{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YMK5LGUWFOZ2SXHPTBZAXRPHAK","short_pith_number":"pith:YMK5LGUW","canonical_record":{"source":{"id":"2406.07524","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-11T17:51:40Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f23d13d793e1264a69fb49966a0b2f97b6c97492837e871b10da955831d4135e","abstract_canon_sha256":"1ff6a4904c916ed856edf5d8f0892ac0491d1bd80eebbcdfdb7fef4f5abb060b"},"schema_version":"1.0"},"canonical_sha256":"c315d59a962bb3a95cef98720bc5e702afcb4ff76063e0db2732b1c86ee4bbef","source":{"kind":"arxiv","id":"2406.07524","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.07524","created_at":"2026-07-05T09:33:33Z"},{"alias_kind":"arxiv_version","alias_value":"2406.07524v2","created_at":"2026-07-05T09:33:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07524","created_at":"2026-07-05T09:33:33Z"},{"alias_kind":"pith_short_12","alias_value":"YMK5LGUWFOZ2","created_at":"2026-07-05T09:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"YMK5LGUWFOZ2SXHP","created_at":"2026-07-05T09:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"YMK5LGUW","created_at":"2026-07-05T09:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YMK5LGUWFOZ2SXHPTBZAXRPHAK","target":"record","payload":{"canonical_record":{"source":{"id":"2406.07524","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-11T17:51:40Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f23d13d793e1264a69fb49966a0b2f97b6c97492837e871b10da955831d4135e","abstract_canon_sha256":"1ff6a4904c916ed856edf5d8f0892ac0491d1bd80eebbcdfdb7fef4f5abb060b"},"schema_version":"1.0"},"canonical_sha256":"c315d59a962bb3a95cef98720bc5e702afcb4ff76063e0db2732b1c86ee4bbef","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:33:33.073232Z","signature_b64":"lHUFvNbRsXTJKHBTnMeushRP4OaoWnmgvJnQ8SUWyXi/Qjl3LiRIpSkGeVP23lWqY7vIFFQIUfi6Ba8ZTdyjCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c315d59a962bb3a95cef98720bc5e702afcb4ff76063e0db2732b1c86ee4bbef","last_reissued_at":"2026-07-05T09:33:33.072758Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:33:33.072758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.07524","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:33:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bw75twASsOGzXobYvhZVHPuaJiNN/CQBjHblKIxUnt6IqF2um139k/sa4zAzMRQqinP/R5aXSGVqVRTuoczZBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:30:51.649362Z"},"content_sha256":"bc54eaf82997398d55805ca53bc911910553626c22790e313199ac2aed01c877","schema_version":"1.0","event_id":"sha256:bc54eaf82997398d55805ca53bc911910553626c22790e313199ac2aed01c877"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YMK5LGUWFOZ2SXHPTBZAXRPHAK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Simple and Effective Masked Diffusion Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aaron Gokaslan, Alexander Rush, Edgar Marroquin, Justin T Chiu, Marianne Arriola, Subham Sekhar Sahoo, Volodymyr Kuleshov, Yair Schiff","submitted_at":"2024-06-11T17:51:40Z","abstract_excerpt":"While diffusion models excel at generating high-quality images, prior work reports a significant performance gap between diffusion and autoregressive (AR) methods in language modeling. In this work, we show that simple masked discrete diffusion is more performant than previously thought. We apply an effective training recipe that improves the performance of masked diffusion models and derive a simplified, Rao-Blackwellized objective that results in additional improvements. Our objective has a simple form -- it is a mixture of classical masked language modeling losses -- and can be used to trai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07524","kind":"arxiv","version":2},"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/2406.07524/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":"2026-07-05T09:33:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qAA3oULnixiSa28GshKJdDMor0NhSF/Q2a9eKofj/YY0CO2W20nWX/c2sZK+BFFhFdDU3qjElKCUqCI+k2AhDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:30:51.649919Z"},"content_sha256":"777806d47c3e54a7d6d36951c1b455cae57d398d7698443b3e30bd7953e9b357","schema_version":"1.0","event_id":"sha256:777806d47c3e54a7d6d36951c1b455cae57d398d7698443b3e30bd7953e9b357"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YMK5LGUWFOZ2SXHPTBZAXRPHAK/bundle.json","state_url":"https://pith.