{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:IXMUCOS3DWO5LCTE253G7RHRA4","short_pith_number":"pith:IXMUCOS3","canonical_record":{"source":{"id":"2306.16601","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-28T23:55:51Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"ddd5a928ddec0ff364b8cbc006aa255d03b0d96402a53631d1ed07d06da7072b","abstract_canon_sha256":"f1e7817e714c9e3e2ffb42b5daaba67b17791fa7862630b8a75c6d363dc8fb27"},"schema_version":"1.0"},"canonical_sha256":"45d9413a5b1d9dd58a64d7766fc4f10706750e05a271db5690514184e049786c","source":{"kind":"arxiv","id":"2306.16601","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.16601","created_at":"2026-07-05T06:26:06Z"},{"alias_kind":"arxiv_version","alias_value":"2306.16601v1","created_at":"2026-07-05T06:26:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.16601","created_at":"2026-07-05T06:26:06Z"},{"alias_kind":"pith_short_12","alias_value":"IXMUCOS3DWO5","created_at":"2026-07-05T06:26:06Z"},{"alias_kind":"pith_short_16","alias_value":"IXMUCOS3DWO5LCTE","created_at":"2026-07-05T06:26:06Z"},{"alias_kind":"pith_short_8","alias_value":"IXMUCOS3","created_at":"2026-07-05T06:26:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:IXMUCOS3DWO5LCTE253G7RHRA4","target":"record","payload":{"canonical_record":{"source":{"id":"2306.16601","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-28T23:55:51Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"ddd5a928ddec0ff364b8cbc006aa255d03b0d96402a53631d1ed07d06da7072b","abstract_canon_sha256":"f1e7817e714c9e3e2ffb42b5daaba67b17791fa7862630b8a75c6d363dc8fb27"},"schema_version":"1.0"},"canonical_sha256":"45d9413a5b1d9dd58a64d7766fc4f10706750e05a271db5690514184e049786c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:26:06.931172Z","signature_b64":"GaIKSsSAdgjn5Zklj5rVgBaM/fEzVhslbikvx7K6fcO8ME0qwJfeso2aaijnhXte3js2nzdBO0Ox8lL4pFQRDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45d9413a5b1d9dd58a64d7766fc4f10706750e05a271db5690514184e049786c","last_reissued_at":"2026-07-05T06:26:06.930751Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:26:06.930751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.16601","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":"2026-07-05T06:26:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"09dfSu46JIoVSUIO0hjciY/vyhLKnqZwM98dusyYWAr9YStJqD58gIZ84v+T4RxlFvKnoVXsnGWim4I2o+k4CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T02:01:14.018083Z"},"content_sha256":"d34ea506605ed48984782ead63c3646064693947b81b5737e577c110c38c1fcb","schema_version":"1.0","event_id":"sha256:d34ea506605ed48984782ead63c3646064693947b81b5737e577c110c38c1fcb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:IXMUCOS3DWO5LCTE253G7RHRA4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Efficient Sparse Inference Software Accelerator for Transformer-based Language Models on CPUs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Bo Dong, Guy Boudoukh, Haihao Shen, Hanwen Chang, Hengyu Meng, Moshe Wasserblat, Ofir Zafrir, Qun Gao, Yi Ding, Yu Luo, Zhe Wang, Ziheng Wang","submitted_at":"2023-06-28T23:55:51Z","abstract_excerpt":"In recent years, Transformer-based language models have become the standard approach for natural language processing tasks. However, stringent throughput and latency requirements in industrial applications are limiting their adoption. To mitigate the gap, model compression techniques such as structured pruning are being used to improve inference efficiency. However, most existing neural network inference runtimes lack adequate support for structured sparsity. In this paper, we propose an efficient sparse deep learning inference software stack for Transformer-based language models where the wei"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.16601","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/2306.16601/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":"2026-07-05T06:26:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+xDhuswcSGAardfdJojsR4Begk9ZOP46zV/GjzOqueEmDVrWyXl2szg26vg2VF+FcLfLox1Mcz5McKEpIwS+Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T02:01:14.018493Z"},"content_sha256":"44b000dfcefc47a77ffe92c5ee4c2e69e3a949c0aceba707206a09c3b7a61808","schema_version":"1.0","event_id":"sha256:44b000dfcefc47a77ffe92c5ee4c2e69e3a949c0aceba707206a09c3b7a61808"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IXMUCOS3DWO5LCTE253G7RHRA4/bundle.json","state_url