{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RZJ6CRDZQOR62ELFWMVIF5EPGG","short_pith_number":"pith:RZJ6CRDZ","canonical_record":{"source":{"id":"2508.02128","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-04T07:22:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"19ee75c147a2f655993286a9ccf974abbf6261c5edc006cb14059e60976a7546","abstract_canon_sha256":"831ae7ccb242e20297f8f32d6509c2d24ef75fe4e425880c62acc592406007ac"},"schema_version":"1.0"},"canonical_sha256":"8e53e1447983a3ed1165b32a82f48f31a17f7aee904b8d3628ce6b5a8c244188","source":{"kind":"arxiv","id":"2508.02128","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.02128","created_at":"2026-07-05T11:48:08Z"},{"alias_kind":"arxiv_version","alias_value":"2508.02128v1","created_at":"2026-07-05T11:48:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.02128","created_at":"2026-07-05T11:48:08Z"},{"alias_kind":"pith_short_12","alias_value":"RZJ6CRDZQOR6","created_at":"2026-07-05T11:48:08Z"},{"alias_kind":"pith_short_16","alias_value":"RZJ6CRDZQOR62ELF","created_at":"2026-07-05T11:48:08Z"},{"alias_kind":"pith_short_8","alias_value":"RZJ6CRDZ","created_at":"2026-07-05T11:48:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RZJ6CRDZQOR62ELFWMVIF5EPGG","target":"record","payload":{"canonical_record":{"source":{"id":"2508.02128","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-04T07:22:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"19ee75c147a2f655993286a9ccf974abbf6261c5edc006cb14059e60976a7546","abstract_canon_sha256":"831ae7ccb242e20297f8f32d6509c2d24ef75fe4e425880c62acc592406007ac"},"schema_version":"1.0"},"canonical_sha256":"8e53e1447983a3ed1165b32a82f48f31a17f7aee904b8d3628ce6b5a8c244188","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:08.688748Z","signature_b64":"JylTa9Mo+8Ub8A1KNKD53DrKXchRaWAccQeTOFM7FSX2oWBPMmLwcWveFH4d8UsRxdDerfngthiB5cQYfnGlDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e53e1447983a3ed1165b32a82f48f31a17f7aee904b8d3628ce6b5a8c244188","last_reissued_at":"2026-07-05T11:48:08.688236Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:08.688236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.02128","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":"2026-07-05T11:48:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cpbEpxRUkClcDHdCibshXxwgSUz1NZoEM+VxEBgTYY5kdJl9aqOMmeVOPABa+SiX4NkLpXlEJEqXeHymuxuLBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T14:24:02.885298Z"},"content_sha256":"3fe41fa78d9a79539df7f74c08aa526da19262e52d405eaa81f50a98f03e8ab1","schema_version":"1.0","event_id":"sha256:3fe41fa78d9a79539df7f74c08aa526da19262e52d405eaa81f50a98f03e8ab1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RZJ6CRDZQOR62ELFWMVIF5EPGG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Amber Pruner: Leveraging N:M Activation Sparsity for Efficient Prefill in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Gongyi Wang, Hao Chen, Pengcheng Xie, Ruwu Cai, Sheng Chang, Tai An, Yang Liu, Yanzhe Zhang, Yiwu Yao","submitted_at":"2025-08-04T07:22:36Z","abstract_excerpt":"In the era of large language models (LLMs), N:M sparsity has emerged as a structured compression technique critical for accelerating inference. While prior work has primarily focused on weight sparsity, it often suffers from significant accuracy degradation. Activation sparsity, though promising, is typically training-dependent and faces challenges in generalization. To address these limitations, we introduce Amber Pruner, a training-free N:M activation sparsity method designed specifically for the prefill stage, targeting the acceleration of linear projection layers in LLMs. Extensive experim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.02128","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/2508.02128/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":"2026-07-05T11:48:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mGlAFeRAfpeLiwRzK5Ek8I+7iWXNgDF0mOWFAUmkG5fiEPTXVHZtnjHDJr70dBSjldiUs8QfZsqeIEbARkEpCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T14:24:02.885813Z"},"content_sha256":"2b25ac7eb4b3c19eeddad3ed5b29459eb1b9839cd2513bad19d818dd2ee2bc45","schema_version":"1.0","event_id":"sha256:2b25ac7eb4b3c19eeddad3ed5b29459eb1b9839cd2513bad19d818dd2ee2bc45"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RZJ6CRDZQOR62ELFWMVIF5EPGG/bundle.json","state_url":"https://pith