{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:N5F57DHM2NMYI7UUUIVPDV24EQ","short_pith_number":"pith:N5F57DHM","canonical_record":{"source":{"id":"2512.00053","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2025-11-19T15:57:09Z","cross_cats_sorted":[],"title_canon_sha256":"9a16540b679ce3b1d3f9b511bcb58992b05470451552dbf60d8f66c60b597aa9","abstract_canon_sha256":"894fbefdede516dc5790e0d6455a94ec946cb2cfcd4166046a9fc71ab9f75cd7"},"schema_version":"1.0"},"canonical_sha256":"6f4bdf8cecd359847e94a22af1d75c241c251723eb7bc646fb2d84ea3a4daf76","source":{"kind":"arxiv","id":"2512.00053","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.00053","created_at":"2026-06-12T01:09:17Z"},{"alias_kind":"arxiv_version","alias_value":"2512.00053v3","created_at":"2026-06-12T01:09:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.00053","created_at":"2026-06-12T01:09:17Z"},{"alias_kind":"pith_short_12","alias_value":"N5F57DHM2NMY","created_at":"2026-06-12T01:09:17Z"},{"alias_kind":"pith_short_16","alias_value":"N5F57DHM2NMYI7UU","created_at":"2026-06-12T01:09:17Z"},{"alias_kind":"pith_short_8","alias_value":"N5F57DHM","created_at":"2026-06-12T01:09:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:N5F57DHM2NMYI7UUUIVPDV24EQ","target":"record","payload":{"canonical_record":{"source":{"id":"2512.00053","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2025-11-19T15:57:09Z","cross_cats_sorted":[],"title_canon_sha256":"9a16540b679ce3b1d3f9b511bcb58992b05470451552dbf60d8f66c60b597aa9","abstract_canon_sha256":"894fbefdede516dc5790e0d6455a94ec946cb2cfcd4166046a9fc71ab9f75cd7"},"schema_version":"1.0"},"canonical_sha256":"6f4bdf8cecd359847e94a22af1d75c241c251723eb7bc646fb2d84ea3a4daf76","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:09:17.298653Z","signature_b64":"AKNGRuiYTar2h4Ym3tf6ZmPz9bv8/gWvUfq/o92QnwrE7Kn3sKuFRDGU3gUV8dSW82JWxb9DiJUvV4XMlgDHCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f4bdf8cecd359847e94a22af1d75c241c251723eb7bc646fb2d84ea3a4daf76","last_reissued_at":"2026-06-12T01:09:17.297750Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:09:17.297750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2512.00053","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-12T01:09:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FO1zMqBM9YuqTv7oXpoM6qrNuPRaOACozDI5HMCRw4AQAs05IHN9rmTy/w3mrcSrHlhsOhTfyuSQTk/jZYheBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T21:35:47.878268Z"},"content_sha256":"77cc5c2a0ed8ab854ec9cbef149939794d8554dfd8e623186f2afd3d1b8bd94a","schema_version":"1.0","event_id":"sha256:77cc5c2a0ed8ab854ec9cbef149939794d8554dfd8e623186f2afd3d1b8bd94a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:N5F57DHM2NMYI7UUUIVPDV24EQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Ten-Four: An Open-Source Fused Dot Product Unit for Mixed-Precision GPGPU Tensor Cores","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Ten-Four fuses floating-point and integer pipelines into one dot-product unit that runs mixed-precision matrix operations in four cycles.","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Blaise Tine, Nikhil Rout","submitted_at":"2025-11-19T15:57:09Z","abstract_excerpt":"Efficient mixed-precision MMA operations are critical for accelerating deep learning workloads on GPGPUs. However, existing open-source Tensor Core implementations rely on discrete arithmetic unit designs, leading to high latency, accumulated rounding errors, and poor resource utilization. To address these challenges, we propose Ten-Four, a configurable mixed-precision fused dot product unit integrating both floating-point and integer arithmetic pipelines within a unified architecture, implemented as part of the open-source RISC-V-based Vortex GPGPU's Tensor Core Unit extension. It supports lo"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Ten-Four achieves 4-cycle operation latency at 262.325 MHz Fmax, delivering 134.308 GFLOPS peak throughput per Tensor Core on the AMD Xilinx Alveo U55C FPGA, demonstrating ~3.1x performance improvement over an equivalent Berkeley HardFloat-based implementation at less than 60% the area cost.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the fused pipeline preserves exact numerical equivalence to discrete units across all supported formats (FP16/BF16/FP8/BF8/INT8/INT4) without hidden rounding differences that only appear under specific input patterns or when integrated into the full Vortex Tensor Core.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Ten-Four delivers a fused mixed-precision dot-product unit for open-source GPGPUs that runs in 4 cycles at 262 MHz, matches NVIDIA numerical accuracy, and uses less than 60% the area of a prior open implementation while delivering 3.1x higher throughput.