{"as_of":"2026-08-09T00:16:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:870b23548e1012f39f2e89f3868ebe7be6c6a9ba6a77e9fbefe7bc950c2be9be","coverage":[{"denominator":30,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":30,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T13:42:26.952910Z","state":"measured"},{"denominator":30,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":30,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2607.20467/citation-record","integrity":"/paper/2607.20467/integrity","json":"/paper/2607.20467/citation-record.json","paper":"/paper/2607.20467"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2108.07732","last_updated":"2021-08-16T03:57:30Z","snapshot_observed_at":"2026-08-02T19:23:53.535075Z","submitted_at":"2021-08-16T03:57:30Z","title":"Program Synthesis with Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.07732","snapshot_observed_at":"2026-08-02T13:42:23.821096Z","title":"Program synthesis with large language models.arXiv preprint arXiv:2108.07732,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.20467","last_updated":"2026-05-19T06:27:58Z","snapshot_observed_at":"2026-08-08T06:33:24.325410Z","submitted_at":"2026-05-19T06:27:58Z","title":"DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-02T13:42:23.821096Z"},"links":{"cited_paper":"/paper/2108.07732","citing_paper":"/paper/2607.20467"},"observation_digest":"sha256:5579a4456bd8adeb90efd74cfbe8973673c316bf3fd73d7337a6df96493f26d5","observation_id":"616293b9-def1-4abc-9e81-22c4f7612938","resolution":{"observed_at":"2026-08-02T13:42:23.821096Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.05271","last_updated":"2025-09-26T12:52:41Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-06T18:57:08Z","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.05271","snapshot_observed_at":"2026-08-02T13:42:24.273802Z","title":"H., and Chen, Y","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.20467","last_updated":"2026-05-19T06:27:58Z","snapshot_observed_at":"2026-08-08T06:33:24.325410Z","submitted_at":"2026-05-19T06:27:58Z","title":"DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-02T13:42:24.273802Z"},"links":{"cited_paper":"/paper/2412.05271","citing_paper":"/paper/2607.20467"},"observation_digest":"sha256:b78576fdb9fafd32de9ccd67fc8ba2a14ddebfc1d4387cf8eca38817d247c122","observation_id":"6ff5951a-8a44-4d34-81e6-8436442d1993","resolution":{"observed_at":"2026-08-02T13:42:24.273802Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-07-06T18:55:11.576666Z","submitted_at":"2024-07-31T17:54:27Z","title":"The Llama 3 Herd of Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21783","snapshot_observed_at":"2026-08-02T13:42:24.457562Z","title":"The llama 3 herd of models.arXiv preprint arXiv:2407.21783,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.20467","last_updated":"2026-05-19T06:27:58Z","snapshot_observed_at":"2026-08-08T06:33:24.325410Z","submitted_at":"2026-05-19T06:27:58Z","title":"DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-02T13:42:24.457562Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2607.20467"},"observation_digest":"sha256:e97c1caa8e0efb8ee46845e23f39232a713a02d462968a10178150ce5d6731e3","observation_id":"d3865e8f-c6c1-4e7b-9bbc-c6da994fbb97","resolution":{"observed_at":"2026-08-02T13:42:24.457562Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.17323","last_updated":"2023-03-22T13:10:47Z","snapshot_observed_at":"2026-08-07T08:38:54.025062Z","submitted_at":"2022-10-31T13:42:40Z","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.17323","snapshot_observed_at":"2026-08-02T13:42:24.528341Z","title":"Gptq: Accurate post-training quantization for generative pre- trained transformers.arXiv preprint