{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OKWHXGL3UDHOF766D5ZTIW2RT2","short_pith_number":"pith:OKWHXGL3","schema_version":"1.0","canonical_sha256":"72ac7b997ba0cee2ffde1f73345b519e9f70972e7ffb59b346b4a2a90f117ccb","source":{"kind":"arxiv","id":"2606.05781","version":1},"attestation_state":"computed","paper":{"title":"Domain-Adapted Small Language Models with Hybrid Post-Processing: Achieving Cost-Efficient, Low-Latency Multi-Label Structured Prediction via LoRA Fine-Tuning on Scarce Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dilipkumar Nallusamy, Haifeng Wu, Sachin Kumar, Srinivasan Manoharan","submitted_at":"2026-06-04T07:09:37Z","abstract_excerpt":"Deploying frontier large language models (LLMs) for domain-specific structured evaluation tasks often incurs substantial latency, cost, and data privacy overhead. We present a hybrid framework that combines a fine-tuned small language model (LLaMA 3.1 8B, with only 2.05% trainable parameters via LoRA) and a deterministic rule-based post-processing layer. Trained on just 219 curated examples, the system is applied to multi-label compliance evaluation of conversational transcripts spanning 18 heterogeneous output fields. In blind evaluation on 53 previously unseen production transcripts, it achi"},"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":"2606.05781","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T07:09:37Z","cross_cats_sorted":[],"title_canon_sha256":"2bb0bc5c0593cf017cb1f7b55740ee1523c5e3e2a3b7bd8cff1a7922d7a7091b","abstract_canon_sha256":"c09fa9cfe125c32c098fd97b3215c2af66ca24a9499b359c89b1b7cfde66fdf8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:02.972527Z","signature_b64":"aLVn6UAlYiy3Rersr4EmJfY+X37geS1GQHGz+AOeLV8jVrKxyhglibwzHc0h1vw1XaZ1BmeGaruyrimdzEC5CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72ac7b997ba0cee2ffde1f73345b519e9f70972e7ffb59b346b4a2a90f117ccb","last_reissued_at":"2026-06-05T01:15:02.972080Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:02.972080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Domain-Adapted Small Language Models with Hybrid Post-Processing: Achieving Cost-Efficient, Low-Latency Multi-Label Structured Prediction via LoRA Fine-Tuning on Scarce Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dilipkumar Nallusamy, Haifeng Wu, Sachin Kumar, Srinivasan Manoharan","submitted_at":"2026-06-04T07:09:37Z","abstract_excerpt":"Deploying frontier large language models (LLMs) for domain-specific structured evaluation tasks often incurs substantial latency, cost, and data privacy overhead. We present a hybrid framework that combines a fine-tuned small language model (LLaMA 3.1 8B, with only 2.05% trainable parameters via LoRA) and a deterministic rule-based post-processing layer. Trained on just 219 curated examples, the system is applied to multi-label compliance evaluation of conversational transcripts spanning 18 heterogeneous output fields. In blind evaluation on 53 previously unseen production transcripts, it achi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05781","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/2606.05781/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":"2606.05781","created_at":"2026-06-05T01:15:02.972148+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05781v1","created_at":"2026-06-05T01:15:02.972148+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05781","created_at":"2026-06-05T01:15:02.972148+00:00"},{"alias_kind":"pith_short_12","alias_value":"OKWHXGL3UDHO","created_at":"2026-06-05T01:15:02.972148+00:00"},{"alias_kind":"pith_short_16","alias_value":"OKWHXGL3UDHOF766","created_at":"2026-06-05T01:15:02.972148+00:00"},{"alias_kind":"pith_short_8","alias_value":"OKWHXGL3","created_at":"2026-06-05T01:15:02.972148+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/OKWHXGL3UDHOF766D5ZTIW2RT2","json":"https://pith.science/pith/OKWHXGL3UDHOF766D5ZTIW2RT2.json","graph_json":"https://pith.science/api/pith-number/OKWHXGL3UDHOF766D5ZTIW2RT2/graph.json","events_json":"https://pith.science/api/pith-number/OKWHXGL3UDHOF766D5ZTIW2RT2/events.json","paper":"https://pith.science/paper/OKWHXGL3"},"agent_actions":{"view_html":"https://pith.science/pith/OKWHXGL3UDHOF766D5ZTIW2RT2","download_json":"https://pith.science/pith/OKWHXGL3UDHOF766D5ZTIW2RT2.json","view_paper":"https://pith.science/paper/OKWHXGL3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05781&json=true","fetch_graph":"https://pith.science/api/pith-number/OKWHXGL3UDHOF766D5ZTIW2RT2/graph.json","fetch_events":"https://pith.science/api/pith-number/OKWHXGL3UDHOF766D5ZTIW2RT2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OKWHXGL3UDHOF766D5ZTIW2RT2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OKWHXGL3UDHOF766D5ZTIW2RT2/action/storage_attestation","attest_author":"https://pith.science/pith/OKWHXGL3UDHOF766D5ZTIW2RT2/action/author_attestation","sign_citation":"https://pith.science/pith/OKWHXGL3UDHOF766D5ZTIW2RT2/action/citation_signature","submit_replication":"https://pith.science/pith/OKWHXGL3UDHOF766D5ZTIW2RT2/action/replication_record"}},"created_at":"2026-06-05T01:15:02.972148+00:00","updated_at":"2026-06-05T01:15:02.972148+00:00"}