{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XHB7KX7XGULC5JGJPEG3URNGSF","short_pith_number":"pith:XHB7KX7X","canonical_record":{"source":{"id":"2505.19349","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AR","submitted_at":"2025-05-25T22:32:35Z","cross_cats_sorted":[],"title_canon_sha256":"c44d43a16745f05c8a029548625570fe29924ee01c59cad1de8fe1a9112d4fdb","abstract_canon_sha256":"c959028417146bfbff576f6b2ab05d3eff649aef21fc510ac9942c7c9963beba"},"schema_version":"1.0"},"canonical_sha256":"b9c3f55ff735162ea4c9790dba45a691776f249235a9ef287ef7e4429c34ac55","source":{"kind":"arxiv","id":"2505.19349","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19349","created_at":"2026-07-05T11:50:37Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19349v2","created_at":"2026-07-05T11:50:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19349","created_at":"2026-07-05T11:50:37Z"},{"alias_kind":"pith_short_12","alias_value":"XHB7KX7XGULC","created_at":"2026-07-05T11:50:37Z"},{"alias_kind":"pith_short_16","alias_value":"XHB7KX7XGULC5JGJ","created_at":"2026-07-05T11:50:37Z"},{"alias_kind":"pith_short_8","alias_value":"XHB7KX7X","created_at":"2026-07-05T11:50:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XHB7KX7XGULC5JGJPEG3URNGSF","target":"record","payload":{"canonical_record":{"source":{"id":"2505.19349","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AR","submitted_at":"2025-05-25T22:32:35Z","cross_cats_sorted":[],"title_canon_sha256":"c44d43a16745f05c8a029548625570fe29924ee01c59cad1de8fe1a9112d4fdb","abstract_canon_sha256":"c959028417146bfbff576f6b2ab05d3eff649aef21fc510ac9942c7c9963beba"},"schema_version":"1.0"},"canonical_sha256":"b9c3f55ff735162ea4c9790dba45a691776f249235a9ef287ef7e4429c34ac55","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:50:37.060394Z","signature_b64":"LfYnPmrAgHaSHKH5zIGNk2K7Ok8SmKtJ90M497zgm+AvfSoSkwJMs1z4HOuP+yAc/HTWqL7aWF81Rz5//I1mDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9c3f55ff735162ea4c9790dba45a691776f249235a9ef287ef7e4429c34ac55","last_reissued_at":"2026-07-05T11:50:37.059727Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:50:37.059727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.19349","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":"2026-07-05T11:50:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ybs3DN8I3065gFEVwFB+nVH8bWI6H/R+bSEBDuSthJfVY5ByZUZChoVNiskf6HL+lFblv7IEOdlerISkIJ9QAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:23:33.143469Z"},"content_sha256":"15121a6403bc527e21cc8914040078ddc12a303d011f61a10eed80d695478946","schema_version":"1.0","event_id":"sha256:15121a6403bc527e21cc8914040078ddc12a303d011f61a10eed80d695478946"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XHB7KX7XGULC5JGJPEG3URNGSF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DECA: A Near-Core LLM Decompression Accelerator Grounded on a 3D Roofline Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Evangelos Georganas (Intel Labs), Gerasimos Gerogiannis (Intel Corporation, Josep Torrellas (University of Illinois at Urbana-Champaign), Stijn Eyerman (Intel Corporation), University of Illinois at Urbana-Champaign), Wim Heirman (Intel Corporation)","submitted_at":"2025-05-25T22:32:35Z","abstract_excerpt":"To alleviate the memory bandwidth bottleneck in Large Language Model (LLM) inference workloads, weight matrices are stored in memory in quantized and sparsified formats. Hence, before tiles of these matrices can be processed by in-core generalized matrix multiplication (GeMM) hardware engines, they need to be dequantized and de-sparsified. This is currently performed in software with vector operations. Unfortunately, this approach delivers only modest performance. Moreover, it is hard to understand how to improve the system, as the overall GeMM performance depends on the interaction between me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19349","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/2505.19349/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":"2026-07-05T11:50:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G0qllkkVkvw1PFheDYyL2zhhyMMnjY5HmTp+6gVInQ/VeLFUBYGYqLG1+YCB/Orj9fpd2hxHQgvnRfB2GiEnCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:23:33.144001Z"},"content_sha256":"56243a27bbc2d66495bae6c552d7df0d96d10b6586a1f27035091f05901be5a5","schema_version":"1.0","event_id":"sha256:56243a27bbc2d66495bae6c552d7df0d96d10b6586a1f27035091f05901be5a5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XHB7KX7XGULC5JGJPEG3URNGSF/bundle.json","state_url":"https://pith.science/pith/XHB7