arXiv:2210.17323,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.20467","last_updated":"2026-05-19T06:27:58Z","snapshot_observed_at":"2026-08-08T06:33:24.325410Z","submitted_at":"2026-05-19T06:27:58Z","title":"DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-02T13:42:24.528341Z"},"links":{"cited_paper":"/paper/2210.17323","citing_paper":"/paper/2607.20467"},"observation_digest":"sha256:87819a1e70387df722b0fa7c45525f32be6c601b31b05ed3e440c8108bd949b6","observation_id":"7ad13206-24c1-4f27-bd69-f44cf71a5ccf","resolution":{"observed_at":"2026-08-02T13:42:24.528341Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T13:42:24.592693Z","title":"Empirical analysis of decoding biases in masked diffusion models.arXiv:2508.13021,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.20467","last_updated":"2026-05-19T06:27:58Z","snapshot_observed_at":"2026-08-08T06:33:24.325410Z","submitted_at":"2026-05-19T06:27:58Z","title":"DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-02T13:42:24.592693Z"},"links":{"citing_paper":"/paper/2607.20467"},"observation_digest":"sha256:88f277788395dd9e3304c261f306b8689610185b8f5d64d08bddfbaac99f71fe","observation_id":"98cf8dae-f94e-43bf-a1c7-c20a013df18c","resolution":{"observed_at":"2026-08-02T13:42:24.592693Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T13:42:24.829332Z","title":"Accelerating diffusion llm inference via local deter- minism propagation.arXiv preprint arXiv:2510.07081,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.20467","last_updated":"2026-05-19T06:27:58Z","snapshot_observed_at":"2026-08-08T06:33:24.325410Z","submitted_at":"2026-05-19T06:27:58Z","title":"DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-02T13:42:24.829332Z"},"links":{"citing_paper":"/paper/2607.20467"},"observation_digest":"sha256:c16a70c99b56deb8922b3a945ce22b46e916de8b55840d3ea3eac498d3d9f2dd","observation_id":"c4bd8e67-7a9d-449f-9f37-dc808febd0b9","resolution":{"observed_at":"2026-08-02T13:42:24.829332Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.18629","last_updated":"2024-06-26T17:43:06Z","snapshot_observed_at":"2026-08-06T00:24:52.274888Z","submitted_at":"2024-06-26T17:43:06Z","title":"Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.18629","snapshot_observed_at":"2026-08-02T13:42:24.987811Z","title":"Lisa: Reasoning segmentation via large language model","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.20467","last_updated":"2026-05-19T06:27:58Z","snapshot_observed_at":"2026-08-08T06:33:24.325410Z","submitted_at":"2026-05-19T06:27:58Z","title":"DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-02T13:42:24.987811Z"},"links":{"cited_paper":"/paper/2406.18629","citing_paper":"/paper/2607.20467"},"observation_digest":"sha256:2e75c2bdce5f845f7c63ce137381d7335af9364decc6ebac6f39144177251680","observation_id":"6ad3e2a1-1796-4da4-ae1e-a62d7563a082","resolution":{"observed_at":"2026-08-02T13:42:24.987811Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.12563","last_updated":"2024-05-13T11:01:17Z","snapshot_observed_at":"2026-08-08T11:37:09.900139Z","submitted_at":"2024-02-19T21:38:02Z","title":"Confidence Matters: Revisiting Intrinsic Self-Correction Capabilities of Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.12563","snapshot_observed_at":"2026-08-02T13:42:25.132171Z","title":"Confidence matters: Revisiting intrinsic self- correction capabilities of large language models.arXiv preprint arXiv:2402.12563, 2024a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.20467","last_updated":"2026-05-19T06:27:58Z","snapshot_observed_at":"2026-08-08T06:33:24.325410Z","submitted_at":"2026-05-19T06:27:58Z","title":"DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-02T13:42:25.132171Z"},"links":{"cited_paper":"/paper/2402.12563","citing_paper":"/paper/2607.20467"},"observation_digest":"sha256:da526713f581b609d497c55c07d1fef294fdcf09a20881e6be422ba2fbe95a13","observation_id":"1ad4f409-1e20-4e09-8cd2-faf89b638128","resolution":{"observed_at":"2026-08-02T13:42:25.132171Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.07800","last_updated":"2022-04-13T23:46:08Z","snapshot_observed_at":"2026-08-03T03:15:29.208149Z","submitted_at":"2022-02-16T00:19:42Z","title":"Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.07800","snapshot_observed_at":"2026-08-02T13:42:25.353013Z","title":"Not