science/pith/YMK5LGUWFOZ2SXHPTBZAXRPHAK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YMK5LGUWFOZ2SXHPTBZAXRPHAK/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":"2026-08-04T23:30:51Z","links":{"resolver":"https://pith.science/pith/YMK5LGUWFOZ2SXHPTBZAXRPHAK","bundle":"https://pith.science/pith/YMK5LGUWFOZ2SXHPTBZAXRPHAK/bundle.json","state":"https://pith.science/pith/YMK5LGUWFOZ2SXHPTBZAXRPHAK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YMK5LGUWFOZ2SXHPTBZAXRPHAK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YMK5LGUWFOZ2SXHPTBZAXRPHAK","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":"1ff6a4904c916ed856edf5d8f0892ac0491d1bd80eebbcdfdb7fef4f5abb060b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-11T17:51:40Z","title_canon_sha256":"f23d13d793e1264a69fb49966a0b2f97b6c97492837e871b10da955831d4135e"},"schema_version":"1.0","source":{"id":"2406.07524","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.07524","created_at":"2026-07-05T09:33:33Z"},{"alias_kind":"arxiv_version","alias_value":"2406.07524v2","created_at":"2026-07-05T09:33:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07524","created_at":"2026-07-05T09:33:33Z"},{"alias_kind":"pith_short_12","alias_value":"YMK5LGUWFOZ2","created_at":"2026-07-05T09:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"YMK5LGUWFOZ2SXHP","created_at":"2026-07-05T09:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"YMK5LGUW","created_at":"2026-07-05T09:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:777806d47c3e54a7d6d36951c1b455cae57d398d7698443b3e30bd7953e9b357","target":"graph","created_at":"2026-07-05T09:33:33Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2406.07524/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While diffusion models excel at generating high-quality images, prior work reports a significant performance gap between diffusion and autoregressive (AR) methods in language modeling. In this work, we show that simple masked discrete diffusion is more performant than previously thought. We apply an effective training recipe that improves the performance of masked diffusion models and derive a simplified, Rao-Blackwellized objective that results in additional improvements. Our objective has a simple form -- it is a mixture of classical masked language modeling losses -- and can be used to trai","authors_text":"Aaron Gokaslan, Alexander Rush, Edgar Marroquin, Justin T Chiu, Marianne Arriola, Subham Sekhar Sahoo, Volodymyr Kuleshov, Yair Schiff","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-11T17:51:40Z","title":"Simple and Effective Masked Diffusion Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07524","kind":"arxiv","version":2},"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:bc54eaf82997398d55805ca53bc911910553626c22790e313199ac2aed01c877","target":"record","created_at":"2026-07-05T09:33:33Z","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":"1ff6a4904c916ed856edf5d8f0892ac0491d1bd80eebbcdfdb7fef4f5abb060b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-11T17:51:40Z","title_canon_sha256":"f23d13d793e1264a69fb49966a0b2f97b6c97492837e871b10da955831d4135e"},"schema_version":"1.0","source":{"id":"2406.07524","kind":"arxiv","version":2}},"canonical_sha256":"c315d59a962bb3a95cef98720bc5e702afcb4ff76063e0db2732b1c86ee4bbef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c315d59a962bb3a95cef98720bc5e702afcb4ff76063e0db2732b1c86ee4bbef","first_computed_at":"2026-07-05T09:33:33.072758Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:33:33.072758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lHUFvNbRsXTJKHBTnMeushRP4OaoWnmgvJnQ8SUWyXi/Qjl3LiRIpSkGeVP23lWqY7vIFFQIUfi6Ba8ZTdyjCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:33:33.073232Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.07524","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc54eaf82997398d55805ca53bc911910553626c22790e313199ac2aed01c877","sha256:777806d47c3e54a7d6d36951c1b455cae57d398d7698443b3e30bd7953e9b357"],"state_sha256":"5ea7588a5779d3bc35a11a4ef483b8e986410f4c1daf186219997b91f879c88e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8sv9iIWYn4fOPS1vu7BxXLOxpHxbT7cd6ngyh+WbDGvCK0/Mij7Un6rATH7ROVJfOHV1EEBSCuF5Xf3gyriOAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T23:30:51.653487Z","bundle_sha256":"b1dafbe0d66003f6173affc4b887e3a9869f0781b20852124f99fac5efa96e9f"}}