{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:M7LYZ5JHGHOCPJRCVP3VZRNTXC","short_pith_number":"pith:M7LYZ5JH","canonical_record":{"source":{"id":"2405.18218","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T14:21:15Z","cross_cats_sorted":[],"title_canon_sha256":"52ba922db7b86905845672948ade761ffa33734fd8599960d5a2844f78d7d69c","abstract_canon_sha256":"6561f86e0654b2e86b4755077c170b33b9373883f99ad74683e48bcf9f542a84"},"schema_version":"1.0"},"canonical_sha256":"67d78cf52731dc27a622abf75cc5b3b8bc66daf2bbafbe7f13af6c873553232a","source":{"kind":"arxiv","id":"2405.18218","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.18218","created_at":"2026-07-05T09:23:06Z"},{"alias_kind":"arxiv_version","alias_value":"2405.18218v2","created_at":"2026-07-05T09:23:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18218","created_at":"2026-07-05T09:23:06Z"},{"alias_kind":"pith_short_12","alias_value":"M7LYZ5JHGHOC","created_at":"2026-07-05T09:23:06Z"},{"alias_kind":"pith_short_16","alias_value":"M7LYZ5JHGHOCPJRC","created_at":"2026-07-05T09:23:06Z"},{"alias_kind":"pith_short_8","alias_value":"M7LYZ5JH","created_at":"2026-07-05T09:23:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:M7LYZ5JHGHOCPJRCVP3VZRNTXC","target":"record","payload":{"canonical_record":{"source":{"id":"2405.18218","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T14:21:15Z","cross_cats_sorted":[],"title_canon_sha256":"52ba922db7b86905845672948ade761ffa33734fd8599960d5a2844f78d7d69c","abstract_canon_sha256":"6561f86e0654b2e86b4755077c170b33b9373883f99ad74683e48bcf9f542a84"},"schema_version":"1.0"},"canonical_sha256":"67d78cf52731dc27a622abf75cc5b3b8bc66daf2bbafbe7f13af6c873553232a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:06.207773Z","signature_b64":"cls0D2eHMTTyzjFz2ojg122ViX28P8ouQWKtykh3BTFZWSeAAPsgtxkHsp63ZCbdHLuZHm/AVVpT4ffarK3xCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67d78cf52731dc27a622abf75cc5b3b8bc66daf2bbafbe7f13af6c873553232a","last_reissued_at":"2026-07-05T09:23:06.207285Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:06.207285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.18218","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":"2026-07-05T09:23:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vr4p5uzw26SNQThg6rLhRvHeJ6csE134OtJ+U1NDsOXIsN/FMB7wRVe3bcgtYi2RWHgdAkzT1FhwG81RmnBNDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T22:21:58.208576Z"},"content_sha256":"73c3438b41f6a220aa126ab8bb7e54708bd0dab2683c73ecd192caabdea71719","schema_version":"1.0","event_id":"sha256:73c3438b41f6a220aa126ab8bb7e54708bd0dab2683c73ecd192caabdea71719"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:M7LYZ5JHGHOCPJRCVP3VZRNTXC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FinerCut: Finer-grained Interpretable Layer Pruning for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Barbara Plank, Bernd Bischl, Kenji Kawaguchi, Mina Rezaei, Qianli Shen, Xinpeng Wang, Yang Zhang, Yawei Li","submitted_at":"2024-05-28T14:21:15Z","abstract_excerpt":"Overparametrized transformer networks are the state-of-the-art architecture for Large Language Models (LLMs). However, such models contain billions of parameters making large compute a necessity, while raising environmental concerns. To address these issues, we propose FinerCut, a new form of fine-grained layer pruning, which in contrast to prior work at the transformer block level, considers all self-attention and feed-forward network (FFN) layers within blocks as individual pruning candidates. FinerCut prunes layers whose removal causes minimal alternation to the model's output -- contributi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18218","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/2405.18218/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":"2026-07-05T09:23:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yLWrgABoXZ2TSN9LYYsUjIK9FUhbixDtqOrO5AV582mSYeXM37WezIN5hM0+mN8et6mKzg+KWHcDRLKfEOf7Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T22:21:58.209087Z"},"content_sha256":"81c65c91995c84617e85ff784df33442cba31cad8a582d99064ba5594019ca7c","schema_version":"1.0","event_id":"sha256:81c65c91995c84617e85ff784df33442cba31cad8a582d99064ba5594019ca7c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M7LYZ5JHGHOCPJRCVP3VZRNTXC/bundle.json","state_url":"https://pith.science