{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:VQRD52DRIY6OGCS7SFHICJPPDV","short_pith_number":"pith:VQRD52DR","canonical_record":{"source":{"id":"2309.10285","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2023-09-19T03:20:02Z","cross_cats_sorted":["cs.AR","cs.LG"],"title_canon_sha256":"74a0a05ffcaa4d47fdc8b7453271227527a29c2eebfb352ef403451f549a49c4","abstract_canon_sha256":"6b0b5b482307a62ff7ec056b6730ce0d793de7af60f5fb5c4e69707336f4c3f6"},"schema_version":"1.0"},"canonical_sha256":"ac223ee871463ce30a5f914e8125ef1d608215755765104e33326115b237449a","source":{"kind":"arxiv","id":"2309.10285","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.10285","created_at":"2026-07-05T06:52:09Z"},{"alias_kind":"arxiv_version","alias_value":"2309.10285v1","created_at":"2026-07-05T06:52:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.10285","created_at":"2026-07-05T06:52:09Z"},{"alias_kind":"pith_short_12","alias_value":"VQRD52DRIY6O","created_at":"2026-07-05T06:52:09Z"},{"alias_kind":"pith_short_16","alias_value":"VQRD52DRIY6OGCS7","created_at":"2026-07-05T06:52:09Z"},{"alias_kind":"pith_short_8","alias_value":"VQRD52DR","created_at":"2026-07-05T06:52:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:VQRD52DRIY6OGCS7SFHICJPPDV","target":"record","payload":{"canonical_record":{"source":{"id":"2309.10285","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2023-09-19T03:20:02Z","cross_cats_sorted":["cs.AR","cs.LG"],"title_canon_sha256":"74a0a05ffcaa4d47fdc8b7453271227527a29c2eebfb352ef403451f549a49c4","abstract_canon_sha256":"6b0b5b482307a62ff7ec056b6730ce0d793de7af60f5fb5c4e69707336f4c3f6"},"schema_version":"1.0"},"canonical_sha256":"ac223ee871463ce30a5f914e8125ef1d608215755765104e33326115b237449a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:52:09.776258Z","signature_b64":"Va8biDtQzt6dplv2DYrOdqgotwnrvpakZGdVzAVBHiPB0ukLiiOKIS8TRrBhI0IErepXJz7GMWkWnhD18uI4Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac223ee871463ce30a5f914e8125ef1d608215755765104e33326115b237449a","last_reissued_at":"2026-07-05T06:52:09.775701Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:52:09.775701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.10285","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":"2026-07-05T06:52:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gfEsD8Q3JBYfzuXMmoigdp+mhZAW/sjX3kgaytJNCoZHJBPLMbq1bNSR/IV7w6V9FhtMcQ4ihYWGgRcClGyVAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:41:12.911292Z"},"content_sha256":"4240d8d47adbbca86899c54e8a0bffa42eab102232abffc8d16b50364c33edf9","schema_version":"1.0","event_id":"sha256:4240d8d47adbbca86899c54e8a0bffa42eab102232abffc8d16b50364c33edf9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:VQRD52DRIY6OGCS7SFHICJPPDV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AR","cs.LG"],"primary_cat":"cs.DC","authors_text":"Donglin Zhuang, Haojun Xia, Shuaiwen Leon Song, Wei Lin, Xiafei Qiu, Yong Li, Yuchao Li, Zhen Zheng, Zhongzhu Zhou","submitted_at":"2023-09-19T03:20:02Z","abstract_excerpt":"With the fast growth of parameter size, it becomes increasingly challenging to deploy large generative models as they typically require large GPU memory consumption and massive computation. Unstructured model pruning has been a common approach to reduce both GPU memory footprint and the overall computation while retaining good model accuracy. However, the existing solutions do not provide a highly-efficient support for handling unstructured sparsity on modern GPUs, especially on the highly-structured Tensor Core hardware. Therefore, we propose Flash-LLM for enabling low-cost and highly-efficie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10285","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/2309.10285/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":"2026-07-05T06:52:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V056Z51uBnpgwK6EhT3fAZqEjLLtkXUyYGMaVy26+x8aoOYrLIeOtuXpYQSW7XtQAb5SdD3NvijeFfAlRNhEBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:41:12.912459Z"},"content_sha256":"6389498a1cfe78b0f1aaff87cc5657bfb3c2b69fe53a5ba6f49dce29529512e5","schema_version":"1.0","event_id":"sha256:6389498a1cfe78b0f1aaff87cc5657bfb3c2b69fe53a5ba6f49dce29529512e5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VQRD52DRIY6OGCS7SFHICJPPDV/bundle.json","state_url":"https://pith.science/pith/VQRD52DRIY6OGCS