{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QUVJEO6KYUGL4LOOL6DH2M3RQH","short_pith_number":"pith:QUVJEO6K","canonical_record":{"source":{"id":"2409.01366","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-02T16:41:44Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"dd426ae8ae441b4b1c96cce5104befae0d71cc1c212d5b5978247344571bdd7f","abstract_canon_sha256":"5c8d9d71b46a8d90e7769ba697b166170e8c759c0b052d105dca3983ebf4627e"},"schema_version":"1.0"},"canonical_sha256":"852a923bcac50cbe2dce5f867d337181f3ba44415624f5f5e66d2892a6f38940","source":{"kind":"arxiv","id":"2409.01366","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.01366","created_at":"2026-07-05T09:54:28Z"},{"alias_kind":"arxiv_version","alias_value":"2409.01366v2","created_at":"2026-07-05T09:54:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.01366","created_at":"2026-07-05T09:54:28Z"},{"alias_kind":"pith_short_12","alias_value":"QUVJEO6KYUGL","created_at":"2026-07-05T09:54:28Z"},{"alias_kind":"pith_short_16","alias_value":"QUVJEO6KYUGL4LOO","created_at":"2026-07-05T09:54:28Z"},{"alias_kind":"pith_short_8","alias_value":"QUVJEO6K","created_at":"2026-07-05T09:54:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QUVJEO6KYUGL4LOOL6DH2M3RQH","target":"record","payload":{"canonical_record":{"source":{"id":"2409.01366","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-02T16:41:44Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"dd426ae8ae441b4b1c96cce5104befae0d71cc1c212d5b5978247344571bdd7f","abstract_canon_sha256":"5c8d9d71b46a8d90e7769ba697b166170e8c759c0b052d105dca3983ebf4627e"},"schema_version":"1.0"},"canonical_sha256":"852a923bcac50cbe2dce5f867d337181f3ba44415624f5f5e66d2892a6f38940","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:28.412468Z","signature_b64":"/qQfBGzmxQ/AlSk3du7edFF4YhZRFtbIaUArUJjS2AMrhg9swVMPpYPKpofiJfGa4JHjxeEEq+ytNp2MsiAdDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"852a923bcac50cbe2dce5f867d337181f3ba44415624f5f5e66d2892a6f38940","last_reissued_at":"2026-07-05T09:54:28.412018Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:28.412018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.01366","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":"2026-07-05T09:54:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OjyNKY+HtNF/nIAfSMRr61mNQBAi9r/RitOKIbjwyPgPprByjcHBABbvTMOR69tibzVOx+R4R6qsU2qvFFvJAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T23:55:41.296352Z"},"content_sha256":"c09bb3963e02e0fe7dc23503b90045fa2ce02eef81d6dbf610fbfcaa987f3e9a","schema_version":"1.0","event_id":"sha256:c09bb3963e02e0fe7dc23503b90045fa2ce02eef81d6dbf610fbfcaa987f3e9a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QUVJEO6KYUGL4LOOL6DH2M3RQH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CHESS: Optimizing LLM Inference via Channel-Wise Thresholding and Selective Sparsification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chun Jason Xue, Junhui He, Qingan Li, Shangyu Wu, Weidong Wen","submitted_at":"2024-09-02T16:41:44Z","abstract_excerpt":"Deploying large language models (LLMs) on edge devices presents significant challenges due to the substantial computational overhead and memory requirements. Activation sparsification can mitigate these resource challenges by reducing the number of activated neurons during inference. Existing methods typically employ thresholding-based sparsification based on the statistics of activation tensors. However, they do not model the impact of activation sparsification on performance, resulting in suboptimal performance degradation. To address the limitations, this paper reformulates the activation s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.01366","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/2409.01366/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":"2026-07-05T09:54:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RFH5GojnkwcbZ7ZyE2lS7bCdujcXDBxGZkZUKf/o6M5BTmS3KQmIE3kYJ3PpXY/8ywdbsx2ayHeMUogYknBMCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T23:55:41.296882Z"},"content_sha256":"2c061de41b1b610aac2986c54227297057637d9ce155710bd2dd30d1ebba0c46","schema_version":"1.0","event_id":"sha256:2c061de41b1b610aac2986c54227297057637d9ce155710bd2dd30d1ebba0c46"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QUVJEO6KYUGL4LOOL6DH2M3RQH/bundle.json","state_url":"https