{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:46GP7IXFFJGQUCVH7TCI7YW5DT","short_pith_number":"pith:46GP7IXF","canonical_record":{"source":{"id":"2508.14090","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-14T09:30:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dfcaad016fef7a624231e5c19c77969df6447e93340a2d4909db8dc9faca901a","abstract_canon_sha256":"a43f0566042ef7b98d8ca2940a6ee431815ef76f211e97905fb76ce7c626f3cc"},"schema_version":"1.0"},"canonical_sha256":"e78cffa2e52a4d0a0aa7fcc48fe2dd1cf00ea716fc4ca5049cd9cb97fecbff05","source":{"kind":"arxiv","id":"2508.14090","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.14090","created_at":"2026-07-05T11:59:20Z"},{"alias_kind":"arxiv_version","alias_value":"2508.14090v2","created_at":"2026-07-05T11:59:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.14090","created_at":"2026-07-05T11:59:20Z"},{"alias_kind":"pith_short_12","alias_value":"46GP7IXFFJGQ","created_at":"2026-07-05T11:59:20Z"},{"alias_kind":"pith_short_16","alias_value":"46GP7IXFFJGQUCVH","created_at":"2026-07-05T11:59:20Z"},{"alias_kind":"pith_short_8","alias_value":"46GP7IXF","created_at":"2026-07-05T11:59:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:46GP7IXFFJGQUCVH7TCI7YW5DT","target":"record","payload":{"canonical_record":{"source":{"id":"2508.14090","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-14T09:30:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dfcaad016fef7a624231e5c19c77969df6447e93340a2d4909db8dc9faca901a","abstract_canon_sha256":"a43f0566042ef7b98d8ca2940a6ee431815ef76f211e97905fb76ce7c626f3cc"},"schema_version":"1.0"},"canonical_sha256":"e78cffa2e52a4d0a0aa7fcc48fe2dd1cf00ea716fc4ca5049cd9cb97fecbff05","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:20.157650Z","signature_b64":"UIWofllV4bz6rOHktU1RGM4klMIePz49gK3N076DiF6VLVn7kvOYYz8LujKgfdtNtGTTw/ZlXs2U7utJN1P3Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e78cffa2e52a4d0a0aa7fcc48fe2dd1cf00ea716fc4ca5049cd9cb97fecbff05","last_reissued_at":"2026-07-05T11:59:20.157185Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:20.157185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.14090","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":"2026-07-05T11:59:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qs1EPDvdsm6gPlx9I5akyBkjncTk7IH4i7aZVPtgKOG5gaJcUQOIYkD9IOH2xgNkp4w8mq+21UVtuXXUPpSIBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T13:20:49.339643Z"},"content_sha256":"c415256b454bd150312c0ae3811917d64e3821c69bf8d5e7dccb235ed7d15d3c","schema_version":"1.0","event_id":"sha256:c415256b454bd150312c0ae3811917d64e3821c69bf8d5e7dccb235ed7d15d3c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:46GP7IXFFJGQUCVH7TCI7YW5DT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DLLMQuant: Quantizing Diffusion-based Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chen Xu, Dawei Yang","submitted_at":"2025-08-14T09:30:17Z","abstract_excerpt":"Diffusion-based large language models (DLLMs) have shown promise for non-autoregressive text generation, but their deployment is constrained by large model sizes and heavy computational costs. Post-training quantization (PTQ), a widely used method for compressing and accelerating Large Language Models (LLMs), suffers from severe accuracy degradation and reduced generalization performance when directly applied to DLLMs (e.g., AWQ suffers a 16% accuracy drop on LLADA under W4A4). This paper explores how DLLMs' key mechanisms - dynamic masking, iterative generation, bidirectional attention - clas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.14090","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/2508.14090/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":"2026-07-05T11:59:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SjdG8buwVWpyO8quPUhcASY0n7UIgyCZq0HNfWBIlLY3jXn/XA1y2aHrrCvSvlAc22umh2AvrHJzK3gDtMmeDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T13:20:49.340198Z"},"content_sha256":"9b70aad4f015357da588c71830919314e7abbc681bade72eae319e2239b41438","schema_version":"1.0","event_id":"sha256:9b70aad4f015357da588c71830919314e7abbc681bade72eae319e2239b41438"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/46GP7IXFFJGQUCVH7TCI7YW5DT/bundle.json","state_url":"https