{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:6FER66X3TGONUAO33J23FFRSFL","short_pith_number":"pith:6FER66X3","canonical_record":{"source":{"id":"2506.02561","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T07:47:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"949e4e03a56735bc60bfbde570a0bd55dae774218687ff90396a0e5d0b8380bb","abstract_canon_sha256":"1468a1190d0de043a0ad431ca331e7a831035fbef65e6140994fe8e38877171d"},"schema_version":"1.0"},"canonical_sha256":"f1491f7afb999cda01dbda75b296322ad8a6571b30178701b7b38bd809e9494d","source":{"kind":"arxiv","id":"2506.02561","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02561","created_at":"2026-07-05T11:15:04Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02561v1","created_at":"2026-07-05T11:15:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02561","created_at":"2026-07-05T11:15:04Z"},{"alias_kind":"pith_short_12","alias_value":"6FER66X3TGON","created_at":"2026-07-05T11:15:04Z"},{"alias_kind":"pith_short_16","alias_value":"6FER66X3TGONUAO3","created_at":"2026-07-05T11:15:04Z"},{"alias_kind":"pith_short_8","alias_value":"6FER66X3","created_at":"2026-07-05T11:15:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:6FER66X3TGONUAO33J23FFRSFL","target":"record","payload":{"canonical_record":{"source":{"id":"2506.02561","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T07:47:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"949e4e03a56735bc60bfbde570a0bd55dae774218687ff90396a0e5d0b8380bb","abstract_canon_sha256":"1468a1190d0de043a0ad431ca331e7a831035fbef65e6140994fe8e38877171d"},"schema_version":"1.0"},"canonical_sha256":"f1491f7afb999cda01dbda75b296322ad8a6571b30178701b7b38bd809e9494d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:04.218190Z","signature_b64":"oUvFL8IoNUIBLaqBPizqfU28S9Q3aCn60dlAo9W8W2WoQLziT3gZJZHD1zK3r1+MzoROkeC0BosQibZ0Gz2LAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1491f7afb999cda01dbda75b296322ad8a6571b30178701b7b38bd809e9494d","last_reissued_at":"2026-07-05T11:15:04.217595Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:04.217595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.02561","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":"2026-07-05T11:15:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WEHdzcmXmgkhhS6djypKBDf5aCmdkxsQ/FROJoi10o4Z8d0+xeKwBQRgJ6I//C9eTU5PKG+GkiNBaB69xq0HDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:32:25.821159Z"},"content_sha256":"913f59c7578f37c9267ad46ad93cda510661a037f36848aea2b3970f6e1af44e","schema_version":"1.0","event_id":"sha256:913f59c7578f37c9267ad46ad93cda510661a037f36848aea2b3970f6e1af44e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:6FER66X3TGONUAO33J23FFRSFL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pruning General Large Language Models into Customized Expert Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Guizhen Chen, Kenji Kawaguchi, Lidong Bing, Wenxuan Zhang, Yirao Zhao","submitted_at":"2025-06-03T07:47:30Z","abstract_excerpt":"Large language models (LLMs) have revolutionized natural language processing, yet their substantial model sizes often require substantial computational resources. To preserve computing resources and accelerate inference speed, it is crucial to prune redundant parameters, especially for experienced users who often need compact expert models tailored to specific downstream scenarios. However, most existing pruning methods focus on preserving the model's general capabilities, often requiring extensive post-training or suffering from degraded performance due to coarse-grained pruning. In this work"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02561","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/2506.02561/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":"2026-07-05T11:15:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rc4KbPYrrh525HIKiWC7K8kC4Nwa8fc/PjsTchpOt9fl/c3HxtVUOfMo5aPCgIhQS2H1MQI5BR26YeoapDXTAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:32:25.824992Z"},"content_sha256":"28501ac7129ff00c864af297ab2dff2d48744bb4f9310145e56cb9004e650390","schema_version":"1.0","event_id":"sha256:28501ac7129ff00c864af297ab2dff2d48744bb4f9310145e56cb9004e650390"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6FER66X3TGONUAO33J23FFRSFL/bundle.json","state_