://pith.science/pith/QUVJEO6KYUGL4LOOL6DH2M3RQH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QUVJEO6KYUGL4LOOL6DH2M3RQH/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":"2026-08-16T23:55:41Z","links":{"resolver":"https://pith.science/pith/QUVJEO6KYUGL4LOOL6DH2M3RQH","bundle":"https://pith.science/pith/QUVJEO6KYUGL4LOOL6DH2M3RQH/bundle.json","state":"https://pith.science/pith/QUVJEO6KYUGL4LOOL6DH2M3RQH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QUVJEO6KYUGL4LOOL6DH2M3RQH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QUVJEO6KYUGL4LOOL6DH2M3RQH","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":"5c8d9d71b46a8d90e7769ba697b166170e8c759c0b052d105dca3983ebf4627e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-02T16:41:44Z","title_canon_sha256":"dd426ae8ae441b4b1c96cce5104befae0d71cc1c212d5b5978247344571bdd7f"},"schema_version":"1.0","source":{"id":"2409.01366","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.01366","created_at":"2026-07-05T09:54:28Z"},{"alias_kind":"arxiv_version","alias_value":"2409.01366v2","created_at":"2026-07-05T09:54:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.01366","created_at":"2026-07-05T09:54:28Z"},{"alias_kind":"pith_short_12","alias_value":"QUVJEO6KYUGL","created_at":"2026-07-05T09:54:28Z"},{"alias_kind":"pith_short_16","alias_value":"QUVJEO6KYUGL4LOO","created_at":"2026-07-05T09:54:28Z"},{"alias_kind":"pith_short_8","alias_value":"QUVJEO6K","created_at":"2026-07-05T09:54:28Z"}],"graph_snapshots":[{"event_id":"sha256:2c061de41b1b610aac2986c54227297057637d9ce155710bd2dd30d1ebba0c46","target":"graph","created_at":"2026-07-05T09:54:28Z","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/2409.01366/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deploying large language models (LLMs) on edge devices presents significant challenges due to the substantial computational overhead and memory requirements. Activation sparsification can mitigate these resource challenges by reducing the number of activated neurons during inference. Existing methods typically employ thresholding-based sparsification based on the statistics of activation tensors. However, they do not model the impact of activation sparsification on performance, resulting in suboptimal performance degradation. To address the limitations, this paper reformulates the activation s","authors_text":"Chun Jason Xue, Junhui He, Qingan Li, Shangyu Wu, Weidong Wen","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-02T16:41:44Z","title":"CHESS: Optimizing LLM Inference via Channel-Wise Thresholding and Selective Sparsification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.01366","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:c09bb3963e02e0fe7dc23503b90045fa2ce02eef81d6dbf610fbfcaa987f3e9a","target":"record","created_at":"2026-07-05T09:54:28Z","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":"5c8d9d71b46a8d90e7769ba697b166170e8c759c0b052d105dca3983ebf4627e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-02T16:41:44Z","title_canon_sha256":"dd426ae8ae441b4b1c96cce5104befae0d71cc1c212d5b5978247344571bdd7f"},"schema_version":"1.0","source":{"id":"2409.01366","kind":"arxiv","version":2}},"canonical_sha256":"852a923bcac50cbe2dce5f867d337181f3ba44415624f5f5e66d2892a6f38940","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"852a923bcac50cbe2dce5f867d337181f3ba44415624f5f5e66d2892a6f38940","first_computed_at":"2026-07-05T09:54:28.412018Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:28.412018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/qQfBGzmxQ/AlSk3du7edFF4YhZRFtbIaUArUJjS2AMrhg9swVMPpYPKpofiJfGa4JHjxeEEq+ytNp2MsiAdDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:28.412468Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.01366","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c09bb3963e02e0fe7dc23503b90045fa2ce02eef81d6dbf610fbfcaa987f3e9a","sha256:2c061de41b1b610aac2986c54227297057637d9ce155710bd2dd30d1ebba0c46"],"state_sha256":"b04ae0a7fa73b41199016eb11f53a7cb9731042b7ca2741fac0e8df5d02956b4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n5IRASfEsohHPV+ciG5iPpWsjhet4bU+EPOc/ZmaFpBhxbHCIY8HUsO5oeZffSsUSNxp1scyw1whuXrXG1BhAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T23:55:41.300147Z","bundle_sha256":"b5c014157482376d9bda869d8dd05c7e56db2fa81a8ca15ff8de201fb8881622"}}