{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:27GB7ZRJ5XO4IJJP6VMFRQI5TZ","short_pith_number":"pith:27GB7ZRJ","canonical_record":{"source":{"id":"2608.03457","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-04T10:53:02Z","cross_cats_sorted":[],"title_canon_sha256":"8954fec3ddb399b7d96086b68e6e61a8513b0130c20483470006d1039c903be8","abstract_canon_sha256":"d2d0e389d1b90aa8a256bbcea06c13a814d1ee38970565b553744a27576c5c4f"},"schema_version":"1.0"},"canonical_sha256":"d7cc1fe629edddc4252ff55858c11d9e48d9e7ec73c8e9138bc5a572b122542a","source":{"kind":"arxiv","id":"2608.03457","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03457","created_at":"2026-08-05T01:35:53Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03457v1","created_at":"2026-08-05T01:35:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03457","created_at":"2026-08-05T01:35:53Z"},{"alias_kind":"pith_short_12","alias_value":"27GB7ZRJ5XO4","created_at":"2026-08-05T01:35:53Z"},{"alias_kind":"pith_short_16","alias_value":"27GB7ZRJ5XO4IJJP","created_at":"2026-08-05T01:35:53Z"},{"alias_kind":"pith_short_8","alias_value":"27GB7ZRJ","created_at":"2026-08-05T01:35:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:27GB7ZRJ5XO4IJJP6VMFRQI5TZ","target":"record","payload":{"canonical_record":{"source":{"id":"2608.03457","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-04T10:53:02Z","cross_cats_sorted":[],"title_canon_sha256":"8954fec3ddb399b7d96086b68e6e61a8513b0130c20483470006d1039c903be8","abstract_canon_sha256":"d2d0e389d1b90aa8a256bbcea06c13a814d1ee38970565b553744a27576c5c4f"},"schema_version":"1.0"},"canonical_sha256":"d7cc1fe629edddc4252ff55858c11d9e48d9e7ec73c8e9138bc5a572b122542a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T01:35:53.638940Z","signature_b64":"uX8gNAwGpGHDw9OvCci9jidRqY25aptlkYbOOJqeZBK42BqYzNkGD2EPi4z8nwDthHTGxKZenAHGCVaSnJdjDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7cc1fe629edddc4252ff55858c11d9e48d9e7ec73c8e9138bc5a572b122542a","last_reissued_at":"2026-08-05T01:35:53.637426Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T01:35:53.637426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.03457","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":"2026-08-05T01:35:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r6+UpVL+cl7MDSJeOzcLkPsfgC7IwmZ+8k31P5HqsmMmiAX/JR+tuGpyaMnTb7OraanHeDE40mb49R7E+5aIDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T07:00:07.570421Z"},"content_sha256":"392b75458bba4d2558c569efea6cd3362f45842a95c92888a2869930f986cc58","schema_version":"1.0","event_id":"sha256:392b75458bba4d2558c569efea6cd3362f45842a95c92888a2869930f986cc58"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:27GB7ZRJ5XO4IJJP6VMFRQI5TZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLaDA MoE v2: Scaling Mixture-of-Experts Diffusion Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chongxuan Li, Fengqi Zhu, Huabin Liu, Jianguo Li, Jingyang Ou, Ji-Rong Wen, Jun Zhou, Shaoxuan Xu, Wayne Xin Zhao, Xiaolu Zhang, Yankai Lin, Yipeng Xing, Zebin You, Zhenzhong Lan","submitted_at":"2026-08-04T10:53:02Z","abstract_excerpt":"Diffusion language models (dLLMs) offer an alternative to autoregressive (AR) language modeling, yet the scaling behavior of Mixture-of-Experts (MoE) dLLMs remains poorly understood. We systematically characterize how optimization hyperparameters, compute allocation, and architecture scale for MoE dLLMs, identifying quantitative differences from scaling trends previously reported for AR models. Specifically, for optimization, the optimal nominal batch size grows faster, while the optimal learning rate decays more rapidly with compute. For model--data allocation, IsoFLOP analysis reveals a slig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03457","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/2608.03457/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":"2026-08-05T01:35:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"urwv1PcgA0CoX3AcXdUt6VQMIykNKDEWD+f8BGHUGASEXLuv9CimI6/q3/lC487rLAch/PhiY5JQpQLZtxXNAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T07:00:07.570939Z"},"content_sha256":"acf4a57fd3295ca2d86096d3f40575e1d06840a1bc82d43a9b7edbe1673631b4","schema_version":"1.0","event_id":"sha256:acf4a57fd3295ca2d86096d3f40575e1d06840a1bc82d43a9b7edbe1673631b4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/27GB7ZRJ5XO4IJJP6VMFRQI5TZ/bundle.json","state_url":"https://pith.