{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:M3OP2AJUPZDHMSXKGRHYHROLCT","short_pith_number":"pith:M3OP2AJU","schema_version":"1.0","canonical_sha256":"66dcfd01347e46764aea344f83c5cb14eeb54ca9aea305ced3f5beae82f5b0aa","source":{"kind":"arxiv","id":"2506.11105","version":3},"attestation_state":"computed","paper":{"title":"Enabling On-Device Medical AI Assistants via Input-Driven Saliency Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.AR","cs.SY","eess.SY"],"primary_cat":"cs.CL","authors_text":"Edward Humes, Rithvik Jonna, Tinoosh Mohsenin, Uttej Kallakurik, Xiaomin Lin","submitted_at":"2025-06-07T01:37:42Z","abstract_excerpt":"Large Language Models (LLMs) have significant impact on the healthcare scenarios but remain prohibitively large for deployment in real-time, resource-constrained environments such as edge devices. In this work, we introduce a novel medical assistant system, optimized through our general-purpose compression framework, which tailors Large Language Models (LLMs) for deployment in specialized domains. By measuring neuron saliency on domain-specific data, our method can aggressively prune irrelevant neurons, reducing model size while preserving performance. Following pruning, we apply post-training"},"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":"2506.11105","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-07T01:37:42Z","cross_cats_sorted":["cs.AI","cs.AR","cs.SY","eess.SY"],"title_canon_sha256":"a8391a4f519502c10813f692729cca4b6fe4fd97d439c791064a70cf7a359679","abstract_canon_sha256":"628602e099b927b3e4b6a057887f720c3db828f1f113f17a3bd0d5d79066fb13"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:55.400192Z","signature_b64":"Bgi8IHp7JVC/F728YtJRDUejJuUOOBG7u1QWp5E+jebeOp4F7HpE8U+xYYSyTqrn0IlpIooJ6tYwoak4xxr9BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66dcfd01347e46764aea344f83c5cb14eeb54ca9aea305ced3f5beae82f5b0aa","last_reissued_at":"2026-07-05T11:49:55.399730Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:55.399730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enabling On-Device Medical AI Assistants via Input-Driven Saliency Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.AR","cs.SY","eess.SY"],"primary_cat":"cs.CL","authors_text":"Edward Humes, Rithvik Jonna, Tinoosh Mohsenin, Uttej Kallakurik, Xiaomin Lin","submitted_at":"2025-06-07T01:37:42Z","abstract_excerpt":"Large Language Models (LLMs) have significant impact on the healthcare scenarios but remain prohibitively large for deployment in real-time, resource-constrained environments such as edge devices. In this work, we introduce a novel medical assistant system, optimized through our general-purpose compression framework, which tailors Large Language Models (LLMs) for deployment in specialized domains. By measuring neuron saliency on domain-specific data, our method can aggressively prune irrelevant neurons, reducing model size while preserving performance. Following pruning, we apply post-training"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11105","kind":"arxiv","version":3},"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/2506.11105/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":"2506.11105","created_at":"2026-07-05T11:49:55.399786+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.11105v3","created_at":"2026-07-05T11:49:55.399786+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11105","created_at":"2026-07-05T11:49:55.399786+00:00"},{"alias_kind":"pith_short_12","alias_value":"M3OP2AJUPZDH","created_at":"2026-07-05T11:49:55.399786+00:00"},{"alias_kind":"pith_short_16","alias_value":"M3OP2AJUPZDHMSXK","created_at":"2026-07-05T11:49:55.399786+00:00"},{"alias_kind":"pith_short_8","alias_value":"M3OP2AJU","created_at":"2026-07-05T11:49:55.399786+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.10306","citing_title":"SatReg: Regression-based Neural Architecture Search for Lightweight Satellite Image Segmentation","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M3OP2AJUPZDHMSXKGRHYHROLCT","json":"https://pith.science/pith/M3OP2AJUPZDHMSXKGRHYHROLCT.json","graph_json":"https://pith.science/api/pith-number/M3OP2AJUPZDHMSXKGRHYHROLCT/graph.json","events_json":"https://pith.science/api/pith-number/M3OP2AJUPZDHMSXKGRHYHROLCT/events.json","paper":"https://pith.science/paper/M3OP2AJU"},"agent_actions":{"view_html":"https://pith.science/pith/M3OP2AJUPZDHMSXKGRHYHROLCT","download_json":"https://pith.science/pith/M3OP2AJUPZDHMSXKGRHYHROLCT.json","view_paper":"https://pith.science/paper/M3OP2AJU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.11105&json=true","fetch_graph":"https://pith.science/api/pith-number/M3OP2AJUPZDHMSXKGRHYHROLCT/graph.json","fetch_events":"https://pith.science/api/pith-number/M3OP2AJUPZDHMSXKGRHYHROLCT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M3OP2AJUPZDHMSXKGRHYHROLCT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M3OP2AJUPZDHMSXKGRHYHROLCT/action/storage_attestation","attest_author":"https://pith.science/pith/M3OP2AJUPZDHMSXKGRHYHROLCT/action/author_attestation","sign_citation":"https://pith.science/pith/M3OP2AJUPZDHMSXKGRHYHROLCT/action/citation_signature","submit_replication":"https://pith.science/pith/M3OP2AJUPZDHMSXKGRHYHROLCT/action/replication_record"}},"created_at":"2026-07-05T11:49:55.399786+00:00","updated_at":"2026-07-05T11:49:55.399786+00:00"}