{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2RZJZRCDHT6HYEFSUBCOB5PT2G","short_pith_number":"pith:2RZJZRCD","schema_version":"1.0","canonical_sha256":"d4729cc4433cfc7c10b2a044e0f5f3d1b5c829bf0de3e35604b766cad845c630","source":{"kind":"arxiv","id":"2411.03350","version":2},"attestation_state":"computed","paper":{"title":"A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthiness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Fali Wang, Junjie Xu, Ming Huang, Qi He, Qiuhao Lu, Rui Li, Suhang Wang, Tzuhao Mo, Wanjing Wang, Xianfeng Tang, Xianren Zhang, Yao Ma, Zhiwei Zhang, Zongyu Wu","submitted_at":"2024-11-04T04:43:01Z","abstract_excerpt":"Large language models (LLMs) have demonstrated emergent abilities in text generation, question answering, and reasoning, facilitating various tasks and domains. Despite their proficiency in various tasks, LLMs like PaLM 540B and Llama-3.1 405B face limitations due to large parameter sizes and computational demands, often requiring cloud API use which raises privacy concerns, limits real-time applications on edge devices, and increases fine-tuning costs. Additionally, LLMs often underperform in specialized domains such as healthcare and law due to insufficient domain-specific knowledge, necessi"},"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":"2411.03350","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-04T04:43:01Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a930679cdc708f007f7de5a769cfe8ecb702d70f1723d64d66c25a0e98bcfa20","abstract_canon_sha256":"3d4e010b0c456328581a85b30466cd73edbad1cd839facf45004c67723566139"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:48.149752Z","signature_b64":"7pgKR9dQ4udCXUgYZcjKu1BIyauNBGdfKb2Fhrstj5OE/JiA3y5adB4Btqi0wAQ8Fv0lTOUQu3cOlF4sSWsfBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4729cc4433cfc7c10b2a044e0f5f3d1b5c829bf0de3e35604b766cad845c630","last_reissued_at":"2026-07-05T09:54:48.149302Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:48.149302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthiness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Fali Wang, Junjie Xu, Ming Huang, Qi He, Qiuhao Lu, Rui Li, Suhang Wang, Tzuhao Mo, Wanjing Wang, Xianfeng Tang, Xianren Zhang, Yao Ma, Zhiwei Zhang, Zongyu Wu","submitted_at":"2024-11-04T04:43:01Z","abstract_excerpt":"Large language models (LLMs) have demonstrated emergent abilities in text generation, question answering, and reasoning, facilitating various tasks and domains. Despite their proficiency in various tasks, LLMs like PaLM 540B and Llama-3.1 405B face limitations due to large parameter sizes and computational demands, often requiring cloud API use which raises privacy concerns, limits real-time applications on edge devices, and increases fine-tuning costs. Additionally, LLMs often underperform in specialized domains such as healthcare and law due to insufficient domain-specific knowledge, necessi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.03350","kind":"arxiv","version":2},"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/2411.03350/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":"2411.03350","created_at":"2026-07-05T09:54:48.149372+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.03350v2","created_at":"2026-07-05T09:54:48.149372+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.03350","created_at":"2026-07-05T09:54:48.149372+00:00"},{"alias_kind":"pith_short_12","alias_value":"2RZJZRCDHT6H","created_at":"2026-07-05T09:54:48.149372+00:00"},{"alias_kind":"pith_short_16","alias_value":"2RZJZRCDHT6HYEFS","created_at":"2026-07-05T09:54:48.149372+00:00"},{"alias_kind":"pith_short_8","alias_value":"2RZJZRCD","created_at":"2026-07-05T09:54:48.149372+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21428","citing_title":"Does Mixture-of-Experts Actually Help Inference on Consumer and Edge Hardware? An Empirical Study","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18190","citing_title":"Multi-Source Cybersecurity Logs: An ATT&CK-Labeled Dataset and SLM Evaluation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2503.08223","citing_title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18455","citing_title":"OrganicHAR: Towards Activity Discovery in Organic Settings for Privacy Preserving Sensors Using Efficient Video Analysis","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2411.18279","citing_title":"Large Language Model-Brained GUI Agents: A Survey","ref_index":186,"is_internal_anchor":false},{"citing_arxiv_id":"2509.06477","citing_title":"MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2506.02153","citing_title":"Small Language Models are the Future of Agentic AI","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27143","citing_title":"Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2RZJZRCDHT6HYEFSUBCOB5PT2G","json":"https://pith.science/pith/2RZJZRCDHT6HYEFSUBCOB5PT2G.json","graph_json":"https://pith.science/api/pith-number/2RZJZRCDHT6HYEFSUBCOB5PT2G/graph.json","events_json":"https://pith.science/api/pith-number/2RZJZRCDHT6HYEFSUBCOB5PT2G/events.json","paper":"https://pith.science/paper/2RZJZRCD"},"agent_actions":{"view_html":"https://pith.science/pith/2RZJZRCDHT6HYEFSUBCOB5PT2G","download_json":"https://pith.science/pith/2RZJZRCDHT6HYEFSUBCOB5PT2G.json","view_paper":"https://pith.science/paper/2RZJZRCD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.03350&json=true","fetch_graph":"https://pith.science/api/pith-number/2RZJZRCDHT6HYEFSUBCOB5PT2G/graph.json","fetch_events":"https://pith.science/api/pith-number/2RZJZRCDHT6HYEFSUBCOB5PT2G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2RZJZRCDHT6HYEFSUBCOB5PT2G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2RZJZRCDHT6HYEFSUBCOB5PT2G/action/storage_attestation","attest_author":"https://pith.science/pith/2RZJZRCDHT6HYEFSUBCOB5PT2G/action/author_attestation","sign_citation":"https://pith.science/pith/2RZJZRCDHT6HYEFSUBCOB5PT2G/action/citation_signature","submit_replication":"https://pith.science/pith/2RZJZRCDHT6HYEFSUBCOB5PT2G/action/replication_record"}},"created_at":"2026-07-05T09:54:48.149372+00:00","updated_at":"2026-07-05T09:54:48.149372+00:00"}