/pith/M7LYZ5JHGHOCPJRCVP3VZRNTXC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M7LYZ5JHGHOCPJRCVP3VZRNTXC/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":"2026-08-22T22:21:58Z","links":{"resolver":"https://pith.science/pith/M7LYZ5JHGHOCPJRCVP3VZRNTXC","bundle":"https://pith.science/pith/M7LYZ5JHGHOCPJRCVP3VZRNTXC/bundle.json","state":"https://pith.science/pith/M7LYZ5JHGHOCPJRCVP3VZRNTXC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M7LYZ5JHGHOCPJRCVP3VZRNTXC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:M7LYZ5JHGHOCPJRCVP3VZRNTXC","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":"6561f86e0654b2e86b4755077c170b33b9373883f99ad74683e48bcf9f542a84","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T14:21:15Z","title_canon_sha256":"52ba922db7b86905845672948ade761ffa33734fd8599960d5a2844f78d7d69c"},"schema_version":"1.0","source":{"id":"2405.18218","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.18218","created_at":"2026-07-05T09:23:06Z"},{"alias_kind":"arxiv_version","alias_value":"2405.18218v2","created_at":"2026-07-05T09:23:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18218","created_at":"2026-07-05T09:23:06Z"},{"alias_kind":"pith_short_12","alias_value":"M7LYZ5JHGHOC","created_at":"2026-07-05T09:23:06Z"},{"alias_kind":"pith_short_16","alias_value":"M7LYZ5JHGHOCPJRC","created_at":"2026-07-05T09:23:06Z"},{"alias_kind":"pith_short_8","alias_value":"M7LYZ5JH","created_at":"2026-07-05T09:23:06Z"}],"graph_snapshots":[{"event_id":"sha256:81c65c91995c84617e85ff784df33442cba31cad8a582d99064ba5594019ca7c","target":"graph","created_at":"2026-07-05T09:23:06Z","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/2405.18218/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Overparametrized transformer networks are the state-of-the-art architecture for Large Language Models (LLMs). However, such models contain billions of parameters making large compute a necessity, while raising environmental concerns. To address these issues, we propose FinerCut, a new form of fine-grained layer pruning, which in contrast to prior work at the transformer block level, considers all self-attention and feed-forward network (FFN) layers within blocks as individual pruning candidates. FinerCut prunes layers whose removal causes minimal alternation to the model's output -- contributi","authors_text":"Barbara Plank, Bernd Bischl, Kenji Kawaguchi, Mina Rezaei, Qianli Shen, Xinpeng Wang, Yang Zhang, Yawei Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T14:21:15Z","title":"FinerCut: Finer-grained Interpretable Layer Pruning for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18218","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":"sha256:73c3438b41f6a220aa126ab8bb7e54708bd0dab2683c73ecd192caabdea71719","target":"record","created_at":"2026-07-05T09:23:06Z","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":"6561f86e0654b2e86b4755077c170b33b9373883f99ad74683e48bcf9f542a84","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T14:21:15Z","title_canon_sha256":"52ba922db7b86905845672948ade761ffa33734fd8599960d5a2844f78d7d69c"},"schema_version":"1.0","source":{"id":"2405.18218","kind":"arxiv","version":2}},"canonical_sha256":"67d78cf52731dc27a622abf75cc5b3b8bc66daf2bbafbe7f13af6c873553232a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67d78cf52731dc27a622abf75cc5b3b8bc66daf2bbafbe7f13af6c873553232a","first_computed_at":"2026-07-05T09:23:06.207285Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:23:06.207285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cls0D2eHMTTyzjFz2ojg122ViX28P8ouQWKtykh3BTFZWSeAAPsgtxkHsp63ZCbdHLuZHm/AVVpT4ffarK3xCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:23:06.207773Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.18218","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73c3438b41f6a220aa126ab8bb7e54708bd0dab2683c73ecd192caabdea71719","sha256:81c65c91995c84617e85ff784df33442cba31cad8a582d99064ba5594019ca7c"],"state_sha256":"db442bc8d596c9eb2f4b39a334a5ac7406003b6590a362995954b5c7d910aeba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WARHr+nsC5vvpQCjQtGMttsY6GS5khg2TDMYjBmP8m45DQNvNdgHPceN0MoK5fRTsLK/UFublcgIlDxBut3JBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T22:21:58.213835Z","bundle_sha256":"48ea355324dd46430ec376932defa64d8e346136db6b46e592a2ee0a8f7ccc20"}}