7SFHICJPPDV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VQRD52DRIY6OGCS7SFHICJPPDV/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":"2026-08-06T04:41:12Z","links":{"resolver":"https://pith.science/pith/VQRD52DRIY6OGCS7SFHICJPPDV","bundle":"https://pith.science/pith/VQRD52DRIY6OGCS7SFHICJPPDV/bundle.json","state":"https://pith.science/pith/VQRD52DRIY6OGCS7SFHICJPPDV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VQRD52DRIY6OGCS7SFHICJPPDV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VQRD52DRIY6OGCS7SFHICJPPDV","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":"6b0b5b482307a62ff7ec056b6730ce0d793de7af60f5fb5c4e69707336f4c3f6","cross_cats_sorted":["cs.AR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2023-09-19T03:20:02Z","title_canon_sha256":"74a0a05ffcaa4d47fdc8b7453271227527a29c2eebfb352ef403451f549a49c4"},"schema_version":"1.0","source":{"id":"2309.10285","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.10285","created_at":"2026-07-05T06:52:09Z"},{"alias_kind":"arxiv_version","alias_value":"2309.10285v1","created_at":"2026-07-05T06:52:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.10285","created_at":"2026-07-05T06:52:09Z"},{"alias_kind":"pith_short_12","alias_value":"VQRD52DRIY6O","created_at":"2026-07-05T06:52:09Z"},{"alias_kind":"pith_short_16","alias_value":"VQRD52DRIY6OGCS7","created_at":"2026-07-05T06:52:09Z"},{"alias_kind":"pith_short_8","alias_value":"VQRD52DR","created_at":"2026-07-05T06:52:09Z"}],"graph_snapshots":[{"event_id":"sha256:6389498a1cfe78b0f1aaff87cc5657bfb3c2b69fe53a5ba6f49dce29529512e5","target":"graph","created_at":"2026-07-05T06:52:09Z","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/2309.10285/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the fast growth of parameter size, it becomes increasingly challenging to deploy large generative models as they typically require large GPU memory consumption and massive computation. Unstructured model pruning has been a common approach to reduce both GPU memory footprint and the overall computation while retaining good model accuracy. However, the existing solutions do not provide a highly-efficient support for handling unstructured sparsity on modern GPUs, especially on the highly-structured Tensor Core hardware. Therefore, we propose Flash-LLM for enabling low-cost and highly-efficie","authors_text":"Donglin Zhuang, Haojun Xia, Shuaiwen Leon Song, Wei Lin, Xiafei Qiu, Yong Li, Yuchao Li, Zhen Zheng, Zhongzhu Zhou","cross_cats":["cs.AR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2023-09-19T03:20:02Z","title":"Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10285","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":"sha256:4240d8d47adbbca86899c54e8a0bffa42eab102232abffc8d16b50364c33edf9","target":"record","created_at":"2026-07-05T06:52:09Z","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":"6b0b5b482307a62ff7ec056b6730ce0d793de7af60f5fb5c4e69707336f4c3f6","cross_cats_sorted":["cs.AR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2023-09-19T03:20:02Z","title_canon_sha256":"74a0a05ffcaa4d47fdc8b7453271227527a29c2eebfb352ef403451f549a49c4"},"schema_version":"1.0","source":{"id":"2309.10285","kind":"arxiv","version":1}},"canonical_sha256":"ac223ee871463ce30a5f914e8125ef1d608215755765104e33326115b237449a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac223ee871463ce30a5f914e8125ef1d608215755765104e33326115b237449a","first_computed_at":"2026-07-05T06:52:09.775701Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:52:09.775701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Va8biDtQzt6dplv2DYrOdqgotwnrvpakZGdVzAVBHiPB0ukLiiOKIS8TRrBhI0IErepXJz7GMWkWnhD18uI4Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:52:09.776258Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.10285","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4240d8d47adbbca86899c54e8a0bffa42eab102232abffc8d16b50364c33edf9","sha256:6389498a1cfe78b0f1aaff87cc5657bfb3c2b69fe53a5ba6f49dce29529512e5"],"state_sha256":"26ce3eb6af9870dd7f3e7e11ecaddb8da7a6c77f09fe19afe672d65721ce157e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6gWIdTmDUgCb22avViO5B5EOf2UREIhU3diIixv9GeXf02RCQpUvuB5cqICJBPkKSPOac5RjcM0eABPJJNOADQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T04:41:12.917548Z","bundle_sha256":"ddd3784e4829f5800eb8ea260526461024833051b3d9b7f11bb4c8e1a4d60afa"}}