2026-07-23T01:23:59.654876Z","signature_status":"signed_v1","first_computed_at":"2026-07-23T01:23:59.654876Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TriAgent: Divergence-Aware Multi-Agent Committees for Cost-Efficient Financial Sentiment Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CE","cs.DB","cs.LG"],"primary_cat":"cs.CL","authors_text":"Isabel Xu (The Overlake School) Cynthia Xu (The Overlake School) Rachel Ren (Edwards Vacuum Inc.) Cong Guo (The University of Memphis) Jiacheng Ding (The University of Memphis)","submitted_at":"2026-07-22T06:20:32Z","abstract_excerpt":"Production LLM-based financial sentiment analysis faces a structural cost trap: most queries are trivially classifiable, yet expensive cloud reasoners process them all, and the bill scales linearly with user count. We present TriAgent, a multi-agent committee stratified by contextual granularity -- a word-level lexicon (VADER), a sentence-level domain transformer (FinBERT), and a cross-sentence reasoner (Qwen2.5, 0.5B-14B-4bit, with Mistral-7B and Phi-3.5-mini cross-family checks). A three-way Semantic Divergence Index (SDI) measures pairwise disagreement across granularities and routes each q"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.19794","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/2607.19794/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":"2607.19794","created_at":"2026-07-23T01:23:59.655305+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.19794v1","created_at":"2026-07-23T01:23:59.655305+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.19794","created_at":"2026-07-23T01:23:59.655305+00:00"},{"alias_kind":"pith_short_12","alias_value":"6I5Y2JTVZSL5","created_at":"2026-07-23T01:23:59.655305+00:00"},{"alias_kind":"pith_short_16","alias_value":"6I5Y2JTVZSL5UERZ","created_at":"2026-07-23T01:23:59.655305+00:00"},{"alias_kind":"pith_short_8","alias_value":"6I5Y2JTV","created_at":"2026-07-23T01:23:59.655305+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/6I5Y2JTVZSL5UERZPDCHU3ET6W","json":"https://pith.science/pith/6I5Y2JTVZSL5UERZPDCHU3ET6W.json","graph_json":"https://pith.science/api/pith-number/6I5Y2JTVZSL5UERZPDCHU3ET6W/graph.json","events_json":"https://pith.science/api/pith-number/6I5Y2JTVZSL5UERZPDCHU3ET6W/events.json","paper":"https://pith.science/paper/6I5Y2JTV"},"agent_actions":{"view_html":"https://pith.science/pith/6I5Y2JTVZSL5UERZPDCHU3ET6W","download_json":"https://pith.science/pith/6I5Y2JTVZSL5UERZPDCHU3ET6W.json","view_paper":"https://pith.science/paper/6I5Y2JTV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.19794&json=true","fetch_graph":"https://pith.science/api/pith-number/6I5Y2JTVZSL5UERZPDCHU3ET6W/graph.json","fetch_events":"https://pith.science/api/pith-number/6I5Y2JTVZSL5UERZPDCHU3ET6W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6I5Y2JTVZSL5UERZPDCHU3ET6W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6I5Y2JTVZSL5UERZPDCHU3ET6W/action/storage_attestation","attest_author":"https://pith.science/pith/6I5Y2JTVZSL5UERZPDCHU3ET6W/action/author_attestation","sign_citation":"https://pith.science/pith/6I5Y2JTVZSL5UERZPDCHU3ET6W/action/citation_signature","submit_replication":"https://pith.science/pith/6I5Y2JTVZSL5UERZPDCHU3ET6W/action/replication_record"}},"created_at":"2026-07-23T01:23:59.655305+00:00","updated_at":"2026-07-23T01:23:59.655305+00:00"}