{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7VHYZGUTQJDKFZLDXWC34J3G2H","short_pith_number":"pith:7VHYZGUT","schema_version":"1.0","canonical_sha256":"fd4f8c9a938246a2e563bd85be2766d1e08571d1264d178c4a686acff3bcdec6","source":{"kind":"arxiv","id":"2509.01190","version":2},"attestation_state":"computed","paper":{"title":"Efficient Large Language Models with Zero-Shot Adjustable Acceleration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mohammad Sharifkhani, Sajjad Kachuee","submitted_at":"2025-09-01T07:15:25Z","abstract_excerpt":"Using Large Language Models (LLMs) in real-world applications presents significant challenges, particularly in balancing computational efficiency with model performance. Optimizing acceleration after fine-tuning and during inference is critical for building efficient architectures. This paper introduces Zero-Shot Adjustable Acceleration, a novel training and inference method that dynamically adjusts hardware utilization during inference without requiring additional fine-tuning. The proposed approach is applied to recent LLMs and evaluated across multiple classification and text generation task"},"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":"2509.01190","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-01T07:15:25Z","cross_cats_sorted":[],"title_canon_sha256":"41e38d028bb6837f9df4ca759e96905ffceb9961f55537fc9ace069b796e1a32","abstract_canon_sha256":"8d6b6c2864c8d88b56a297952f80967256f1f4e55ff80d92a5ce500e12e245e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:19.507441Z","signature_b64":"I5bAcJt3VbnX75BLB+BQSNHv5PwpbFCl8y3lq0OQxclrclsZdSbgGZ71wVxuoW7SESeFQxA2wmJ3MzD6b1dQAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd4f8c9a938246a2e563bd85be2766d1e08571d1264d178c4a686acff3bcdec6","last_reissued_at":"2026-07-05T12:06:19.506931Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:19.506931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Large Language Models with Zero-Shot Adjustable Acceleration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mohammad Sharifkhani, Sajjad Kachuee","submitted_at":"2025-09-01T07:15:25Z","abstract_excerpt":"Using Large Language Models (LLMs) in real-world applications presents significant challenges, particularly in balancing computational efficiency with model performance. Optimizing acceleration after fine-tuning and during inference is critical for building efficient architectures. This paper introduces Zero-Shot Adjustable Acceleration, a novel training and inference method that dynamically adjusts hardware utilization during inference without requiring additional fine-tuning. The proposed approach is applied to recent LLMs and evaluated across multiple classification and text generation task"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.01190","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/2509.01190/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":"2509.01190","created_at":"2026-07-05T12:06:19.506998+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.01190v2","created_at":"2026-07-05T12:06:19.506998+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.01190","created_at":"2026-07-05T12:06:19.506998+00:00"},{"alias_kind":"pith_short_12","alias_value":"7VHYZGUTQJDK","created_at":"2026-07-05T12:06:19.506998+00:00"},{"alias_kind":"pith_short_16","alias_value":"7VHYZGUTQJDKFZLD","created_at":"2026-07-05T12:06:19.506998+00:00"},{"alias_kind":"pith_short_8","alias_value":"7VHYZGUT","created_at":"2026-07-05T12:06:19.506998+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/7VHYZGUTQJDKFZLDXWC34J3G2H","json":"https://pith.science/pith/7VHYZGUTQJDKFZLDXWC34J3G2H.json","graph_json":"https://pith.science/api/pith-number/7VHYZGUTQJDKFZLDXWC34J3G2H/graph.json","events_json":"https://pith.science/api/pith-number/7VHYZGUTQJDKFZLDXWC34J3G2H/events.json","paper":"https://pith.science/paper/7VHYZGUT"},"agent_actions":{"view_html":"https://pith.science/pith/7VHYZGUTQJDKFZLDXWC34J3G2H","download_json":"https://pith.science/pith/7VHYZGUTQJDKFZLDXWC34J3G2H.json","view_paper":"https://pith.science/paper/7VHYZGUT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.01190&json=true","fetch_graph":"https://pith.science/api/pith-number/7VHYZGUTQJDKFZLDXWC34J3G2H/graph.json","fetch_events":"https://pith.science/api/pith-number/7VHYZGUTQJDKFZLDXWC34J3G2H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7VHYZGUTQJDKFZLDXWC34J3G2H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7VHYZGUTQJDKFZLDXWC34J3G2H/action/storage_attestation","attest_author":"https://pith.science/pith/7VHYZGUTQJDKFZLDXWC34J3G2H/action/author_attestation","sign_citation":"https://pith.science/pith/7VHYZGUTQJDKFZLDXWC34J3G2H/action/citation_signature","submit_replication":"https://pith.science/pith/7VHYZGUTQJDKFZLDXWC34J3G2H/action/replication_record"}},"created_at":"2026-07-05T12:06:19.506998+00:00","updated_at":"2026-07-05T12:06:19.506998+00:00"}