{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MNKAKQ7527D3D3GFHKUY7NHRHS","short_pith_number":"pith:MNKAKQ75","canonical_record":{"source":{"id":"2510.18245","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-21T03:08:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0cef0b59fc135437be336a9e9bd6f5f1a486856ec6c6f966f0a677e1cdcb2acb","abstract_canon_sha256":"5775a70cb4239b87686a16af5fb48b2727086653ea461c66b9a8a15961e5137a"},"schema_version":"1.0"},"canonical_sha256":"63540543fdd7c7b1ecc53aa98fb4f13c8c5da36b95e244d4ec268ee262668fdb","source":{"kind":"arxiv","id":"2510.18245","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.18245","created_at":"2026-05-18T03:09:33Z"},{"alias_kind":"arxiv_version","alias_value":"2510.18245v3","created_at":"2026-05-18T03:09:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.18245","created_at":"2026-05-18T03:09:33Z"},{"alias_kind":"pith_short_12","alias_value":"MNKAKQ7527D3","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"MNKAKQ7527D3D3GF","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"MNKAKQ75","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MNKAKQ7527D3D3GFHKUY7NHRHS","target":"record","payload":{"canonical_record":{"source":{"id":"2510.18245","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-21T03:08:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0cef0b59fc135437be336a9e9bd6f5f1a486856ec6c6f966f0a677e1cdcb2acb","abstract_canon_sha256":"5775a70cb4239b87686a16af5fb48b2727086653ea461c66b9a8a15961e5137a"},"schema_version":"1.0"},"canonical_sha256":"63540543fdd7c7b1ecc53aa98fb4f13c8c5da36b95e244d4ec268ee262668fdb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:33.762072Z","signature_b64":"X0KJaLhyodL7p9DIoE5gZoTGnnzgcEyPLIbNp+mQPMsXxOfAnIGgzMNmYNjkcvuaZO3w1wdEojZEl2USvmrUBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63540543fdd7c7b1ecc53aa98fb4f13c8c5da36b95e244d4ec268ee262668fdb","last_reissued_at":"2026-05-18T03:09:33.761411Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:33.761411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2510.18245","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":"2026-05-18T03:09:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jx+xZCLCse6PhnYYQxn3BSVkSF9E4FUgNpumeP5QejoLT5Nf5PdAhWFGkDBLVorJ59wzTW5U3nlmVXY+qTL+AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T03:32:42.072679Z"},"content_sha256":"3265711542d179358675baffa7f594e8a9d6c4a194f0404ff40d8d143ba48b06","schema_version":"1.0","event_id":"sha256:3265711542d179358675baffa7f594e8a9d6c4a194f0404ff40d8d143ba48b06"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MNKAKQ7527D3D3GFHKUY7NHRHS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scaling Laws Meet Model Architecture: Toward Inference-Efficient LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Shivaram Venkataraman, Song Bian, Tao Yu, Youngsuk Park","submitted_at":"2025-10-21T03:08:48Z","abstract_excerpt":"Scaling the number of parameters and the size of training data has proven to be an effective strategy for improving large language model (LLM) performance. Yet, as these models grow increasingly powerful and widely deployed, the cost of inference has become a pressing concern. Despite its importance, the trade-off between model accuracy and inference efficiency remains underexplored. In this work, we examine how key architectural factors, hidden size, the allocation of parameters between MLP and attention (mlp-to-attention ratio), and grouped-query attention (GQA), influence both inference cos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.18245","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-18T03:09:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FHb5yNXH6VAffc5VrK3bF50saducsUs/pR9J8PDX5BxVIBbuiFxivg4OCFy+dLUfF45UPVoOzqQQUuYGSSl5Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T03:32:42.073035Z"},"content_sha256":"d582f23ed5413f8d7e21f8a7d3cacc5a1875bab09611ad3b487eb9cbe120b1fb","schema_version":"1.0","event_id":"sha256:d582f23ed5413f8d7e21f8a7d3cacc5a1875bab09611ad3b487eb9cbe120b1fb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MNKAKQ7527D3D3GFHKUY7NHRHS/bundle.json","state_url":"https://pith.science/pith/MNKAKQ7527D3D3GFHKUY7NHRHS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MNKAKQ7527D3D3GFHKUY7NHRHS/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":"2026-06-04T03:32:42Z","links":{"resolver":"https://pith.science/pith/MNKAKQ7527D3D3GFHKUY7NHRHS","bundle":"https://pith.science/pith/MNKAKQ7527D3D3GFHKUY7NHRHS/bundle.json","state":"https://pith.science/pith/MNKAKQ7527D3D3GFHKUY7NHRHS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MNKAKQ7527D3D3GFHKUY7NHRHS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MNKAKQ7527D3D3GFHKUY7NHRHS","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":"5775a70cb4239b87686a16af5fb48b2727086653ea461c66b9a8a15961e5137a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-21T03:08:48Z","title_canon_sha256":"0cef0b59fc135437be336a9e9bd6f5f1a486856ec6c6f966f0a677e1cdcb2acb"},"schema_version":"1.0","source":{"id":"2510.18245","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.18245","created_at":"2026-05-18T03:09:33Z"},{"alias_kind":"arxiv_version","alias_value":"2510.18245v3","created_at":"2026-05-18T03:09:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.18245","created_at":"2026-05-18T03:09:33Z"},{"alias_kind":"pith_short_12","alias_value":"MNKAKQ7527D3","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"MNKAKQ7527D3D3GF","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"MNKAKQ75","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:d582f23ed5413f8d7e21f8a7d3cacc5a1875bab09611ad3b487eb9cbe120b1fb","target":"graph","created_at":"2026-05-18T03:09:33Z","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"},"paper":{"abstract_excerpt":"Scaling the number of parameters and the size of training data has proven to be an effective strategy for improving large language model (LLM) performance. Yet, as these models grow increasingly powerful and widely deployed, the cost of inference has become a pressing concern. Despite its importance, the trade-off between model accuracy and inference efficiency remains underexplored. In this work, we examine how key architectural factors, hidden size, the allocation of parameters between MLP and attention (mlp-to-attention ratio), and grouped-query attention (GQA), influence both inference cos","authors_text":"Shivaram Venkataraman, Song Bian, Tao Yu, Youngsuk Park","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-21T03:08:48Z","title":"Scaling Laws Meet Model Architecture: Toward Inference-Efficient LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.18245","kind":"arxiv","version":3},"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":"sha256:3265711542d179358675baffa7f594e8a9d6c4a194f0404ff40d8d143ba48b06","target":"record","created_at":"2026-05-18T03:09:33Z","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":"5775a70cb4239b87686a16af5fb48b2727086653ea461c66b9a8a15961e5137a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-21T03:08:48Z","title_canon_sha256":"0cef0b59fc135437be336a9e9bd6f5f1a486856ec6c6f966f0a677e1cdcb2acb"},"schema_version":"1.0","source":{"id":"2510.18245","kind":"arxiv","version":3}},"canonical_sha256":"63540543fdd7c7b1ecc53aa98fb4f13c8c5da36b95e244d4ec268ee262668fdb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63540543fdd7c7b1ecc53aa98fb4f13c8c5da36b95e244d4ec268ee262668fdb","first_computed_at":"2026-05-18T03:09:33.761411Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:33.761411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X0KJaLhyodL7p9DIoE5gZoTGnnzgcEyPLIbNp+mQPMsXxOfAnIGgzMNmYNjkcvuaZO3w1wdEojZEl2USvmrUBg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:33.762072Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.18245","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3265711542d179358675baffa7f594e8a9d6c4a194f0404ff40d8d143ba48b06","sha256:d582f23ed5413f8d7e21f8a7d3cacc5a1875bab09611ad3b487eb9cbe120b1fb"],"state_sha256":"d64827b87ee8575b70f36ff81c21516c12b3a735e995b49b57d0bc84ebab7205"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uCt8ZvVYfOhYsTwWZMnxisx2ugNY1HmsgClZxoUGl8pavEtw5ZpvuKrpdDv3d6TLjWdUOdcjUBdE1Iw78uNNCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T03:32:42.075344Z","bundle_sha256":"707ae6fd782d02bb66f5493e657ea69dcc60d9fe5545c21ab9cb4b619469ec59"}}