.science/pith/RZJ6CRDZQOR62ELFWMVIF5EPGG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RZJ6CRDZQOR62ELFWMVIF5EPGG/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":"2026-08-06T14:24:02Z","links":{"resolver":"https://pith.science/pith/RZJ6CRDZQOR62ELFWMVIF5EPGG","bundle":"https://pith.science/pith/RZJ6CRDZQOR62ELFWMVIF5EPGG/bundle.json","state":"https://pith.science/pith/RZJ6CRDZQOR62ELFWMVIF5EPGG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RZJ6CRDZQOR62ELFWMVIF5EPGG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RZJ6CRDZQOR62ELFWMVIF5EPGG","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":"831ae7ccb242e20297f8f32d6509c2d24ef75fe4e425880c62acc592406007ac","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-04T07:22:36Z","title_canon_sha256":"19ee75c147a2f655993286a9ccf974abbf6261c5edc006cb14059e60976a7546"},"schema_version":"1.0","source":{"id":"2508.02128","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.02128","created_at":"2026-07-05T11:48:08Z"},{"alias_kind":"arxiv_version","alias_value":"2508.02128v1","created_at":"2026-07-05T11:48:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.02128","created_at":"2026-07-05T11:48:08Z"},{"alias_kind":"pith_short_12","alias_value":"RZJ6CRDZQOR6","created_at":"2026-07-05T11:48:08Z"},{"alias_kind":"pith_short_16","alias_value":"RZJ6CRDZQOR62ELF","created_at":"2026-07-05T11:48:08Z"},{"alias_kind":"pith_short_8","alias_value":"RZJ6CRDZ","created_at":"2026-07-05T11:48:08Z"}],"graph_snapshots":[{"event_id":"sha256:2b25ac7eb4b3c19eeddad3ed5b29459eb1b9839cd2513bad19d818dd2ee2bc45","target":"graph","created_at":"2026-07-05T11:48:08Z","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/2508.02128/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the era of large language models (LLMs), N:M sparsity has emerged as a structured compression technique critical for accelerating inference. While prior work has primarily focused on weight sparsity, it often suffers from significant accuracy degradation. Activation sparsity, though promising, is typically training-dependent and faces challenges in generalization. To address these limitations, we introduce Amber Pruner, a training-free N:M activation sparsity method designed specifically for the prefill stage, targeting the acceleration of linear projection layers in LLMs. Extensive experim","authors_text":"Gongyi Wang, Hao Chen, Pengcheng Xie, Ruwu Cai, Sheng Chang, Tai An, Yang Liu, Yanzhe Zhang, Yiwu Yao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-04T07:22:36Z","title":"Amber Pruner: Leveraging N:M Activation Sparsity for Efficient Prefill in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.02128","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":"sha256:3fe41fa78d9a79539df7f74c08aa526da19262e52d405eaa81f50a98f03e8ab1","target":"record","created_at":"2026-07-05T11:48:08Z","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":"831ae7ccb242e20297f8f32d6509c2d24ef75fe4e425880c62acc592406007ac","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-04T07:22:36Z","title_canon_sha256":"19ee75c147a2f655993286a9ccf974abbf6261c5edc006cb14059e60976a7546"},"schema_version":"1.0","source":{"id":"2508.02128","kind":"arxiv","version":1}},"canonical_sha256":"8e53e1447983a3ed1165b32a82f48f31a17f7aee904b8d3628ce6b5a8c244188","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e53e1447983a3ed1165b32a82f48f31a17f7aee904b8d3628ce6b5a8c244188","first_computed_at":"2026-07-05T11:48:08.688236Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:48:08.688236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JylTa9Mo+8Ub8A1KNKD53DrKXchRaWAccQeTOFM7FSX2oWBPMmLwcWveFH4d8UsRxdDerfngthiB5cQYfnGlDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:48:08.688748Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.02128","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3fe41fa78d9a79539df7f74c08aa526da19262e52d405eaa81f50a98f03e8ab1","sha256:2b25ac7eb4b3c19eeddad3ed5b29459eb1b9839cd2513bad19d818dd2ee2bc45"],"state_sha256":"88ff571e5e581d4d7ef5e15d0adbbd7b5c2f57e80c34873615e6b27dea20097f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uLGtGlBF0roL/6JPuh5P0yHeYeMTIEfHxO8HBlePa9hYcLsZerI6+9UbaS6J2p35l+10tMKLG6D9cXWWxYt0Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T14:24:02.889605Z","bundle_sha256":"db0b7958d160070db606531ba4e03598019cc2f0eebecdbc27faf469fc59e3a6"}}