all patches are what you need: Expediting vision transformers via token reorganizations.arXiv preprint arXiv:2202.07800,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.20467","last_updated":"2026-05-19T06:27:58Z","snapshot_observed_at":"2026-08-08T06:33:24.325410Z","submitted_at":"2026-05-19T06:27:58Z","title":"DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-02T13:42:25.353013Z"},"links":{"cited_paper":"/paper/2202.07800","citing_paper":"/paper/2607.20467"},"observation_digest":"sha256:2324153ba207d2628a155157666a0751de2d5f1a5654a711b8c29cb8eeaf5564","observation_id":"2a02f626-1fca-44ae-bedd-8c23a35f2520","resolution":{"observed_at":"2026-08-02T13:42:25.353013Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.06295","last_updated":"2026-06-06T06:01:00Z","snapshot_observed_at":"2026-08-07T15:43:50.180226Z","submitted_at":"2025-05-17T15:50:46Z","title":"dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.06295","snapshot_observed_at":"2026-08-02T13:42:25.497970Z","title":"Liu, Z., Yang, Y ., Zhang, Y ., Chen, J., Zou, C., Wei, Q., Wang, S., and Zhang, L","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.20467","last_updated":"2026-05-19T06:27:58Z","snapshot_observed_at":"2026-08-08T06:33:24.325410Z","submitted_at":"2026-05-19T06:27:58Z","title":"DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-02T13:42:25.497970Z"},"links":{"cited_paper":"/paper/2506.06295","citing_paper":"/paper/2607.20467"},"observation_digest":"sha256:2990002d257d5f7701a6971aed1962231d51f0f3bc4ed1033ea6fb499a27fda8","observation_id":"880be54c-ecb7-4242-af6b-4aa594fc84d7","resolution":{"observed_at":"2026-08-02T13:42:25.497970Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T13:42:25.596364Z","title":"Large language diffusion models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.20467","last_updated":"2026-05-19T06:27:58Z","snapshot_observed_at":"2026-08-08T06:33:24.325410Z","submitted_at":"2026-05-19T06:27:58Z","title":"DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-02T13:42:25.596364Z"},"links":{"citing_paper":"/paper/2607.20467"},"observation_digest":"sha256:3ea8eceeba07fce3200c84ab45627b8df50d11d6a13d5aa5b8d0aed6f6fc4803","observation_id":"f7a6fdb1-b5d4-494a-8482-fd2a4103fc1c","resolution":{"observed_at":"2026-08-02T13:42:25.596364Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07470","last_updated":"2024-04-11T04:22:15Z","snapshot_observed_at":"2026-08-07T09:52:49.159319Z","submitted_at":"2024-04-11T04:22:15Z","title":"Scalable Language Model with Generalized Continual Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.07470","snapshot_observed_at":"2026-08-02T13:42:25.714439Z","title":"Scalable lan- guage model with generalized continual learning.arXiv preprint arXiv:2404.07470, 2024a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.20467","last_updated":"2026-05-19T06:27:58Z","snapshot_observed_at":"2026-08-08T06:33:24.325410Z","submitted_at":"2026-05-19T06:27:58Z","title":"DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-02T13:42:25.714439Z"},"links":{"cited_paper":"/paper/2404.07470","citing_paper":"/paper/2607.20467"},"observation_digest":"sha256:a7873792594f47f6df7064a24a9f6e0ba3a37fa439a92ddaeb5a95df94cd5264","observation_id":"8daa6cea-3707-4c39-a05a-fa3b3ec6e825","resolution":{"observed_at":"2026-08-02T13:42:25.714439Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.11256","last_updated":"2025-08-15T06:43:51Z","snapshot_observed_at":"2026-08-07T05:04:02.338549Z","submitted_at":"2025-08-15T06:43:51Z","title":"Generalized Decoupled Learning for