{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:K34V5MCNBWDKP5GRVP6BFQDSED","short_pith_number":"pith:K34V5MCN","canonical_record":{"source":{"id":"2507.19142","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AR","submitted_at":"2025-07-25T10:26:01Z","cross_cats_sorted":[],"title_canon_sha256":"602bff555e178fb5fd5779d736bfb6320d410d38600246f9312099a096015411","abstract_canon_sha256":"b1bd0f3f6c13dae79421f3a71c35be72c8b3147cfdc7e42815176761ff2078c3"},"schema_version":"1.0"},"canonical_sha256":"56f95eb04d0d86a7f4d1abfc12c07220f8640931e8a33b60f3eeac93ad2e5410","source":{"kind":"arxiv","id":"2507.19142","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.19142","created_at":"2026-07-05T11:43:20Z"},{"alias_kind":"arxiv_version","alias_value":"2507.19142v1","created_at":"2026-07-05T11:43:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19142","created_at":"2026-07-05T11:43:20Z"},{"alias_kind":"pith_short_12","alias_value":"K34V5MCNBWDK","created_at":"2026-07-05T11:43:20Z"},{"alias_kind":"pith_short_16","alias_value":"K34V5MCNBWDKP5GR","created_at":"2026-07-05T11:43:20Z"},{"alias_kind":"pith_short_8","alias_value":"K34V5MCN","created_at":"2026-07-05T11:43:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:K34V5MCNBWDKP5GRVP6BFQDSED","target":"record","payload":{"canonical_record":{"source":{"id":"2507.19142","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AR","submitted_at":"2025-07-25T10:26:01Z","cross_cats_sorted":[],"title_canon_sha256":"602bff555e178fb5fd5779d736bfb6320d410d38600246f9312099a096015411","abstract_canon_sha256":"b1bd0f3f6c13dae79421f3a71c35be72c8b3147cfdc7e42815176761ff2078c3"},"schema_version":"1.0"},"canonical_sha256":"56f95eb04d0d86a7f4d1abfc12c07220f8640931e8a33b60f3eeac93ad2e5410","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:20.319532Z","signature_b64":"rhG5gAL7UKAiB/WdnvqmvqrhM9nj7t2aD3pNQhlB19+Lj23amKWZpNdFdZ5HCNAzrHhn60TB+jI/GCaD9anWDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56f95eb04d0d86a7f4d1abfc12c07220f8640931e8a33b60f3eeac93ad2e5410","last_reissued_at":"2026-07-05T11:43:20.319015Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:20.319015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.19142","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":"2026-07-05T11:43:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nsBi7IKlUX7Fe3DhhSS5AcEeSh2oVTyXNkmneqDWE00Yezd0LkGKe52436GodcLM1QFXB8xHVFTUHOIJYzjfCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T19:35:08.696206Z"},"content_sha256":"90e6b762f2f96307d9c99a111d67a8c6f31c94761b29c0829b601bd58efd2057","schema_version":"1.0","event_id":"sha256:90e6b762f2f96307d9c99a111d67a8c6f31c94761b29c0829b601bd58efd2057"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:K34V5MCNBWDKP5GRVP6BFQDSED","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A3D-MoE: Acceleration of Large Language Models with Mixture of Experts via 3D Heterogeneous Integration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Cheng-Jhih Shih, Faaiq Waqar, Janak Sharda, Pin-Jun Chen, Shimeng Yu, Wei-Hsing Huang, Yingyan (Celine) Lin, Yuyao Kong","submitted_at":"2025-07-25T10:26:01Z","abstract_excerpt":"Conventional large language models (LLMs) are equipped with dozens of GB to TB of model parameters, making inference highly energy-intensive and costly as all the weights need to be loaded to onboard processing elements during computation. Recently, the Mixture-of-Experts (MoE) architecture has emerged as an efficient alternative, promising efficient inference with less activated weights per token. Nevertheless, fine-grained MoE-based LLMs face several challenges: 1) Variable workloads during runtime create arbitrary GEMV-GEMM ratios that reduce hardware utilization, 2) Traditional MoE-based s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19142","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/2507.19142/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":"2026-07-05T11:43:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"suAL/G2xJBa49yEgVyU0xX7tW0NZgp6jl96rgVBAjwGwcEjqw1fAsqRomiFddiuWQMN6FsVW9+soufiZv3VEAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T19:35:08.696953Z"},"content_sha256":"ab5f3cd30d63f9f82a3d9a23fb22e9de4e2895534097bf600894cf1c83ce910a","schema_version":"1.0","event_id":"sha256:ab5f3cd30d63f9f82a3d9a23fb22e9de4e2895534097bf600894cf1c83ce910a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K34V5MCNBWDKP5GRVP6BFQDSED/bundle.json","state_url":"https://pith.science/pith/K34