{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:F7WTJQEMEGX6OYYVRQPJQZJ6LW","short_pith_number":"pith:F7WTJQEM","canonical_record":{"source":{"id":"2407.21046","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-22T18:00:00Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"857cd5f4dcaacde707afd23e7d44286af041f7991e1c0e2dd4211cd4ddad9a6e","abstract_canon_sha256":"e6075b5dadacc0fa19efe825ca01b214f226e08477d7495c04b3e63e7d13da13"},"schema_version":"1.0"},"canonical_sha256":"2fed34c08c21afe763158c1e98653e5db8759c8d32dc0311eb3a465edf0bfe10","source":{"kind":"arxiv","id":"2407.21046","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.21046","created_at":"2026-07-05T08:50:32Z"},{"alias_kind":"arxiv_version","alias_value":"2407.21046v1","created_at":"2026-07-05T08:50:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.21046","created_at":"2026-07-05T08:50:32Z"},{"alias_kind":"pith_short_12","alias_value":"F7WTJQEMEGX6","created_at":"2026-07-05T08:50:32Z"},{"alias_kind":"pith_short_16","alias_value":"F7WTJQEMEGX6OYYV","created_at":"2026-07-05T08:50:32Z"},{"alias_kind":"pith_short_8","alias_value":"F7WTJQEM","created_at":"2026-07-05T08:50:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:F7WTJQEMEGX6OYYVRQPJQZJ6LW","target":"record","payload":{"canonical_record":{"source":{"id":"2407.21046","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-22T18:00:00Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"857cd5f4dcaacde707afd23e7d44286af041f7991e1c0e2dd4211cd4ddad9a6e","abstract_canon_sha256":"e6075b5dadacc0fa19efe825ca01b214f226e08477d7495c04b3e63e7d13da13"},"schema_version":"1.0"},"canonical_sha256":"2fed34c08c21afe763158c1e98653e5db8759c8d32dc0311eb3a465edf0bfe10","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:50:32.831279Z","signature_b64":"EG8si2UlF32JnO/opX9wyk1llnv/VWJI5jKZxcH2bdoDUQ2IIra1G9TPpaGhDWTcvTUxC+YzR1VfRDCSg2WWBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fed34c08c21afe763158c1e98653e5db8759c8d32dc0311eb3a465edf0bfe10","last_reissued_at":"2026-07-05T08:50:32.830738Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:50:32.830738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.21046","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":"2026-07-05T08:50:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DfAnZS7x9KR6jzwSQoHvNelu7tegJYG69woIs50PRCPDLNK3OGepXNHF8qcqMd6qb+YCPzFCyGf4L8X55hrSBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:57:36.834695Z"},"content_sha256":"ca25bc669e17078e13c9e5060a107c7db60df5761fc64ac557556a444c9dceda","schema_version":"1.0","event_id":"sha256:ca25bc669e17078e13c9e5060a107c7db60df5761fc64ac557556a444c9dceda"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:F7WTJQEMEGX6OYYVRQPJQZJ6LW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Promises and Pitfalls of Generative Masked Language Modeling: Theoretical Framework and Practical Guidelines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Aashay Mehta, Alexandre Kirchmeyer, Andrej Risteski, Boris Dadachev, Kishore Papineni, Sanjiv Kumar, Yilong Qin, Yuchen Li","submitted_at":"2024-07-22T18:00:00Z","abstract_excerpt":"Autoregressive language models are the currently dominant paradigm for text generation, but they have some fundamental limitations that cannot be remedied by scale-for example inherently sequential and unidirectional generation. While alternate classes of models have been explored, we have limited mathematical understanding of their fundamental power and limitations. In this paper we focus on Generative Masked Language Models (GMLMs), a non-autoregressive paradigm in which we train a model to fit conditional probabilities of the data distribution via masking, which are subsequently used as inp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.21046","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/2407.21046/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":"2026-07-05T08:50:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ig5yM42XdDP9cknXCUu2jbIz72p1FWsCCESmMvh5FI9Lja3ZJP++VnPkQ5Cg2oTTIrQqtWgCaqPxSbSDhRUvDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:57:36.835567Z"},"content_sha256":"cb759f12ba0fe9b752ee3014d60061563a3f4feb55671640996cc456c49e14c6","schema_version":"1.0","event_id":"sha256:cb759f12ba0fe9b752ee3014d60061563a3f4feb55671640996cc456c49e14c6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F7WTJQEMEGX6OYYVRQPJQZJ6LW/bundle.json","state_url":"https://pith.science/pith/F7WTJQEMEGX6OYYVRQPJQZJ6LW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F7WTJQEMEGX6OYYVRQPJQZJ6LW/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":"2026-08-03T19:57:36Z","links":{"resolver":"https://pith.science/pith/F7WTJQEMEGX6OYYVRQPJQZJ6LW","bundle":"https://pith.science/pith/F7WTJQEMEGX6OYYVRQPJQZJ6LW/bundle.json","state":"https://pith.science/pith/F7WTJQEMEGX6OYYVRQPJQZJ6LW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F7WTJQEMEGX6OYYVRQPJQZJ6LW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:F7WTJQEMEGX6OYYVRQPJQZJ6LW","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":"e6075b5dadacc0fa19efe825ca01b214f226e08477d7495c04b3e63e7d13da13","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-22T18:00:00Z","title_canon_sha256":"857cd5f4dcaacde707afd23e7d44286af041f7991e1c0e2dd4211cd4ddad9a6e"},"schema_version":"1.0","source":{"id":"2407.21046","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.21046","created_at":"2026-07-05T08:50:32Z"},{"alias_kind":"arxiv_version","alias_value":"2407.21046v1","created_at":"2026-07-05T08:50:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.21046","created_at":"2026-07-05T08:50:32Z"},{"alias_kind":"pith_short_12","alias_value":"F7WTJQEMEGX6","created_at":"2026-07-05T08:50:32Z"},{"alias_kind":"pith_short_16","alias_value":"F7WTJQEMEGX6OYYV","created_at":"2026-07-05T08:50:32Z"},{"alias_kind":"pith_short_8","alias_value":"F7WTJQEM","created_at":"2026-07-05T08:50:32Z"}],"graph_snapshots":[{"event_id":"sha256:cb759f12ba0fe9b752ee3014d60061563a3f4feb55671640996cc456c49e14c6","target":"graph","created_at":"2026-07-05T08:50:32Z","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/2407.21046/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Autoregressive language models are the currently dominant paradigm for text generation, but they have some fundamental limitations that cannot be remedied by scale-for example inherently sequential and unidirectional generation. While alternate classes of models have been explored, we have limited mathematical understanding of their fundamental power and limitations. In this paper we focus on Generative Masked Language Models (GMLMs), a non-autoregressive paradigm in which we train a model to fit conditional probabilities of the data distribution via masking, which are subsequently used as inp","authors_text":"Aashay Mehta, Alexandre Kirchmeyer, Andrej Risteski, Boris Dadachev, Kishore Papineni, Sanjiv Kumar, Yilong Qin, Yuchen Li","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-22T18:00:00Z","title":"Promises and Pitfalls of Generative Masked Language Modeling: Theoretical Framework and Practical Guidelines"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.21046","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:ca25bc669e17078e13c9e5060a107c7db60df5761fc64ac557556a444c9dceda","target":"record","created_at":"2026-07-05T08:50:32Z","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":"e6075b5dadacc0fa19efe825ca01b214f226e08477d7495c04b3e63e7d13da13","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-22T18:00:00Z","title_canon_sha256":"857cd5f4dcaacde707afd23e7d44286af041f7991e1c0e2dd4211cd4ddad9a6e"},"schema_version":"1.0","source":{"id":"2407.21046","kind":"arxiv","version":1}},"canonical_sha256":"2fed34c08c21afe763158c1e98653e5db8759c8d32dc0311eb3a465edf0bfe10","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2fed34c08c21afe763158c1e98653e5db8759c8d32dc0311eb3a465edf0bfe10","first_computed_at":"2026-07-05T08:50:32.830738Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:50:32.830738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EG8si2UlF32JnO/opX9wyk1llnv/VWJI5jKZxcH2bdoDUQ2IIra1G9TPpaGhDWTcvTUxC+YzR1VfRDCSg2WWBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:50:32.831279Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.21046","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca25bc669e17078e13c9e5060a107c7db60df5761fc64ac557556a444c9dceda","sha256:cb759f12ba0fe9b752ee3014d60061563a3f4feb55671640996cc456c49e14c6"],"state_sha256":"9518b8376af134e74cd9d35d355bf579b7bb573a7cb260f04aa9c7300f2fb338"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2PNsDHZ2iS3vBR5bLiNk9GS+fhe7yg2PRoT8m0UPNdLqSB+RdVNgoJ/DuB/xmZWjdXJiAxKTVZ90MmgmRsU/DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T19:57:36.842532Z","bundle_sha256":"5db12df509ca406c9c0045256438483b29d356bef9fdfa43cb5bd5322c8ce9d1"}}