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Ten-Four fuses floating-point and integer pipelines into one dot-product unit that runs mixed-precision matrix operations in four cycles.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"330ed9e535d85a13fd73b3f1f1b2561ef556128a1ec8af7593e0595485888f78"},"source":{"id":"2512.00053","kind":"arxiv","version":3},"verdict":{"id":"c7a68bf3-5005-48d4-8b28-716166a6e185","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T20:32:14.255485Z","strongest_claim":"Ten-Four achieves 4-cycle operation latency at 262.325 MHz Fmax, delivering 134.308 GFLOPS peak throughput per Tensor Core on the AMD Xilinx Alveo U55C FPGA, demonstrating ~3.1x performance improvement over an equivalent Berkeley HardFloat-based implementation at less than 60% the area cost.","one_line_summary":"Ten-Four delivers a fused mixed-precision dot-product unit for open-source GPGPUs that runs in 4 cycles at 262 MHz, matches NVIDIA numerical accuracy, and uses less than 60% the area of a prior open implementation while delivering 3.1x higher throughput.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the fused pipeline preserves exact numerical equivalence to discrete units across all supported formats (FP16/BF16/FP8/BF8/INT8/INT4) without hidden rounding differences that only appear under specific input patterns or when integrated into the full Vortex Tensor Core.","pith_extraction_headline":"Ten-Four fuses floating-point and integer pipelines into one dot-product unit that runs mixed-precision matrix operations in four cycles."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2512.00053/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":2,"snapshot_sha256":"3f3a1ec68ad5750dd2f34c0e4c70f0eb7c36de5975423351257c572d3726c114"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"c7a68bf3-5005-48d4-8b28-716166a6e185"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-12T01:09:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b3grF3DdJb+oa0weD9o4mM+ChHLSIp9xeYpKP/LFvOImdlfQILuZtqLHJumfYlibuGJD22SssWrQrCaUkMcXAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T21:35:47.878724Z"},"content_sha256":"72d78f5b8c6e4d5d2040379186b5c88f30193feacce112914d323985e6f58fed","schema_version":"1.0","event_id":"sha256:72d78f5b8c6e4d5d2040379186b5c88f30193feacce112914d323985e6f58fed"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N5F57DHM2NMYI7UUUIVPDV24EQ/bundle.json","state_url":"https://pith.science/pith/N5F57DHM2NMYI7UUUIVPDV24EQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N5F57DHM2NMYI7UUUIVPDV24EQ/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":"2026-06-27T21:35:47Z","links":{"resolver":"https://pith.science/pith/N5F57DHM2NMYI7UUUIVPDV24EQ","bundle":"https://pith.science/pith/N5F57DHM2NMYI7UUUIVPDV24EQ/bundle.json","state":"https://pith.science/pith/N5F57DHM2NMYI7UUUIVPDV24EQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N5F57DHM2NMYI7UUUIVPDV24EQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:N5F57DHM2NMYI7UUUIVPDV24EQ","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":"894fbefdede516dc5790e0d6455a94ec946cb2cfcd4166046a9fc71ab9f75cd7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2025-11-19T15:57:09Z","title_canon_sha256":"9a16540b679ce3b1d3f9b511bcb58992b05470451552dbf60d8f66c60b597aa9"},"schema_version":"1.0","source":{"id":"2512.00053","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.00053","created_at":"2026-06-12T01:09:17Z"},{"alias_kind":"arxiv_version","alias_value":"2512.00053v3","created_at":"2026-06-12T01:09:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.00053","created_at":"2026-06-12T01:09:17Z"},{"alias_kind":"pith_short_12","alias_value":"N5F57DHM2NMY","created_at":"2026-06-12T01:09:17Z"},{"alias_kind":"pith_short_16","alias_value":"N5F57DHM2NMYI7UU","created_at":"2026-06-12T01:09:17Z"},{"alias_kind":"pith_short_8","alias_value":"N5F57DHM","created_at":"2026-06-12T01:09:17Z"}],"graph_snapshots":[{"event_id":"sha256:72d78f5b8c6e4d5d2040379186b5c88f30193feacce112914d323985e6f58fed","target":"graph","created_at":"2026-06-12T01:09:17Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Ten-Four achieves 4-cycle operation latency at 262.325 MHz Fmax, delivering 134.308 GFLOPS peak throughput per Tensor Core on the AMD Xilinx Alveo U55C FPGA, demonstrating ~3.1x performance improvement over an equivalent Berkeley HardFloat-based implementation at less than 60% the area cost."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the fused pipeline preserves exact numerical equivalence to discrete units across all supported formats (FP16/BF16/FP8/BF8/INT8/INT4) without hidden rounding differences that only appear under specific input patterns or when integrated into the full Vortex Tensor Core."