Enhancing Open-Vocabulary Dense Perception","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.11256","snapshot_observed_at":"2026-08-02T13:42:25.796548Z","title":"Declip: Decoupled learning for open-vocabulary dense perception","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.20467","last_updated":"2026-05-19T06:27:58Z","snapshot_observed_at":"2026-08-08T06:33:24.325410Z","submitted_at":"2026-05-19T06:27:58Z","title":"DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-02T13:42:25.796548Z"},"links":{"cited_paper":"/paper/2508.11256","citing_paper":"/paper/2607.20467"},"observation_digest":"sha256:1559867be257ae7a730ad235660e9104b0e40470457532ad398b06a6742eed22","observation_id":"2648fb87-7a24-4a22-bfd8-9cbc79320386","resolution":{"observed_at":"2026-08-02T13:42:25.796548Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.09388","last_updated":"2025-05-14T13:41:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-14T13:41:34Z","title":"Qwen3 Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.09388","snapshot_observed_at":"2026-08-02T13:42:25.885006Z","title":"Qwen3 technical report.arXiv preprint arXiv:2505.09388, 2025a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.20467","last_updated":"2026-05-19T06:27:58Z","snapshot_observed_at":"2026-08-08T06:33:24.325410Z","submitted_at":"2026-05-19T06:27:58Z","title":"DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-02T13:42:25.885006Z"},"links":{"cited_paper":"/paper/2505.09388","citing_paper":"/paper/2607.20467"},"observation_digest":"sha256:49174d73804862cb0b6933d46f75c7e11fa6fa7fb3a6e1607bb34371aaa4e837","observation_id":"dc2c8fec-4adb-4d11-bc4b-07cfc3bdd1f7","resolution":{"observed_at":"2026-08-02T13:42:25.885006Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.15487","last_updated":"2025-08-21T12:09:58Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-08-21T12:09:58Z","title":"Dream 7B: Diffusion Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.15487","snapshot_observed_at":"2026-08-02T13:42:26.006034Z","title":"Visionzip: Longer is better but not necessary in vision language models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.20467","last_updated":"2026-05-19T06:27:58Z","snapshot_observed_at":"2026-08-08T06:33:24.325410Z","submitted_at":"2026-05-19T06:27:58Z","title":"DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-02T13:42:26.006034Z"},"links":{"cited_paper":"/paper/2508.15487","citing_paper":"/paper/2607.20467"},"observation_digest":"sha256:5431067ea3bc00d5f768e0a611e3a988a3e3aaddcd80571a933cdafbcfcd5d24","observation_id":"06260476-1ef6-4756-89a0-1bf4e3ae113a","resolution":{"observed_at":"2026-08-02T13:42:26.006034Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.19223","last_updated":"2025-10-12T15:42:47Z","snapshot_observed_at":"2026-07-06T21:30:09.658226Z","submitted_at":"2025-05-25T16:36:20Z","title":"LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.19223","snapshot_observed_at":"2026-08-02T13:42:26.123398Z","title":"Llada 1.5: Variance- reduced preference optimization for large language diffu- sion models.arXiv preprint arXiv:2505.19223,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.20467","last_updated":"2026-05-19T06:27:58Z","snapshot_observed_at":"2026-08-08T06:33:24.325410Z","submitted_at":"2026-05-19T06:27:58Z","title":"DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-02T13:42:26.123398Z"},"links":{"cited_paper":"/paper/2505.19223","citing_paper":"/paper/2607.20467"},"observation_digest":"sha256:273c38b811746e2e256e086f56185be875ebfa6fb89351791520133b3869eda8","observation_id":"02e8daa0-e477-424b-a15c-c102f0bb703e","resolution":{"observed_at":"2026-08-02T13:42:26.123398Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T13:42:26.236548Z","title":"Related Work