{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:RGWD5HDFQ4EDDQ3S2ZT74PWHUB","short_pith_number":"pith:RGWD5HDF","canonical_record":{"source":{"id":"2312.17238","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-28T18:58:13Z","cross_cats_sorted":["cs.AI","cs.DC"],"title_canon_sha256":"226648469ab81c9fc578e389d28db919aea1c0cde320a3ae42bb8429648b81eb","abstract_canon_sha256":"97257f25cfbb8d3f86629495107dd73d7f77e67255ba1992ad9d37f5c36fa5fd"},"schema_version":"1.0"},"canonical_sha256":"89ac3e9c65870831c372d667fe3ec7a05bf11ebeff3b0b0a63530748e7272371","source":{"kind":"arxiv","id":"2312.17238","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.17238","created_at":"2026-07-05T07:28:41Z"},{"alias_kind":"arxiv_version","alias_value":"2312.17238v1","created_at":"2026-07-05T07:28:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.17238","created_at":"2026-07-05T07:28:41Z"},{"alias_kind":"pith_short_12","alias_value":"RGWD5HDFQ4ED","created_at":"2026-07-05T07:28:41Z"},{"alias_kind":"pith_short_16","alias_value":"RGWD5HDFQ4EDDQ3S","created_at":"2026-07-05T07:28:41Z"},{"alias_kind":"pith_short_8","alias_value":"RGWD5HDF","created_at":"2026-07-05T07:28:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:RGWD5HDFQ4EDDQ3S2ZT74PWHUB","target":"record","payload":{"canonical_record":{"source":{"id":"2312.17238","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-28T18:58:13Z","cross_cats_sorted":["cs.AI","cs.DC"],"title_canon_sha256":"226648469ab81c9fc578e389d28db919aea1c0cde320a3ae42bb8429648b81eb","abstract_canon_sha256":"97257f25cfbb8d3f86629495107dd73d7f77e67255ba1992ad9d37f5c36fa5fd"},"schema_version":"1.0"},"canonical_sha256":"89ac3e9c65870831c372d667fe3ec7a05bf11ebeff3b0b0a63530748e7272371","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:28:41.232553Z","signature_b64":"2yb5ydJmB2XzHsq4YjNuJf6fRdftnNOQOuW6wEiqE69RQOmGDL3zgYqMkRhwvkyyyw5TbCLc2CVNkOd3CUgOBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89ac3e9c65870831c372d667fe3ec7a05bf11ebeff3b0b0a63530748e7272371","last_reissued_at":"2026-07-05T07:28:41.232127Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:28:41.232127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.17238","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":"2026-07-05T07:28:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rmlQgf3lwM0UPjt6B6MqgavBNoUbAVNxwiTuqH7h3gO6OjrhDUTtc0DV8LOo16Cc1hEnWlojrOhn9aXfIDFaAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:48:37.477776Z"},"content_sha256":"5d153976034bd4922353360249acd2e37dbea86a5a0d8ea3a4264880b1e46da2","schema_version":"1.0","event_id":"sha256:5d153976034bd4922353360249acd2e37dbea86a5a0d8ea3a4264880b1e46da2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:RGWD5HDFQ4EDDQ3S2ZT74PWHUB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fast Inference of Mixture-of-Experts Language Models with Offloading","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Artyom Eliseev, Denis Mazur","submitted_at":"2023-12-28T18:58:13Z","abstract_excerpt":"With the widespread adoption of Large Language Models (LLMs), many deep learning practitioners are looking for strategies of running these models more efficiently. One such strategy is to use sparse Mixture-of-Experts (MoE) - a type of model architectures where only a fraction of model layers are active for any given input. This property allows MoE-based language models to generate tokens faster than their dense counterparts, but it also increases model size due to having multiple experts. Unfortunately, this makes state-of-the-art MoE language models difficult to run without high-end GPUs. In"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.17238","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/2312.17238/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":"2026-07-05T07:28:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FhxZraoi/ieBRvoJLNPy2i7BtAqpKkWypn9tC62yiFz75JNxjtxDUEc2S+/EzSVoNDroZMEVM2bibfOm4GUiDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:48:37.478165Z"},"content_sha256":"f43a65dcf1ad461bbad16a6937257abceabf9c85b3f0ea1dd7822d3a8f854c2a","schema_version":"1.0","event_id":"sha256:f43a65dcf1ad461bbad16a6937257abceabf9c85b3f0ea1dd7822d3a8f854c2a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RGWD5HDFQ4EDDQ3S2ZT74PWHUB/bundle.json","state_url":"https://pith.science/pith/RGWD5HDFQ4EDDQ3S2ZT74