url":"https://pith.science/pith/6FER66X3TGONUAO33J23FFRSFL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6FER66X3TGONUAO33J23FFRSFL/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":"2026-08-05T06:32:25Z","links":{"resolver":"https://pith.science/pith/6FER66X3TGONUAO33J23FFRSFL","bundle":"https://pith.science/pith/6FER66X3TGONUAO33J23FFRSFL/bundle.json","state":"https://pith.science/pith/6FER66X3TGONUAO33J23FFRSFL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6FER66X3TGONUAO33J23FFRSFL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6FER66X3TGONUAO33J23FFRSFL","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":"1468a1190d0de043a0ad431ca331e7a831035fbef65e6140994fe8e38877171d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T07:47:30Z","title_canon_sha256":"949e4e03a56735bc60bfbde570a0bd55dae774218687ff90396a0e5d0b8380bb"},"schema_version":"1.0","source":{"id":"2506.02561","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02561","created_at":"2026-07-05T11:15:04Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02561v1","created_at":"2026-07-05T11:15:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02561","created_at":"2026-07-05T11:15:04Z"},{"alias_kind":"pith_short_12","alias_value":"6FER66X3TGON","created_at":"2026-07-05T11:15:04Z"},{"alias_kind":"pith_short_16","alias_value":"6FER66X3TGONUAO3","created_at":"2026-07-05T11:15:04Z"},{"alias_kind":"pith_short_8","alias_value":"6FER66X3","created_at":"2026-07-05T11:15:04Z"}],"graph_snapshots":[{"event_id":"sha256:28501ac7129ff00c864af297ab2dff2d48744bb4f9310145e56cb9004e650390","target":"graph","created_at":"2026-07-05T11:15:04Z","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/2506.02561/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have revolutionized natural language processing, yet their substantial model sizes often require substantial computational resources. To preserve computing resources and accelerate inference speed, it is crucial to prune redundant parameters, especially for experienced users who often need compact expert models tailored to specific downstream scenarios. However, most existing pruning methods focus on preserving the model's general capabilities, often requiring extensive post-training or suffering from degraded performance due to coarse-grained pruning. In this work","authors_text":"Guizhen Chen, Kenji Kawaguchi, Lidong Bing, Wenxuan Zhang, Yirao Zhao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T07:47:30Z","title":"Pruning General Large Language Models into Customized Expert Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02561","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":"sha256:913f59c7578f37c9267ad46ad93cda510661a037f36848aea2b3970f6e1af44e","target":"record","created_at":"2026-07-05T11:15:04Z","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":"1468a1190d0de043a0ad431ca331e7a831035fbef65e6140994fe8e38877171d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T07:47:30Z","title_canon_sha256":"949e4e03a56735bc60bfbde570a0bd55dae774218687ff90396a0e5d0b8380bb"},"schema_version":"1.0","source":{"id":"2506.02561","kind":"arxiv","version":1}},"canonical_sha256":"f1491f7afb999cda01dbda75b296322ad8a6571b30178701b7b38bd809e9494d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f1491f7afb999cda01dbda75b296322ad8a6571b30178701b7b38bd809e9494d","first_computed_at":"2026-07-05T11:15:04.217595Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:04.217595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oUvFL8IoNUIBLaqBPizqfU28S9Q3aCn60dlAo9W8W2WoQLziT3gZJZHD1zK3r1+MzoROkeC0BosQibZ0Gz2LAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:04.218190Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.02561","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:913f59c7578f37c9267ad46ad93cda510661a037f36848aea2b3970f6e1af44e","sha256:28501ac7129ff00c864af297ab2dff2d48744bb4f9310145e56cb9004e650390"],"state_sha256":"6429b6165d7821c7031c6b808f5485170b7851b2144c112f51996902d6384e43"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VKddud0grw6VF6OEPoyqOyFb0m84z93JXpKdhQtnxRlQIFgZlEYH89jwVRWiZ0FhjHVXSfusBr/jCcRQ+WftBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T06:32:25.879175Z","bundle_sha256":"e939570d8df453993e51e210d4cffc16a1192dd644f74edfe96a210d59fe003f"}}