{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QOL5LLM6ZKEGP3JKF3OYEL7ML5","short_pith_number":"pith:QOL5LLM6","schema_version":"1.0","canonical_sha256":"8397d5ad9eca8867ed2a2edd822fec5f5277fa5acaa79cc383fc831063ca7a77","source":{"kind":"arxiv","id":"2505.02309","version":2},"attestation_state":"computed","paper":{"title":"Optimizing LLMs for Resource-Constrained Environments: A Survey of Model Compression Techniques","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Aman Raj, Ankit Shetgaonkar, Dipen Pradhan, Lakshit Arora, Sanjay Surendranath Girija, Shashank Kapoor","submitted_at":"2025-05-05T01:27:47Z","abstract_excerpt":"Large Language Models (LLMs) have revolutionized many areas of artificial intelligence (AI), but their substantial resource requirements limit their deployment on mobile and edge devices. This survey paper provides a comprehensive overview of techniques for compressing LLMs to enable efficient inference in resource-constrained environments. We examine three primary approaches: Knowledge Distillation, Model Quantization, and Model Pruning. For each technique, we discuss the underlying principles, present different variants, and provide examples of successful applications. We also briefly discus"},"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":"2505.02309","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-05T01:27:47Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"832662ad8ae2e1d24370b94243c101579675f8c56b8bd9a4ac3be9342c36b650","abstract_canon_sha256":"097fe4befb3599086780efd6f51532f73fb12ea424e2958b300247889ef74fe0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:01.014828Z","signature_b64":"bv/NYwW7Jyao8qb/Pc/GAqpQZWfbaOt4aHEidL+20umF1M7eXoeizr3XHHQsTPCvumJyMohQLo4wyym/hD7GDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8397d5ad9eca8867ed2a2edd822fec5f5277fa5acaa79cc383fc831063ca7a77","last_reissued_at":"2026-07-05T12:02:01.014331Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:01.014331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimizing LLMs for Resource-Constrained Environments: A Survey of Model Compression Techniques","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Aman Raj, Ankit Shetgaonkar, Dipen Pradhan, Lakshit Arora, Sanjay Surendranath Girija, Shashank Kapoor","submitted_at":"2025-05-05T01:27:47Z","abstract_excerpt":"Large Language Models (LLMs) have revolutionized many areas of artificial intelligence (AI), but their substantial resource requirements limit their deployment on mobile and edge devices. This survey paper provides a comprehensive overview of techniques for compressing LLMs to enable efficient inference in resource-constrained environments. We examine three primary approaches: Knowledge Distillation, Model Quantization, and Model Pruning. For each technique, we discuss the underlying principles, present different variants, and provide examples of successful applications. We also briefly discus"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02309","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/2505.02309/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":"2505.02309","created_at":"2026-07-05T12:02:01.014395+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.02309v2","created_at":"2026-07-05T12:02:01.014395+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02309","created_at":"2026-07-05T12:02:01.014395+00:00"},{"alias_kind":"pith_short_12","alias_value":"QOL5LLM6ZKEG","created_at":"2026-07-05T12:02:01.014395+00:00"},{"alias_kind":"pith_short_16","alias_value":"QOL5LLM6ZKEGP3JK","created_at":"2026-07-05T12:02:01.014395+00:00"},{"alias_kind":"pith_short_8","alias_value":"QOL5LLM6","created_at":"2026-07-05T12:02:01.014395+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.04534","citing_title":"Quantized Large Language Models in Biomedical Natural Language Processing: Evaluation and Recommendation","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QOL5LLM6ZKEGP3JKF3OYEL7ML5","json":"https://pith.science/pith/QOL5LLM6ZKEGP3JKF3OYEL7ML5.json","graph_json":"https://pith.science/api/pith-number/QOL5LLM6ZKEGP3JKF3OYEL7ML5/graph.json","events_json":"https://pith.science/api/pith-number/QOL5LLM6ZKEGP3JKF3OYEL7ML5/events.json","paper":"https://pith.science/paper/QOL5LLM6"},"agent_actions":{"view_html":"https://pith.science/pith/QOL5LLM6ZKEGP3JKF3OYEL7ML5","download_json":"https://pith.science/pith/QOL5LLM6ZKEGP3JKF3OYEL7ML5.json","view_paper":"https://pith.science/paper/QOL5LLM6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.02309&json=true","fetch_graph":"https://pith.science/api/pith-number/QOL5LLM6ZKEGP3JKF3OYEL7ML5/graph.json","fetch_events":"https://pith.science/api/pith-number/QOL5LLM6ZKEGP3JKF3OYEL7ML5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QOL5LLM6ZKEGP3JKF3OYEL7ML5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QOL5LLM6ZKEGP3JKF3OYEL7ML5/action/storage_attestation","attest_author":"https://pith.science/pith/QOL5LLM6ZKEGP3JKF3OYEL7ML5/action/author_attestation","sign_citation":"https://pith.science/pith/QOL5LLM6ZKEGP3JKF3OYEL7ML5/action/citation_signature","submit_replication":"https://pith.science/pith/QOL5LLM6ZKEGP3JKF3OYEL7ML5/action/replication_record"}},"created_at":"2026-07-05T12:02:01.014395+00:00","updated_at":"2026-07-05T12:02:01.014395+00:00"}