{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Z6426YSSMXWF4YXGUJGX5XJ5G6","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":"f51b22e25357f2bd1c1b5a8ef278fb1cf1be555bf4aa60016742bd3763918ff7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-22T17:55:04Z","title_canon_sha256":"d5d0f869602bb04c1a3c0c2b718530ac74e37adf687f5814d1a03105e0f40341"},"schema_version":"1.0","source":{"id":"2505.16990","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16990","created_at":"2026-07-05T11:09:15Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16990v2","created_at":"2026-07-05T11:09:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16990","created_at":"2026-07-05T11:09:15Z"},{"alias_kind":"pith_short_12","alias_value":"Z6426YSSMXWF","created_at":"2026-07-05T11:09:15Z"},{"alias_kind":"pith_short_16","alias_value":"Z6426YSSMXWF4YXG","created_at":"2026-07-05T11:09:15Z"},{"alias_kind":"pith_short_8","alias_value":"Z6426YSS","created_at":"2026-07-05T11:09:15Z"}],"graph_snapshots":[{"event_id":"sha256:90634d884353db6e8e2e6fd33945805a1a0b398f0dada7b5a40136ffe50d6482","target":"graph","created_at":"2026-07-05T11:09:15Z","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/2505.16990/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we propose Dimple, the first Discrete Diffusion Multimodal Large Language Model (DMLLM). We observe that training with a purely discrete diffusion approach leads to significant training instability, suboptimal performance, and severe length bias issues. To address these challenges, we design a novel training paradigm that combines an initial autoregressive phase with a subsequent diffusion phase. This approach yields the Dimple-7B model, trained on the same dataset and using a similar training pipeline as LLaVA-NEXT. Dimple-7B ultimately surpasses LLaVA-NEXT in performance by 3.9","authors_text":"Runpeng Yu, Xinchao Wang, Xinyin Ma","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-22T17:55:04Z","title":"Dimple: Discrete Diffusion Multimodal Large Language Model with Parallel Decoding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16990","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":"sha256:9a96d5ea3b285374525fa88ea0c461b91e7bdd93e9f22a7764a0c1d12cca89f0","target":"record","created_at":"2026-07-05T11:09:15Z","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":"f51b22e25357f2bd1c1b5a8ef278fb1cf1be555bf4aa60016742bd3763918ff7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-22T17:55:04Z","title_canon_sha256":"d5d0f869602bb04c1a3c0c2b718530ac74e37adf687f5814d1a03105e0f40341"},"schema_version":"1.0","source":{"id":"2505.16990","kind":"arxiv","version":2}},"canonical_sha256":"cfb9af625265ec5e62e6a24d7edd3d37acf4cddd97b68dd3d774932cb63d3731","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cfb9af625265ec5e62e6a24d7edd3d37acf4cddd97b68dd3d774932cb63d3731","first_computed_at":"2026-07-05T11:09:15.506801Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:15.506801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EP7V8rt/wMasObaqPTio5YrmESR9gI2fkUtjQnC94DeQqIdE2hfqBqytp865wdS520f5SQe2RzwmlBXN+PAuCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:15.507288Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.16990","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a96d5ea3b285374525fa88ea0c461b91e7bdd93e9f22a7764a0c1d12cca89f0","sha256:90634d884353db6e8e2e6fd33945805a1a0b398f0dada7b5a40136ffe50d6482"],"state_sha256":"be468f156070467c1b682830244dc5ff187a8e860b8eed651e8493ed9080f500"}