://pith.science/pith/46GP7IXFFJGQUCVH7TCI7YW5DT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/46GP7IXFFJGQUCVH7TCI7YW5DT/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":"2026-08-05T13:20:49Z","links":{"resolver":"https://pith.science/pith/46GP7IXFFJGQUCVH7TCI7YW5DT","bundle":"https://pith.science/pith/46GP7IXFFJGQUCVH7TCI7YW5DT/bundle.json","state":"https://pith.science/pith/46GP7IXFFJGQUCVH7TCI7YW5DT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/46GP7IXFFJGQUCVH7TCI7YW5DT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:46GP7IXFFJGQUCVH7TCI7YW5DT","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":"a43f0566042ef7b98d8ca2940a6ee431815ef76f211e97905fb76ce7c626f3cc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-14T09:30:17Z","title_canon_sha256":"dfcaad016fef7a624231e5c19c77969df6447e93340a2d4909db8dc9faca901a"},"schema_version":"1.0","source":{"id":"2508.14090","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.14090","created_at":"2026-07-05T11:59:20Z"},{"alias_kind":"arxiv_version","alias_value":"2508.14090v2","created_at":"2026-07-05T11:59:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.14090","created_at":"2026-07-05T11:59:20Z"},{"alias_kind":"pith_short_12","alias_value":"46GP7IXFFJGQ","created_at":"2026-07-05T11:59:20Z"},{"alias_kind":"pith_short_16","alias_value":"46GP7IXFFJGQUCVH","created_at":"2026-07-05T11:59:20Z"},{"alias_kind":"pith_short_8","alias_value":"46GP7IXF","created_at":"2026-07-05T11:59:20Z"}],"graph_snapshots":[{"event_id":"sha256:9b70aad4f015357da588c71830919314e7abbc681bade72eae319e2239b41438","target":"graph","created_at":"2026-07-05T11:59:20Z","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/2508.14090/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion-based large language models (DLLMs) have shown promise for non-autoregressive text generation, but their deployment is constrained by large model sizes and heavy computational costs. Post-training quantization (PTQ), a widely used method for compressing and accelerating Large Language Models (LLMs), suffers from severe accuracy degradation and reduced generalization performance when directly applied to DLLMs (e.g., AWQ suffers a 16% accuracy drop on LLADA under W4A4). This paper explores how DLLMs' key mechanisms - dynamic masking, iterative generation, bidirectional attention - clas","authors_text":"Chen Xu, Dawei Yang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-14T09:30:17Z","title":"DLLMQuant: Quantizing Diffusion-based Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.14090","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:c415256b454bd150312c0ae3811917d64e3821c69bf8d5e7dccb235ed7d15d3c","target":"record","created_at":"2026-07-05T11:59:20Z","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":"a43f0566042ef7b98d8ca2940a6ee431815ef76f211e97905fb76ce7c626f3cc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-14T09:30:17Z","title_canon_sha256":"dfcaad016fef7a624231e5c19c77969df6447e93340a2d4909db8dc9faca901a"},"schema_version":"1.0","source":{"id":"2508.14090","kind":"arxiv","version":2}},"canonical_sha256":"e78cffa2e52a4d0a0aa7fcc48fe2dd1cf00ea716fc4ca5049cd9cb97fecbff05","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e78cffa2e52a4d0a0aa7fcc48fe2dd1cf00ea716fc4ca5049cd9cb97fecbff05","first_computed_at":"2026-07-05T11:59:20.157185Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:59:20.157185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UIWofllV4bz6rOHktU1RGM4klMIePz49gK3N076DiF6VLVn7kvOYYz8LujKgfdtNtGTTw/ZlXs2U7utJN1P3Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:59:20.157650Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.14090","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c415256b454bd150312c0ae3811917d64e3821c69bf8d5e7dccb235ed7d15d3c","sha256:9b70aad4f015357da588c71830919314e7abbc681bade72eae319e2239b41438"],"state_sha256":"1467ab87283bba22f412f182edc1ee22501cef4f37b7262423bb8ffdbee31ef6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4KICWEWyTHB887tcSgw+9UM0tCxMaawuOGPQ9BZsIzTHzAmroml8FvseSWpqmg0pX99hNzn1dKrE+7knX/CtAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T13:20:49.351757Z","bundle_sha256":"6fb2912d7130e4093be97751dbaf2098a4b348b3ce29eaf994dca3588d109cbd"}}