PWHUB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RGWD5HDFQ4EDDQ3S2ZT74PWHUB/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":"2026-07-09T06:48:37Z","links":{"resolver":"https://pith.science/pith/RGWD5HDFQ4EDDQ3S2ZT74PWHUB","bundle":"https://pith.science/pith/RGWD5HDFQ4EDDQ3S2ZT74PWHUB/bundle.json","state":"https://pith.science/pith/RGWD5HDFQ4EDDQ3S2ZT74PWHUB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RGWD5HDFQ4EDDQ3S2ZT74PWHUB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RGWD5HDFQ4EDDQ3S2ZT74PWHUB","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":"97257f25cfbb8d3f86629495107dd73d7f77e67255ba1992ad9d37f5c36fa5fd","cross_cats_sorted":["cs.AI","cs.DC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-28T18:58:13Z","title_canon_sha256":"226648469ab81c9fc578e389d28db919aea1c0cde320a3ae42bb8429648b81eb"},"schema_version":"1.0","source":{"id":"2312.17238","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.17238","created_at":"2026-07-05T07:28:41Z"},{"alias_kind":"arxiv_version","alias_value":"2312.17238v1","created_at":"2026-07-05T07:28:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.17238","created_at":"2026-07-05T07:28:41Z"},{"alias_kind":"pith_short_12","alias_value":"RGWD5HDFQ4ED","created_at":"2026-07-05T07:28:41Z"},{"alias_kind":"pith_short_16","alias_value":"RGWD5HDFQ4EDDQ3S","created_at":"2026-07-05T07:28:41Z"},{"alias_kind":"pith_short_8","alias_value":"RGWD5HDF","created_at":"2026-07-05T07:28:41Z"}],"graph_snapshots":[{"event_id":"sha256:f43a65dcf1ad461bbad16a6937257abceabf9c85b3f0ea1dd7822d3a8f854c2a","target":"graph","created_at":"2026-07-05T07:28:41Z","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/2312.17238/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the widespread adoption of Large Language Models (LLMs), many deep learning practitioners are looking for strategies of running these models more efficiently. One such strategy is to use sparse Mixture-of-Experts (MoE) - a type of model architectures where only a fraction of model layers are active for any given input. This property allows MoE-based language models to generate tokens faster than their dense counterparts, but it also increases model size due to having multiple experts. Unfortunately, this makes state-of-the-art MoE language models difficult to run without high-end GPUs. In","authors_text":"Artyom Eliseev, Denis Mazur","cross_cats":["cs.AI","cs.DC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-28T18:58:13Z","title":"Fast Inference of Mixture-of-Experts Language Models with Offloading"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.17238","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":"sha256:5d153976034bd4922353360249acd2e37dbea86a5a0d8ea3a4264880b1e46da2","target":"record","created_at":"2026-07-05T07:28:41Z","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":"97257f25cfbb8d3f86629495107dd73d7f77e67255ba1992ad9d37f5c36fa5fd","cross_cats_sorted":["cs.AI","cs.DC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-28T18:58:13Z","title_canon_sha256":"226648469ab81c9fc578e389d28db919aea1c0cde320a3ae42bb8429648b81eb"},"schema_version":"1.0","source":{"id":"2312.17238","kind":"arxiv","version":1}},"canonical_sha256":"89ac3e9c65870831c372d667fe3ec7a05bf11ebeff3b0b0a63530748e7272371","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89ac3e9c65870831c372d667fe3ec7a05bf11ebeff3b0b0a63530748e7272371","first_computed_at":"2026-07-05T07:28:41.232127Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:28:41.232127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2yb5ydJmB2XzHsq4YjNuJf6fRdftnNOQOuW6wEiqE69RQOmGDL3zgYqMkRhwvkyyyw5TbCLc2CVNkOd3CUgOBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:28:41.232553Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.17238","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d153976034bd4922353360249acd2e37dbea86a5a0d8ea3a4264880b1e46da2","sha256:f43a65dcf1ad461bbad16a6937257abceabf9c85b3f0ea1dd7822d3a8f854c2a"],"state_sha256":"ae1fe939a7fbbd3a5cd9a5469a10c96a0540a9a7eb9738e006a4c7c21735a981"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u88eWFDdLGPpWknT7jXUcjNPOiYLLDqzgk7W8qjW3djmMvmAPtEyPUa5+NG1N1hQnh5kWfC8Qk291e5LG+yiDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T06:48:37.480539Z","bundle_sha256":"15deed0a6bd94a82c2a9d720157b419e81a544f65603ffefa6980ecffe7e3cfd"}}