{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EPJWV7UZYF7WOQDBOBKS2XGQW6","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":"2c32918151a0def493fdc2d430d3ea326b3a8d21615359e8c9659262e68cf79d","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-10-24T08:01:22Z","title_canon_sha256":"a446b0e4198e626a1fbe9267839150be5a3b7d7f50984513fd1a38928a90454b"},"schema_version":"1.0","source":{"id":"2410.18514","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.18514","created_at":"2026-07-05T10:21:25Z"},{"alias_kind":"arxiv_version","alias_value":"2410.18514v3","created_at":"2026-07-05T10:21:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18514","created_at":"2026-07-05T10:21:25Z"},{"alias_kind":"pith_short_12","alias_value":"EPJWV7UZYF7W","created_at":"2026-07-05T10:21:25Z"},{"alias_kind":"pith_short_16","alias_value":"EPJWV7UZYF7WOQDB","created_at":"2026-07-05T10:21:25Z"},{"alias_kind":"pith_short_8","alias_value":"EPJWV7UZ","created_at":"2026-07-05T10:21:25Z"}],"graph_snapshots":[{"event_id":"sha256:10a98ce3775d35df1bc39f340759c93c9a738ac0596cb4e7b8e96c91279a28cd","target":"graph","created_at":"2026-07-05T10:21:25Z","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/2410.18514/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Masked diffusion models (MDMs) have shown promise in language modeling, yet their scalability and effectiveness in core language tasks, such as text generation and language understanding, remain underexplored. This paper establishes the first scaling law for MDMs, demonstrating a scaling rate comparable to autoregressive models (ARMs) and a relatively small compute gap. Motivated by their scalability, we train a family of MDMs with up to 1.1 billion (B) parameters to systematically evaluate their performance against ARMs of comparable or larger sizes. Fully leveraging the probabilistic formula","authors_text":"Chao Du, Chongxuan Li, Fengqi Zhu, Guangtao Zeng, Min Lin, Qian Liu, Shen Nie, Tianyu Pang","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-10-24T08:01:22Z","title":"Scaling up Masked Diffusion Models on Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18514","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":"sha256:65577500a0b8f9818dd802da3977e1ea8d3ba11285bc0fe48e86a433c0f8519b","target":"record","created_at":"2026-07-05T10:21:25Z","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":"2c32918151a0def493fdc2d430d3ea326b3a8d21615359e8c9659262e68cf79d","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-10-24T08:01:22Z","title_canon_sha256":"a446b0e4198e626a1fbe9267839150be5a3b7d7f50984513fd1a38928a90454b"},"schema_version":"1.0","source":{"id":"2410.18514","kind":"arxiv","version":3}},"canonical_sha256":"23d36afe99c17f67406170552d5cd0b7a6076ccb785b4a12707018433c5f32b4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23d36afe99c17f67406170552d5cd0b7a6076ccb785b4a12707018433c5f32b4","first_computed_at":"2026-07-05T10:21:25.364706Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:21:25.364706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Cm3S8AWGNswSd0gmHDwIQCdAt5ZkjfQZmIk3VJDeipvGXQKTxogQUoQi1uQ7iLn+Tq/tY/AsqS0pRi0WKEtPAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:21:25.365235Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.18514","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:65577500a0b8f9818dd802da3977e1ea8d3ba11285bc0fe48e86a433c0f8519b","sha256:10a98ce3775d35df1bc39f340759c93c9a738ac0596cb4e7b8e96c91279a28cd"],"state_sha256":"dab6ac659c52894a51be4c725c593cab281aad8ead9a56f6f65978127c884de9"}