science/pith/27GB7ZRJ5XO4IJJP6VMFRQI5TZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/27GB7ZRJ5XO4IJJP6VMFRQI5TZ/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":"2026-08-22T07:00:07Z","links":{"resolver":"https://pith.science/pith/27GB7ZRJ5XO4IJJP6VMFRQI5TZ","bundle":"https://pith.science/pith/27GB7ZRJ5XO4IJJP6VMFRQI5TZ/bundle.json","state":"https://pith.science/pith/27GB7ZRJ5XO4IJJP6VMFRQI5TZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/27GB7ZRJ5XO4IJJP6VMFRQI5TZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:27GB7ZRJ5XO4IJJP6VMFRQI5TZ","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":"d2d0e389d1b90aa8a256bbcea06c13a814d1ee38970565b553744a27576c5c4f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-04T10:53:02Z","title_canon_sha256":"8954fec3ddb399b7d96086b68e6e61a8513b0130c20483470006d1039c903be8"},"schema_version":"1.0","source":{"id":"2608.03457","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03457","created_at":"2026-08-05T01:35:53Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03457v1","created_at":"2026-08-05T01:35:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03457","created_at":"2026-08-05T01:35:53Z"},{"alias_kind":"pith_short_12","alias_value":"27GB7ZRJ5XO4","created_at":"2026-08-05T01:35:53Z"},{"alias_kind":"pith_short_16","alias_value":"27GB7ZRJ5XO4IJJP","created_at":"2026-08-05T01:35:53Z"},{"alias_kind":"pith_short_8","alias_value":"27GB7ZRJ","created_at":"2026-08-05T01:35:53Z"}],"graph_snapshots":[{"event_id":"sha256:acf4a57fd3295ca2d86096d3f40575e1d06840a1bc82d43a9b7edbe1673631b4","target":"graph","created_at":"2026-08-05T01:35:53Z","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/2608.03457/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion language models (dLLMs) offer an alternative to autoregressive (AR) language modeling, yet the scaling behavior of Mixture-of-Experts (MoE) dLLMs remains poorly understood. We systematically characterize how optimization hyperparameters, compute allocation, and architecture scale for MoE dLLMs, identifying quantitative differences from scaling trends previously reported for AR models. Specifically, for optimization, the optimal nominal batch size grows faster, while the optimal learning rate decays more rapidly with compute. For model--data allocation, IsoFLOP analysis reveals a slig","authors_text":"Chongxuan Li, Fengqi Zhu, Huabin Liu, Jianguo Li, Jingyang Ou, Ji-Rong Wen, Jun Zhou, Shaoxuan Xu, Wayne Xin Zhao, Xiaolu Zhang, Yankai Lin, Yipeng Xing, Zebin You, Zhenzhong Lan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-04T10:53:02Z","title":"LLaDA MoE v2: Scaling Mixture-of-Experts Diffusion Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03457","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":"sha256:392b75458bba4d2558c569efea6cd3362f45842a95c92888a2869930f986cc58","target":"record","created_at":"2026-08-05T01:35:53Z","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":"d2d0e389d1b90aa8a256bbcea06c13a814d1ee38970565b553744a27576c5c4f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-04T10:53:02Z","title_canon_sha256":"8954fec3ddb399b7d96086b68e6e61a8513b0130c20483470006d1039c903be8"},"schema_version":"1.0","source":{"id":"2608.03457","kind":"arxiv","version":1}},"canonical_sha256":"d7cc1fe629edddc4252ff55858c11d9e48d9e7ec73c8e9138bc5a572b122542a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d7cc1fe629edddc4252ff55858c11d9e48d9e7ec73c8e9138bc5a572b122542a","first_computed_at":"2026-08-05T01:35:53.637426Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T01:35:53.637426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uX8gNAwGpGHDw9OvCci9jidRqY25aptlkYbOOJqeZBK42BqYzNkGD2EPi4z8nwDthHTGxKZenAHGCVaSnJdjDg==","signature_status":"signed_v1","signed_at":"2026-08-05T01:35:53.638940Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.03457","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:392b75458bba4d2558c569efea6cd3362f45842a95c92888a2869930f986cc58","sha256:acf4a57fd3295ca2d86096d3f40575e1d06840a1bc82d43a9b7edbe1673631b4"],"state_sha256":"ea8671fe644280cb84f515fcb4e96a0f56117433beebe80508afec276660ad94"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UQe9/4wjDu7t/iTD4FNVXG3RkFQliVplJH8dc/Tyu69bB6MAKG1jJN9Rm2KMut3CCFp+cmFqoy5l0jwPDrOJAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T07:00:07.576080Z","bundle_sha256":"2f0e6cd2127747b8851393af82347932667e6a2a48c1db9a992f8009124ae466"}}