":"https://pith.science/pith/IXMUCOS3DWO5LCTE253G7RHRA4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IXMUCOS3DWO5LCTE253G7RHRA4/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":"2026-07-09T02:01:14Z","links":{"resolver":"https://pith.science/pith/IXMUCOS3DWO5LCTE253G7RHRA4","bundle":"https://pith.science/pith/IXMUCOS3DWO5LCTE253G7RHRA4/bundle.json","state":"https://pith.science/pith/IXMUCOS3DWO5LCTE253G7RHRA4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IXMUCOS3DWO5LCTE253G7RHRA4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IXMUCOS3DWO5LCTE253G7RHRA4","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":"f1e7817e714c9e3e2ffb42b5daaba67b17791fa7862630b8a75c6d363dc8fb27","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-28T23:55:51Z","title_canon_sha256":"ddd5a928ddec0ff364b8cbc006aa255d03b0d96402a53631d1ed07d06da7072b"},"schema_version":"1.0","source":{"id":"2306.16601","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.16601","created_at":"2026-07-05T06:26:06Z"},{"alias_kind":"arxiv_version","alias_value":"2306.16601v1","created_at":"2026-07-05T06:26:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.16601","created_at":"2026-07-05T06:26:06Z"},{"alias_kind":"pith_short_12","alias_value":"IXMUCOS3DWO5","created_at":"2026-07-05T06:26:06Z"},{"alias_kind":"pith_short_16","alias_value":"IXMUCOS3DWO5LCTE","created_at":"2026-07-05T06:26:06Z"},{"alias_kind":"pith_short_8","alias_value":"IXMUCOS3","created_at":"2026-07-05T06:26:06Z"}],"graph_snapshots":[{"event_id":"sha256:44b000dfcefc47a77ffe92c5ee4c2e69e3a949c0aceba707206a09c3b7a61808","target":"graph","created_at":"2026-07-05T06:26:06Z","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/2306.16601/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, Transformer-based language models have become the standard approach for natural language processing tasks. However, stringent throughput and latency requirements in industrial applications are limiting their adoption. To mitigate the gap, model compression techniques such as structured pruning are being used to improve inference efficiency. However, most existing neural network inference runtimes lack adequate support for structured sparsity. In this paper, we propose an efficient sparse deep learning inference software stack for Transformer-based language models where the wei","authors_text":"Bo Dong, Guy Boudoukh, Haihao Shen, Hanwen Chang, Hengyu Meng, Moshe Wasserblat, Ofir Zafrir, Qun Gao, Yi Ding, Yu Luo, Zhe Wang, Ziheng Wang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-28T23:55:51Z","title":"An Efficient Sparse Inference Software Accelerator for Transformer-based Language Models on CPUs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.16601","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:d34ea506605ed48984782ead63c3646064693947b81b5737e577c110c38c1fcb","target":"record","created_at":"2026-07-05T06:26:06Z","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":"f1e7817e714c9e3e2ffb42b5daaba67b17791fa7862630b8a75c6d363dc8fb27","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-28T23:55:51Z","title_canon_sha256":"ddd5a928ddec0ff364b8cbc006aa255d03b0d96402a53631d1ed07d06da7072b"},"schema_version":"1.0","source":{"id":"2306.16601","kind":"arxiv","version":1}},"canonical_sha256":"45d9413a5b1d9dd58a64d7766fc4f10706750e05a271db5690514184e049786c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"45d9413a5b1d9dd58a64d7766fc4f10706750e05a271db5690514184e049786c","first_computed_at":"2026-07-05T06:26:06.930751Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:26:06.930751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GaIKSsSAdgjn5Zklj5rVgBaM/fEzVhslbikvx7K6fcO8ME0qwJfeso2aaijnhXte3js2nzdBO0Ox8lL4pFQRDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:26:06.931172Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.16601","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d34ea506605ed48984782ead63c3646064693947b81b5737e577c110c38c1fcb","sha256:44b000dfcefc47a77ffe92c5ee4c2e69e3a949c0aceba707206a09c3b7a61808"],"state_sha256":"13abe208e84a193b9e3a9006fc498e4b420faf008d1f1e2c0e2d7d9670ba826a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qPExFSWF3HcYZmOai0IPdDzObChNiZ7UJzASVYqDP2PIwFmLavj+7+sVrZFYDgBLwclxo/+5PN66ogKaeMepAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T02:01:14.020534Z","bundle_sha256":"040198fc6a6b2a7f813852628cfa403a67f2ebddecca0c55e8baa614fcaa55aa"}}