V5MCNBWDKP5GRVP6BFQDSED/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K34V5MCNBWDKP5GRVP6BFQDSED/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":"2026-08-10T19:35:08Z","links":{"resolver":"https://pith.science/pith/K34V5MCNBWDKP5GRVP6BFQDSED","bundle":"https://pith.science/pith/K34V5MCNBWDKP5GRVP6BFQDSED/bundle.json","state":"https://pith.science/pith/K34V5MCNBWDKP5GRVP6BFQDSED/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K34V5MCNBWDKP5GRVP6BFQDSED/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:K34V5MCNBWDKP5GRVP6BFQDSED","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":"b1bd0f3f6c13dae79421f3a71c35be72c8b3147cfdc7e42815176761ff2078c3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AR","submitted_at":"2025-07-25T10:26:01Z","title_canon_sha256":"602bff555e178fb5fd5779d736bfb6320d410d38600246f9312099a096015411"},"schema_version":"1.0","source":{"id":"2507.19142","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.19142","created_at":"2026-07-05T11:43:20Z"},{"alias_kind":"arxiv_version","alias_value":"2507.19142v1","created_at":"2026-07-05T11:43:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19142","created_at":"2026-07-05T11:43:20Z"},{"alias_kind":"pith_short_12","alias_value":"K34V5MCNBWDK","created_at":"2026-07-05T11:43:20Z"},{"alias_kind":"pith_short_16","alias_value":"K34V5MCNBWDKP5GR","created_at":"2026-07-05T11:43:20Z"},{"alias_kind":"pith_short_8","alias_value":"K34V5MCN","created_at":"2026-07-05T11:43:20Z"}],"graph_snapshots":[{"event_id":"sha256:ab5f3cd30d63f9f82a3d9a23fb22e9de4e2895534097bf600894cf1c83ce910a","target":"graph","created_at":"2026-07-05T11:43:20Z","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/2507.19142/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Conventional large language models (LLMs) are equipped with dozens of GB to TB of model parameters, making inference highly energy-intensive and costly as all the weights need to be loaded to onboard processing elements during computation. Recently, the Mixture-of-Experts (MoE) architecture has emerged as an efficient alternative, promising efficient inference with less activated weights per token. Nevertheless, fine-grained MoE-based LLMs face several challenges: 1) Variable workloads during runtime create arbitrary GEMV-GEMM ratios that reduce hardware utilization, 2) Traditional MoE-based s","authors_text":"Cheng-Jhih Shih, Faaiq Waqar, Janak Sharda, Pin-Jun Chen, Shimeng Yu, Wei-Hsing Huang, Yingyan (Celine) Lin, Yuyao Kong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AR","submitted_at":"2025-07-25T10:26:01Z","title":"A3D-MoE: Acceleration of Large Language Models with Mixture of Experts via 3D Heterogeneous Integration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19142","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":"sha256:90e6b762f2f96307d9c99a111d67a8c6f31c94761b29c0829b601bd58efd2057","target":"record","created_at":"2026-07-05T11:43:20Z","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":"b1bd0f3f6c13dae79421f3a71c35be72c8b3147cfdc7e42815176761ff2078c3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AR","submitted_at":"2025-07-25T10:26:01Z","title_canon_sha256":"602bff555e178fb5fd5779d736bfb6320d410d38600246f9312099a096015411"},"schema_version":"1.0","source":{"id":"2507.19142","kind":"arxiv","version":1}},"canonical_sha256":"56f95eb04d0d86a7f4d1abfc12c07220f8640931e8a33b60f3eeac93ad2e5410","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"56f95eb04d0d86a7f4d1abfc12c07220f8640931e8a33b60f3eeac93ad2e5410","first_computed_at":"2026-07-05T11:43:20.319015Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:43:20.319015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rhG5gAL7UKAiB/WdnvqmvqrhM9nj7t2aD3pNQhlB19+Lj23amKWZpNdFdZ5HCNAzrHhn60TB+jI/GCaD9anWDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:43:20.319532Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.19142","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90e6b762f2f96307d9c99a111d67a8c6f31c94761b29c0829b601bd58efd2057","sha256:ab5f3cd30d63f9f82a3d9a23fb22e9de4e2895534097bf600894cf1c83ce910a"],"state_sha256":"79aeecf4d8b8e09c84cbd8c4d95f67ed701d63308b717ea6efdfdc0c63a8e042"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JlAWwtmaz2e9rDHiwd6YN2boiT09YRGDxXs+OQBnOI8BkF9P9JyzyqWQVYkt2NsdTFSCw5iN6kuNoWM93qCnBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T19:35:08.703591Z","bundle_sha256":"1bc92b1f81e0ef3ef95e323adf947bf8f4d1da5e2249ae778208dd110d99d700"}}