{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OXRYN2TOQOYECO5M3HGTWP3DQL","short_pith_number":"pith:OXRYN2TO","schema_version":"1.0","canonical_sha256":"75e386ea6e83b0413bacd9cd3b3f6382e830d6c2bd36482b94a3b5f90829bd03","source":{"kind":"arxiv","id":"2603.23985","version":3},"attestation_state":"computed","paper":{"title":"Diet Your LLM: Dimension-wise Global Pruning of LLMs via Merging Task-specific Importance Score","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"DIET prunes LLM dimensions by merging per-task activation scores into one global mask without any training.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jaehyung Kim, Jimyung Hong","submitted_at":"2026-03-25T06:28:58Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable capabilities, but their massive scale poses significant challenges for practical deployment. Structured pruning offers a promising solution by removing entire dimensions or layers, yet existing methods face critical trade-offs: task-agnostic approaches cannot adapt to task-specific requirements, while task-aware methods require costly training to learn task adaptability. We propose DIET (Dimension-wise global pruning of LLMs via merging Task-wise importance scores), a training-free structured pruning method that combines dimension-level"},"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":true},"canonical_record":{"source":{"id":"2603.23985","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-25T06:28:58Z","cross_cats_sorted":[],"title_canon_sha256":"bb50e61da520dd9eb49619541867382880f6005196f6b1f634af04c91e99cee8","abstract_canon_sha256":"902a117a272fcd9238d3d408303513c06388bdfce6a2c2a3b59da6a271578778"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:53.465905Z","signature_b64":"XGFmHLEVWnaWtVR0vUTuXsK+KmGHP7HpueFZjUBVYixbLDDHOk2xobB7wDKBhM5f9Z8dvP1QbCt8ima/6rfGBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75e386ea6e83b0413bacd9cd3b3f6382e830d6c2bd36482b94a3b5f90829bd03","last_reissued_at":"2026-05-27T01:05:53.464958Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:53.464958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diet Your LLM: Dimension-wise Global Pruning of LLMs via Merging Task-specific Importance Score","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"DIET prunes LLM dimensions by merging per-task activation scores into one global mask without any training.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jaehyung Kim, Jimyung Hong","submitted_at":"2026-03-25T06:28:58Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable capabilities, but their massive scale poses significant challenges for practical deployment. Structured pruning offers a promising solution by removing entire dimensions or layers, yet existing methods face critical trade-offs: task-agnostic approaches cannot adapt to task-specific requirements, while task-aware methods require costly training to learn task adaptability. We propose DIET (Dimension-wise global pruning of LLMs via merging Task-wise importance scores), a training-free structured pruning method that combines dimension-level"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"at 20% sparsity on Gemma-2 2B, DIET achieves near 10% average accuracy improvement, compared to previous state-of-the-art structured pruning methods.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"that activation magnitudes computed from only 100 samples per task are sufficient to produce a reliable global importance ranking that generalizes across unseen tasks and inputs.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"DIET prunes LLMs dimension-wise by merging task-specific activation importance scores via majority voting on 100 samples per task, yielding up to 10% accuracy gains over prior structured methods at 20% sparsity on Gemma-2 models.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"DIET prunes LLM dimensions by merging per-task activation scores into one global mask without any training.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"80943eec44744cd9029eded8a210fdac1618d561f9e108b13974ec5b9a67f168"},"source":{"id":"2603.23985","kind":"arxiv","version":3},"verdict":{"id":"f9cd5a15-2fcb-495c-9242-b8b6cf769d9e","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T00:51:10.787003Z","strongest_claim":"at 20% sparsity on Gemma-2 2B, DIET achieves near 10% average accuracy improvement, compared to previous state-of-the-art structured pruning methods.","one_line_summary":"DIET prunes LLMs dimension-wise by merging task-specific activation importance scores via majority voting on 100 samples per task, yielding up to 10% accuracy gains over prior structured methods at 20% sparsity on Gemma-2 models.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"that activation magnitudes computed from only 100 samples per task are sufficient to produce a reliable global importance ranking that generalizes across unseen tasks and inputs.","pith_extraction_headline":"DIET prunes LLM dimensions by merging per-task activation scores into one global mask without any training."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.23985/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":2,"snapshot_sha256":"a189ac9aee3c7b82f5eb3e0bdce72037212b4b18be16d87e14f59cb4ef9734e1"},"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":"2603.23985","created_at":"2026-05-27T01:05:53.465101+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.23985v3","created_at":"2026-05-27T01:05:53.465101+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.23985","created_at":"2026-05-27T01:05:53.465101+00:00"},{"alias_kind":"pith_short_12","alias_value":"OXRYN2TOQOYE","created_at":"2026-05-27T01:05:53.465101+00:00"},{"alias_kind":"pith_short_16","alias_value":"OXRYN2TOQOYECO5M","created_at":"2026-05-27T01:05:53.465101+00:00"},{"alias_kind":"pith_short_8","alias_value":"OXRYN2TO","created_at":"2026-05-27T01:05:53.465101+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OXRYN2TOQOYECO5M3HGTWP3DQL","json":"https://pith.science/pith/OXRYN2TOQOYECO5M3HGTWP3DQL.json","graph_json":"https://pith.science/api/pith-number/OXRYN2TOQOYECO5M3HGTWP3DQL/graph.json","events_json":"https://pith.science/api/pith-number/OXRYN2TOQOYECO5M3HGTWP3DQL/events.json","paper":"https://pith.science/paper/OXRYN2TO"},"agent_actions":{"view_html":"https://pith.science/pith/OXRYN2TOQOYECO5M3HGTWP3DQL","download_json":"https://pith.science/pith/OXRYN2TOQOYECO5M3HGTWP3DQL.json","view_paper":"https://pith.science/paper/OXRYN2TO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.23985&json=true","fetch_graph":"https://pith.science/api/pith-number/OXRYN2TOQOYECO5M3HGTWP3DQL/graph.json","fetch_events":"https://pith.science/api/pith-number/OXRYN2TOQOYECO5M3HGTWP3DQL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OXRYN2TOQOYECO5M3HGTWP3DQL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OXRYN2TOQOYECO5M3HGTWP3DQL/action/storage_attestation","attest_author":"https://pith.science/pith/OXRYN2TOQOYECO5M3HGTWP3DQL/action/author_attestation","sign_citation":"https://pith.science/pith/OXRYN2TOQOYECO5M3HGTWP3DQL/action/citation_signature","submit_replication":"https://pith.science/pith/OXRYN2TOQOYECO5M3HGTWP3DQL/action/replication_record"}},"created_at":"2026-05-27T01:05:53.465101+00:00","updated_at":"2026-05-27T01:05:53.465101+00:00"}