{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CHGU24OWAT36YUGVWSFJCAYPU6","short_pith_number":"pith:CHGU24OW","canonical_record":{"source":{"id":"2506.04179","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T17:26:31Z","cross_cats_sorted":[],"title_canon_sha256":"958cc40c8c16a9ab18dcf7fe3432b627a4adddc8403ed6e67757400e7e7e7211","abstract_canon_sha256":"af310bd2f3b19f580ea3773c68a9251713b251bc62331b5ac8f16a6c06b95d42"},"schema_version":"1.0"},"canonical_sha256":"11cd4d71d604f7ec50d5b48a91030fa7bcc84a3e5be919279c0750c9d1c34e85","source":{"kind":"arxiv","id":"2506.04179","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04179","created_at":"2026-07-05T11:15:58Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04179v1","created_at":"2026-07-05T11:15:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04179","created_at":"2026-07-05T11:15:58Z"},{"alias_kind":"pith_short_12","alias_value":"CHGU24OWAT36","created_at":"2026-07-05T11:15:58Z"},{"alias_kind":"pith_short_16","alias_value":"CHGU24OWAT36YUGV","created_at":"2026-07-05T11:15:58Z"},{"alias_kind":"pith_short_8","alias_value":"CHGU24OW","created_at":"2026-07-05T11:15:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CHGU24OWAT36YUGVWSFJCAYPU6","target":"record","payload":{"canonical_record":{"source":{"id":"2506.04179","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T17:26:31Z","cross_cats_sorted":[],"title_canon_sha256":"958cc40c8c16a9ab18dcf7fe3432b627a4adddc8403ed6e67757400e7e7e7211","abstract_canon_sha256":"af310bd2f3b19f580ea3773c68a9251713b251bc62331b5ac8f16a6c06b95d42"},"schema_version":"1.0"},"canonical_sha256":"11cd4d71d604f7ec50d5b48a91030fa7bcc84a3e5be919279c0750c9d1c34e85","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:58.408148Z","signature_b64":"IxQGIkXwUQNHXwzVFu8+PD94NAp6ixSM1msT7SyNGFvMNcDInNH1syeN8aH2fxTDhKAAkrF5hmo9IaxaGYBABg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11cd4d71d604f7ec50d5b48a91030fa7bcc84a3e5be919279c0750c9d1c34e85","last_reissued_at":"2026-07-05T11:15:58.407735Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:58.407735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.04179","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:15:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RudZl9K3AQA70zBD9t0+Y+BTKt1G6oWQkAwucluCwFu78kXLgZMaJsFixtJVgXCpIONVqDxr8d/twvLoU7kGDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:20:50.383038Z"},"content_sha256":"141500d4e09922dfe3e6137696dd43c659370eec093a195002fa1cd191d58504","schema_version":"1.0","event_id":"sha256:141500d4e09922dfe3e6137696dd43c659370eec093a195002fa1cd191d58504"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CHGU24OWAT36YUGVWSFJCAYPU6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SkipGPT: Dynamic Layer Pruning Reinvented with Token Awareness and Module Decoupling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anhao Zhao, Fanghua Ye, Hui Su, Junlong Tong, Xiaoyu Shen, Yingqi Fan, Zhiwei Fei","submitted_at":"2025-06-04T17:26:31Z","abstract_excerpt":"Large language models (LLMs) achieve remarkable performance across tasks but incur substantial computational costs due to their deep, multi-layered architectures. Layer pruning has emerged as a strategy to alleviate these inefficiencies, but conventional static pruning methods overlook two critical dynamics inherent to LLM inference: (1) horizontal dynamics, where token-level heterogeneity demands context-aware pruning decisions, and (2) vertical dynamics, where the distinct functional roles of MLP and self-attention layers necessitate component-specific pruning policies. We introduce SkipGPT,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04179","kind":"arxiv","version":1},"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/2506.04179/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":"2026-07-05T11:15:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p5TrXM7s69Wtr23ZaHvdthLHZ8mI7BTA3hbzA9ZT5eRbhUs8OvKeOOeEWgWfXD5mt37D/y4Qy7hFQNOkvZEgDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:20:50.383642Z"},"content_sha256":"814eb0430f5aede0606bfb734ec773a9cb8db258ea00f9cd661e352a5a7bdc4e","schema_version":"1.0","event_id":"sha256:814eb0430f5aede0606bfb734ec773a9cb8db258ea00f9cd661e352a5a7bdc4e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CHGU24OWAT36YUGVWSFJCAYPU6/bundle.json","state_url":"https://pith.science