{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:FSXMTANUZCWIPVZF5HNSS5GUVS","short_pith_number":"pith:FSXMTANU","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"},"canonical_sha256":"2caec981b4c8ac87d725e9db2974d4ac9a42577c1066bbbe73dd33422ce2d291","source":{"kind":"arxiv","id":"2602.14649","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.14649","created_at":"2026-07-31T01:33:16Z"},{"alias_kind":"arxiv_version","alias_value":"2602.14649v2","created_at":"2026-07-31T01:33:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.14649","created_at":"2026-07-31T01:33:16Z"},{"alias_kind":"pith_short_12","alias_value":"FSXMTANUZCWI","created_at":"2026-07-31T01:33:16Z"},{"alias_kind":"pith_short_16","alias_value":"FSXMTANUZCWIPVZF","created_at":"2026-07-31T01:33:16Z"},{"alias_kind":"pith_short_8","alias_value":"FSXMTANU","created_at":"2026-07-31T01:33:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:FSXMTANUZCWIPVZF5HNSS5GUVS","target":"record","payload":{"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"},"canonical_sha256":"2caec981b4c8ac87d725e9db2974d4ac9a42577c1066bbbe73dd33422ce2d291","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"},"source_kind":"arxiv","source_id":"2602.14649","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-31T01:33:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4InR7DFgu0TJh2A8jZjwT+23yTNCIOSfbKLKssow3ElLgIYWYhk0u/n1mOUdMB+wx2fpQfFV4SJnHcdyKQ3xBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T14:45:37.821829Z"},"content_sha256":"ab97cd9c03815b0aefb9b9a80c116258d8255431acebe56276c1a13a2a971e68","schema_version":"1.0","event_id":"sha256:ab97cd9c03815b0aefb9b9a80c116258d8255431acebe56276c1a13a2a971e68"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:FSXMTANUZCWIPVZF5HNSS5GUVS","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-31T01:33:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HI7bxKe3VVNFE2xHLD8MkzfBYC1XywF20ENcYc6SIRLJnRq6QoAOiS0fkka4aJjajtjj0277I5kl5CxebDuhAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T14:45:37.822843Z"},"content_sha256":"5a24a7ca0a6aa24569d916984fb9adcafb14b88cc15781368673e53be83bc1f0","schema_version":"1.0","event_id":"sha256:5a24a7ca0a6aa24569d916984fb9adcafb14b88cc15781368673e53be83bc1f0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FSXMTANUZCWIPVZF5HNSS5GUVS/bundle.json","state_url":"https://pith.science/pith/FSXMTANUZCWIPVZF5HNSS5GUVS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FSXMTANUZCWIPVZF5HNSS5GUVS/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T14:45:37Z","links":{"resolver":"https://pith.science/pith/FSXMTANUZCWIPVZF5HNSS5GUVS","bundle":"https://pith.science/pith/FSXMTANUZCWIPVZF5HNSS5GUVS/bundle.json","state":"https://pith.science/pith/FSXMTANUZCWIPVZF5HNSS5GUVS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FSXMTANUZCWIPVZF5HNSS5GUVS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FSXMTANUZCWIPVZF5HNSS5GUVS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5de42744a17d098b46d2003c5134032dc455c8da80c7dd09df9ccabaa5a0d7a9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-02-16T11:14:02Z","title_canon_sha256":"149f55a0269d8966d9934474af144c88cd91a64556d243c7303dd916a6cac311"},"schema_version":"1.0","source":{"id":"2602.14649","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.14649","created_at":"2026-07-31T01:33:16Z"},{"alias_kind":"arxiv_version","alias_value":"2602.14649v2","created_at":"2026-07-31T01:33:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.14649","created_at":"2026-07-31T01:33:16Z"},{"alias_kind":"pith_short_12","alias_value":"FSXMTANUZCWI","created_at":"2026-07-31T01:33:16Z"},{"alias_kind":"pith_short_16","alias_value":"FSXMTANUZCWIPVZF","created_at":"2026-07-31T01:33:16Z"},{"alias_kind":"pith_short_8","alias_value":"FSXMTANU","created_at":"2026-07-31T01:33:16Z"}],"graph_snapshots":[{"event_id":"sha256:5a24a7ca0a6aa24569d916984fb9adcafb14b88cc15781368673e53be83bc1f0","target":"graph","created_at":"2026-07-31T01:33:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2602.14649/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Guangyan Li, Hao Liu, Wensheng Zhang, Yongqiang Tang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-02-16T11:14:02Z","title":"GradMAP: Faster Layer Pruning with Gradient Metric and Projection Compensation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.14649","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ab97cd9c03815b0aefb9b9a80c116258d8255431acebe56276c1a13a2a971e68","target":"record","created_at":"2026-07-31T01:33:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5de42744a17d098b46d2003c5134032dc455c8da80c7dd09df9ccabaa5a0d7a9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-02-16T11:14:02Z","title_canon_sha256":"149f55a0269d8966d9934474af144c88cd91a64556d243c7303dd916a6cac311"},"schema_version":"1.0","source":{"id":"2602.14649","kind":"arxiv","version":2}},"canonical_sha256":"2caec981b4c8ac87d725e9db2974d4ac9a42577c1066bbbe73dd33422ce2d291","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2caec981b4c8ac87d725e9db2974d4ac9a42577c1066bbbe73dd33422ce2d291","first_computed_at":"2026-07-31T01:33:16.563940Z","kind":"pith_receipt","last_reissued_at":"2026-07-31T01:33:16.563940Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2602.14649","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab97cd9c03815b0aefb9b9a80c116258d8255431acebe56276c1a13a2a971e68","sha256:5a24a7ca0a6aa24569d916984fb9adcafb14b88cc15781368673e53be83bc1f0"],"state_sha256":"baa213c5fdb7e4f73a60c10ac99f9e32319e482aea4089f785b44a6ae2536ce4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gGglhtxRkmp9MbX/LYBMXf/7sbN1Zh05cL6aphyLDH2FogcICETvYY5YK+EIy4UvU7+y01EKK+O3UDkXqO56DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T14:45:37.828486Z","bundle_sha256":"92c2301e6d78d00dea701848ceb581ea768485e99d954057e30cdb31d504b52b"}}