{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DEMRO4AR7LZ77SEIX6D6NFZTGS","short_pith_number":"pith:DEMRO4AR","schema_version":"1.0","canonical_sha256":"1919177011faf3ffc888bf87e6973334951bb5f0c8e1e5e208af8934f5afc9b8","source":{"kind":"arxiv","id":"2505.12216","version":2},"attestation_state":"computed","paper":{"title":"One-for-All Pruning: A Universal Model for Customized Compression of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ming Tang, Rongguang Ye","submitted_at":"2025-05-18T03:26:07Z","abstract_excerpt":"Existing pruning methods for large language models (LLMs) focus on achieving high compression rates while maintaining model performance. Although these methods have demonstrated satisfactory performance in handling a single user's compression request, their processing time increases linearly with the number of requests, making them inefficient for real-world scenarios with multiple simultaneous requests. To address this limitation, we propose a Univeral Model for Customized Compression (UniCuCo) for LLMs, which introduces a StratNet that learns to map arbitrary requests to their optimal prunin"},"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":"2505.12216","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-18T03:26:07Z","cross_cats_sorted":[],"title_canon_sha256":"235bd784f0e4369bace1e304c89f8d6df1bd45596eb640c438feddefab11bcad","abstract_canon_sha256":"a35dbbb8a37b34d46c28be352d7d25c9f546bbc2f0f6299597737cf79627944c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:13.678265Z","signature_b64":"oTewWo4HZR1W/SuHEVb8e6hIR40p9HNUdJ8QFh+qtf2c9gW934mreVeqaASHxC7kbmHnqaUdfK68aj9+mqXuAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1919177011faf3ffc888bf87e6973334951bb5f0c8e1e5e208af8934f5afc9b8","last_reissued_at":"2026-07-05T11:09:13.677748Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:13.677748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One-for-All Pruning: A Universal Model for Customized Compression of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ming Tang, Rongguang Ye","submitted_at":"2025-05-18T03:26:07Z","abstract_excerpt":"Existing pruning methods for large language models (LLMs) focus on achieving high compression rates while maintaining model performance. Although these methods have demonstrated satisfactory performance in handling a single user's compression request, their processing time increases linearly with the number of requests, making them inefficient for real-world scenarios with multiple simultaneous requests. To address this limitation, we propose a Univeral Model for Customized Compression (UniCuCo) for LLMs, which introduces a StratNet that learns to map arbitrary requests to their optimal prunin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12216","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/2505.12216/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":"2505.12216","created_at":"2026-07-05T11:09:13.677808+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.12216v2","created_at":"2026-07-05T11:09:13.677808+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12216","created_at":"2026-07-05T11:09:13.677808+00:00"},{"alias_kind":"pith_short_12","alias_value":"DEMRO4AR7LZ7","created_at":"2026-07-05T11:09:13.677808+00:00"},{"alias_kind":"pith_short_16","alias_value":"DEMRO4AR7LZ77SEI","created_at":"2026-07-05T11:09:13.677808+00:00"},{"alias_kind":"pith_short_8","alias_value":"DEMRO4AR","created_at":"2026-07-05T11:09:13.677808+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/DEMRO4AR7LZ77SEIX6D6NFZTGS","json":"https://pith.science/pith/DEMRO4AR7LZ77SEIX6D6NFZTGS.json","graph_json":"https://pith.science/api/pith-number/DEMRO4AR7LZ77SEIX6D6NFZTGS/graph.json","events_json":"https://pith.science/api/pith-number/DEMRO4AR7LZ77SEIX6D6NFZTGS/events.json","paper":"https://pith.science/paper/DEMRO4AR"},"agent_actions":{"view_html":"https://pith.science/pith/DEMRO4AR7LZ77SEIX6D6NFZTGS","download_json":"https://pith.science/pith/DEMRO4AR7LZ77SEIX6D6NFZTGS.json","view_paper":"https://pith.science/paper/DEMRO4AR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.12216&json=true","fetch_graph":"https://pith.science/api/pith-number/DEMRO4AR7LZ77SEIX6D6NFZTGS/graph.json","fetch_events":"https://pith.science/api/pith-number/DEMRO4AR7LZ77SEIX6D6NFZTGS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DEMRO4AR7LZ77SEIX6D6NFZTGS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DEMRO4AR7LZ77SEIX6D6NFZTGS/action/storage_attestation","attest_author":"https://pith.science/pith/DEMRO4AR7LZ77SEIX6D6NFZTGS/action/author_attestation","sign_citation":"https://pith.science/pith/DEMRO4AR7LZ77SEIX6D6NFZTGS/action/citation_signature","submit_replication":"https://pith.science/pith/DEMRO4AR7LZ77SEIX6D6NFZTGS/action/replication_record"}},"created_at":"2026-07-05T11:09:13.677808+00:00","updated_at":"2026-07-05T11:09:13.677808+00:00"}