{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FSXMTANUZCWIPVZF5HNSS5GUVS","short_pith_number":"pith:FSXMTANU","schema_version":"1.0","canonical_sha256":"2caec981b4c8ac87d725e9db2974d4ac9a42577c1066bbbe73dd33422ce2d291","source":{"kind":"arxiv","id":"2602.14649","version":2},"attestation_state":"computed","paper":{"title":"GradMAP: Faster Layer Pruning with Gradient Metric and Projection Compensation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guangyan Li, Hao Liu, Wensheng Zhang, Yongqiang Tang","submitted_at":"2026-02-16T11:14:02Z","abstract_excerpt":"Large Language Models (LLMs) exhibit strong reasoning abilities, but their high computational costs limit their practical deployment. Recent studies reveal significant redundancy in LLMs layers, making layer pruning an active research topic. Layer pruning research primarily focuses on two aspects: measuring layer importance and recovering performance after pruning. Unfortunately, the present works fail to simultaneously maintain pruning performance and efficiency. In this study, we propose GradMAP, a faster layer pruning method with \\textbf{Grad}ient \\textbf{M}etric \\textbf{A}nd \\textbf{P}roje"},"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":"2602.14649","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-02-16T11:14:02Z","cross_cats_sorted":[],"title_canon_sha256":"149f55a0269d8966d9934474af144c88cd91a64556d243c7303dd916a6cac311","abstract_canon_sha256":"5de42744a17d098b46d2003c5134032dc455c8da80c7dd09df9ccabaa5a0d7a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2caec981b4c8ac87d725e9db2974d4ac9a42577c1066bbbe73dd33422ce2d291","last_reissued_at":"2026-07-31T01:33:16.563940Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:33:16.563940Z"},"graph_snapshot":{"paper":{"title":"GradMAP: Faster Layer Pruning with Gradient Metric and Projection Compensation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guangyan Li, Hao Liu, Wensheng Zhang, Yongqiang Tang","submitted_at":"2026-02-16T11:14:02Z","abstract_excerpt":"Large Language Models (LLMs) exhibit strong reasoning abilities, but their high computational costs limit their practical deployment. Recent studies reveal significant redundancy in LLMs layers, making layer pruning an active research topic. Layer pruning research primarily focuses on two aspects: measuring layer importance and recovering performance after pruning. Unfortunately, the present works fail to simultaneously maintain pruning performance and efficiency. In this study, we propose GradMAP, a faster layer pruning method with \\textbf{Grad}ient \\textbf{M}etric \\textbf{A}nd \\textbf{P}roje"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.14649","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/2602.14649/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":"2602.14649","created_at":"2026-07-31T01:33:16.567011+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.14649v2","created_at":"2026-07-31T01:33:16.567011+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.14649","created_at":"2026-07-31T01:33:16.567011+00:00"},{"alias_kind":"pith_short_12","alias_value":"FSXMTANUZCWI","created_at":"2026-07-31T01:33:16.567011+00:00"},{"alias_kind":"pith_short_16","alias_value":"FSXMTANUZCWIPVZF","created_at":"2026-07-31T01:33:16.567011+00:00"},{"alias_kind":"pith_short_8","alias_value":"FSXMTANU","created_at":"2026-07-31T01:33:16.567011+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/FSXMTANUZCWIPVZF5HNSS5GUVS","json":"https://pith.science/pith/FSXMTANUZCWIPVZF5HNSS5GUVS.json","graph_json":"https://pith.science/api/pith-number/FSXMTANUZCWIPVZF5HNSS5GUVS/graph.json","events_json":"https://pith.science/api/pith-number/FSXMTANUZCWIPVZF5HNSS5GUVS/events.json","paper":"https://pith.science/paper/FSXMTANU"},"agent_actions":{"view_html":"https://pith.science/pith/FSXMTANUZCWIPVZF5HNSS5GUVS","download_json":"https://pith.science/pith/FSXMTANUZCWIPVZF5HNSS5GUVS.json","view_paper":"https://pith.science/paper/FSXMTANU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.14649&json=true","fetch_graph":"https://pith.science/api/pith-number/FSXMTANUZCWIPVZF5HNSS5GUVS/graph.json","fetch_events":"https://pith.science/api/pith-number/FSXMTANUZCWIPVZF5HNSS5GUVS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FSXMTANUZCWIPVZF5HNSS5GUVS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FSXMTANUZCWIPVZF5HNSS5GUVS/action/storage_attestation","attest_author":"https://pith.science/pith/FSXMTANUZCWIPVZF5HNSS5GUVS/action/author_attestation","sign_citation":"https://pith.science/pith/FSXMTANUZCWIPVZF5HNSS5GUVS/action/citation_signature","submit_replication":"https://pith.science/pith/FSXMTANUZCWIPVZF5HNSS5GUVS/action/replication_record"}},"created_at":"2026-07-31T01:33:16.567011+00:00","updated_at":"2026-07-31T01:33:16.567011+00:00"}