KX7XGULC5JGJPEG3URNGSF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XHB7KX7XGULC5JGJPEG3URNGSF/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":"2026-08-08T16:23:33Z","links":{"resolver":"https://pith.science/pith/XHB7KX7XGULC5JGJPEG3URNGSF","bundle":"https://pith.science/pith/XHB7KX7XGULC5JGJPEG3URNGSF/bundle.json","state":"https://pith.science/pith/XHB7KX7XGULC5JGJPEG3URNGSF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XHB7KX7XGULC5JGJPEG3URNGSF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XHB7KX7XGULC5JGJPEG3URNGSF","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":"c959028417146bfbff576f6b2ab05d3eff649aef21fc510ac9942c7c9963beba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AR","submitted_at":"2025-05-25T22:32:35Z","title_canon_sha256":"c44d43a16745f05c8a029548625570fe29924ee01c59cad1de8fe1a9112d4fdb"},"schema_version":"1.0","source":{"id":"2505.19349","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19349","created_at":"2026-07-05T11:50:37Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19349v2","created_at":"2026-07-05T11:50:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19349","created_at":"2026-07-05T11:50:37Z"},{"alias_kind":"pith_short_12","alias_value":"XHB7KX7XGULC","created_at":"2026-07-05T11:50:37Z"},{"alias_kind":"pith_short_16","alias_value":"XHB7KX7XGULC5JGJ","created_at":"2026-07-05T11:50:37Z"},{"alias_kind":"pith_short_8","alias_value":"XHB7KX7X","created_at":"2026-07-05T11:50:37Z"}],"graph_snapshots":[{"event_id":"sha256:56243a27bbc2d66495bae6c552d7df0d96d10b6586a1f27035091f05901be5a5","target":"graph","created_at":"2026-07-05T11:50:37Z","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/2505.19349/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To alleviate the memory bandwidth bottleneck in Large Language Model (LLM) inference workloads, weight matrices are stored in memory in quantized and sparsified formats. Hence, before tiles of these matrices can be processed by in-core generalized matrix multiplication (GeMM) hardware engines, they need to be dequantized and de-sparsified. This is currently performed in software with vector operations. Unfortunately, this approach delivers only modest performance. Moreover, it is hard to understand how to improve the system, as the overall GeMM performance depends on the interaction between me","authors_text":"Evangelos Georganas (Intel Labs), Gerasimos Gerogiannis (Intel Corporation, Josep Torrellas (University of Illinois at Urbana-Champaign), Stijn Eyerman (Intel Corporation), University of Illinois at Urbana-Champaign), Wim Heirman (Intel Corporation)","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AR","submitted_at":"2025-05-25T22:32:35Z","title":"DECA: A Near-Core LLM Decompression Accelerator Grounded on a 3D Roofline Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19349","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":"sha256:15121a6403bc527e21cc8914040078ddc12a303d011f61a10eed80d695478946","target":"record","created_at":"2026-07-05T11:50:37Z","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":"c959028417146bfbff576f6b2ab05d3eff649aef21fc510ac9942c7c9963beba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AR","submitted_at":"2025-05-25T22:32:35Z","title_canon_sha256":"c44d43a16745f05c8a029548625570fe29924ee01c59cad1de8fe1a9112d4fdb"},"schema_version":"1.0","source":{"id":"2505.19349","kind":"arxiv","version":2}},"canonical_sha256":"b9c3f55ff735162ea4c9790dba45a691776f249235a9ef287ef7e4429c34ac55","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b9c3f55ff735162ea4c9790dba45a691776f249235a9ef287ef7e4429c34ac55","first_computed_at":"2026-07-05T11:50:37.059727Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:50:37.059727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LfYnPmrAgHaSHKH5zIGNk2K7Ok8SmKtJ90M497zgm+AvfSoSkwJMs1z4HOuP+yAc/HTWqL7aWF81Rz5//I1mDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:50:37.060394Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.19349","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:15121a6403bc527e21cc8914040078ddc12a303d011f61a10eed80d695478946","sha256:56243a27bbc2d66495bae6c552d7df0d96d10b6586a1f27035091f05901be5a5"],"state_sha256":"f49e79a90eff161a35b9e93aa633ea14fb41fc9b5a82f135a9d4df08bbe856c1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2ZJYkZCcl0SPJqbc00eoeYAtqSqEo2dXCNaJI693Ii7pfn/+5W5Z/xfI3gJ709V9BU9WsGhuio8LwFpbNc3CDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T16:23:33.147717Z","bundle_sha256":"89c622c019715781048bf48325362db447327a9f5cf31690473b881e6e558822"}}