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Ten-Four delivers a fused mixed-precision dot-product unit for open-source GPGPUs that runs in 4 cycles at 262 MHz, matches NVIDIA numerical accuracy, and uses less than 60% the area of a prior open implementation while delivering 3.1x higher throughput."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Ten-Four fuses floating-point and integer pipelines into one dot-product unit that runs mixed-precision matrix operations in four cycles."}],"snapshot_sha256":"330ed9e535d85a13fd73b3f1f1b2561ef556128a1ec8af7593e0595485888f78"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"3f3a1ec68ad5750dd2f34c0e4c70f0eb7c36de5975423351257c572d3726c114"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2512.00053/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Efficient mixed-precision MMA operations are critical for accelerating deep learning workloads on GPGPUs. However, existing open-source Tensor Core implementations rely on discrete arithmetic unit designs, leading to high latency, accumulated rounding errors, and poor resource utilization. To address these challenges, we propose Ten-Four, a configurable mixed-precision fused dot product unit integrating both floating-point and integer arithmetic pipelines within a unified architecture, implemented as part of the open-source RISC-V-based Vortex GPGPU's Tensor Core Unit extension. It supports lo","authors_text":"Blaise Tine, Nikhil Rout","cross_cats":[],"headline":"Ten-Four fuses floating-point and integer pipelines into one dot-product unit that runs mixed-precision matrix operations in four cycles.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2025-11-19T15:57:09Z","title":"Ten-Four: An Open-Source Fused Dot Product Unit for Mixed-Precision GPGPU Tensor Cores"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.00053","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-17T20:32:14.255485Z","id":"c7a68bf3-5005-48d4-8b28-716166a6e185","model_set":{"reader":"grok-4.3"},"one_line_summary":"Ten-Four delivers a fused mixed-precision dot-product unit for open-source GPGPUs that runs in 4 cycles at 262 MHz, matches NVIDIA numerical accuracy, and uses less than 60% the area of a prior open implementation while delivering 3.1x higher throughput.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Ten-Four fuses floating-point and integer pipelines into one dot-product unit that runs mixed-precision matrix operations in four cycles.","strongest_claim":"Ten-Four achieves 4-cycle operation latency at 262.325 MHz Fmax, delivering 134.308 GFLOPS peak throughput per Tensor Core on the AMD Xilinx Alveo U55C FPGA, demonstrating ~3.1x performance improvement over an equivalent Berkeley HardFloat-based implementation at less than 60% the area cost.","weakest_assumption":"That the fused pipeline preserves exact numerical equivalence to discrete units across all supported formats (FP16/BF16/FP8/BF8/INT8/INT4) without hidden rounding differences that only appear under specific input patterns or when integrated into the full Vortex Tensor Core."}},"verdict_id":"c7a68bf3-5005-48d4-8b28-716166a6e185"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:77cc5c2a0ed8ab854ec9cbef149939794d8554dfd8e623186f2afd3d1b8bd94a","target":"record","created_at":"2026-06-12T01:09:17Z","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":"894fbefdede516dc5790e0d6455a94ec946cb2cfcd4166046a9fc71ab9f75cd7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2025-11-19T15:57:09Z","title_canon_sha256":"9a16540b679ce3b1d3f9b511bcb58992b05470451552dbf60d8f66c60b597aa9"},"schema_version":"1.0","source":{"id":"2512.00053","kind":"arxiv","version":3}},"canonical_sha256":"6f4bdf8cecd359847e94a22af1d75c241c251723eb7bc646fb2d84ea3a4daf76","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6f4bdf8cecd359847e94a22af1d75c241c251723eb7bc646fb2d84ea3a4daf76","first_computed_at":"2026-06-12T01:09:17.297750Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-12T01:09:17.297750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AKNGRuiYTar2h4Ym3tf6ZmPz9bv8/gWvUfq/o92QnwrE7Kn3sKuFRDGU3gUV8dSW82JWxb9DiJUvV4XMlgDHCw==","signature_status":"signed_v1","signed_at":"2026-06-12T01:09:17.298653Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.00053","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:77cc5c2a0ed8ab854ec9cbef149939794d8554dfd8e623186f2afd3d1b8bd94a","sha256:72d78f5b8c6e4d5d2040379186b5c88f30193feacce112914d323985e6f58fed"],"state_sha256":"d02576ac866652c4ee3bc46e2bfb2959eb8188a153b53e3a96d6fe37a4571af8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zZz/ordO8g4pOXVVyLk5PgmJR+SUkG2n+QtKK3KYkAAD+LW4JhtwTG+kIUA0EEnZdqGos3s9ntP+dWJWNWi4CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T21:35:47.880878Z","bundle_sha256":"de1e610d1ff7e3d265bf256e4aa2733bad7cfbc17125840740a039c131aa043c"}}