/pith/CHGU24OWAT36YUGVWSFJCAYPU6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CHGU24OWAT36YUGVWSFJCAYPU6/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":"2026-08-06T05:20:50Z","links":{"resolver":"https://pith.science/pith/CHGU24OWAT36YUGVWSFJCAYPU6","bundle":"https://pith.science/pith/CHGU24OWAT36YUGVWSFJCAYPU6/bundle.json","state":"https://pith.science/pith/CHGU24OWAT36YUGVWSFJCAYPU6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CHGU24OWAT36YUGVWSFJCAYPU6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CHGU24OWAT36YUGVWSFJCAYPU6","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":"af310bd2f3b19f580ea3773c68a9251713b251bc62331b5ac8f16a6c06b95d42","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T17:26:31Z","title_canon_sha256":"958cc40c8c16a9ab18dcf7fe3432b627a4adddc8403ed6e67757400e7e7e7211"},"schema_version":"1.0","source":{"id":"2506.04179","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04179","created_at":"2026-07-05T11:15:58Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04179v1","created_at":"2026-07-05T11:15:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04179","created_at":"2026-07-05T11:15:58Z"},{"alias_kind":"pith_short_12","alias_value":"CHGU24OWAT36","created_at":"2026-07-05T11:15:58Z"},{"alias_kind":"pith_short_16","alias_value":"CHGU24OWAT36YUGV","created_at":"2026-07-05T11:15:58Z"},{"alias_kind":"pith_short_8","alias_value":"CHGU24OW","created_at":"2026-07-05T11:15:58Z"}],"graph_snapshots":[{"event_id":"sha256:814eb0430f5aede0606bfb734ec773a9cb8db258ea00f9cd661e352a5a7bdc4e","target":"graph","created_at":"2026-07-05T11:15:58Z","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/2506.04179/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) achieve remarkable performance across tasks but incur substantial computational costs due to their deep, multi-layered architectures. Layer pruning has emerged as a strategy to alleviate these inefficiencies, but conventional static pruning methods overlook two critical dynamics inherent to LLM inference: (1) horizontal dynamics, where token-level heterogeneity demands context-aware pruning decisions, and (2) vertical dynamics, where the distinct functional roles of MLP and self-attention layers necessitate component-specific pruning policies. We introduce SkipGPT,","authors_text":"Anhao Zhao, Fanghua Ye, Hui Su, Junlong Tong, Xiaoyu Shen, Yingqi Fan, Zhiwei Fei","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T17:26:31Z","title":"SkipGPT: Dynamic Layer Pruning Reinvented with Token Awareness and Module Decoupling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04179","kind":"arxiv","version":1},"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":"sha256:141500d4e09922dfe3e6137696dd43c659370eec093a195002fa1cd191d58504","target":"record","created_at":"2026-07-05T11:15:58Z","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":"af310bd2f3b19f580ea3773c68a9251713b251bc62331b5ac8f16a6c06b95d42","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T17:26:31Z","title_canon_sha256":"958cc40c8c16a9ab18dcf7fe3432b627a4adddc8403ed6e67757400e7e7e7211"},"schema_version":"1.0","source":{"id":"2506.04179","kind":"arxiv","version":1}},"canonical_sha256":"11cd4d71d604f7ec50d5b48a91030fa7bcc84a3e5be919279c0750c9d1c34e85","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"11cd4d71d604f7ec50d5b48a91030fa7bcc84a3e5be919279c0750c9d1c34e85","first_computed_at":"2026-07-05T11:15:58.407735Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:58.407735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IxQGIkXwUQNHXwzVFu8+PD94NAp6ixSM1msT7SyNGFvMNcDInNH1syeN8aH2fxTDhKAAkrF5hmo9IaxaGYBABg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:58.408148Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.04179","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:141500d4e09922dfe3e6137696dd43c659370eec093a195002fa1cd191d58504","sha256:814eb0430f5aede0606bfb734ec773a9cb8db258ea00f9cd661e352a5a7bdc4e"],"state_sha256":"3021f461e186f4b4468b8c7349dc79dc9333b2c1a978657385794ae561940646"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"csV5Lok3baY+dmsDXB5RPTdOQRjc+okR5P8e5QLjJ/Y3ESwqNbEBk8gtmwcomlNLSyHiIPZTAP2yIB2G/V45BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T05:20:50.388945Z","bundle_sha256":"35963e9283c7b8d7f1e707cf14bef08c1200189c5ae94f4253bf9c146de47e70"}}