B.1","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.20467","last_updated":"2026-05-19T06:27:58Z","snapshot_observed_at":"2026-08-08T06:33:24.325410Z","submitted_at":"2026-05-19T06:27:58Z","title":"DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-02T13:42:26.236548Z"},"links":{"citing_paper":"/paper/2607.20467"},"observation_digest":"sha256:8dbcc131ce95d38846e7f866c06c31a9deb8538449f8ec4000cd1bdf29c8ae0f","observation_id":"f0bdada5-263c-4c38-bbed-f0835187c65c","resolution":{"observed_at":"2026-08-02T13:42:26.236548Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T13:42:26.354834Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.20467","last_updated":"2026-05-19T06:27:58Z","snapshot_observed_at":"2026-08-08T06:33:24.325410Z","submitted_at":"2026-05-19T06:27:58Z","title":"DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-02T13:42:26.354834Z"},"links":{"citing_paper":"/paper/2607.20467"},"observation_digest":"sha256:bfc855f72e9b300147036ab8ebc74c9299004c0ae78089549fb3c32479b0fa5b","observation_id":"d44c4db4-a2fa-4d16-9211-502c3a1d5ffa","resolution":{"observed_at":"2026-08-02T13:42:26.354834Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T13:42:26.413562Z","title":"While these methods effectively mitigate the overhead of AR architectures, they remain bound by the causal requirement of sequential drafting","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.20467","last_updated":"2026-05-19T06:27:58Z","snapshot_observed_at":"2026-08-08T06:33:24.325410Z","submitted_at":"2026-05-19T06:27:58Z","title":"DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-02T13:42:26.413562Z"},"links":{"citing_paper":"/paper/2607.20467"},"observation_digest":"sha256:755074af41f71627e577b07b58c53755e5875a85addf6ac844adde4ae0a5e480","observation_id":"f192dead-2d76-4edc-bb77-31db269e28a2","resolution":{"observed_at":"2026-08-02T13:42:26.413562Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T13:42:26.504377Z","title":"Efficient representations in these spaces are also key to downstream generation tasks, such as multi-angle 3D asset editing (Huang et al., 2025)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.20467","last_updated":"2026-05-19T06:27:58Z","snapshot_observed_at":"2026-08-08T06:33:24.325410Z","submitted_at":"2026-05-19T06:27:58Z","title":"DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-02T13:42:26.504377Z"},"links":{"citing_paper":"/paper/2607.20467"},"observation_digest":"sha256:1eeff1ec3119d411b43adebd3b357800971b3aacb90b26e1f1f180bc78d7533b","observation_id":"b39ddd4f-afd0-4561-b022-0e78802da216","resolution":{"observed_at":"2026-08-02T13:42:26.504377Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T13:42:26.622923Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.20467","last_updated":"2026-05-19T06:27:58Z","snapshot_observed_at":"2026-08-08T06:33:24.325410Z","submitted_at":"2026-05-19T06:27:58Z","title":"DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-02T13:42:26.622923Z"},"links":{"citing_paper":"/paper/2607.20467"},"observation_digest":"sha256:6206539974c45e8bf2feac214103b3094a0cc31217548576dbb220d442f1b19f","observation_id":"aa3615c1-6c6f-43fd-8e73-86f24544ddc1","resolution":{"observed_at":"2026-08-02T13:42:26.622923Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T13:42:26.727462Z","title":"However, a critical limitation in these parallel approaches is the independence assumption","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.20467","last_updated":"2026-05-19T06:27:58Z","snapshot_observed_at":"2026-08-08T06:33:24.325410Z","submitted_at":"2026-05-19T06:27:58Z","title":"DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-02T13:42:26.727462Z"},"links":{"citing_paper":"/paper/2607.20467"},"observation_digest":"sha256:a5f411c975d59e5f2438ccf348b23a491483c80297ca3f45606ed68554857f7f","observation_id":"77061a81-7d80-474e-b0ad-dc4faa8659da","resolution":{"observed_at":"2026-08-02T13:42:26.727462Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T13:42:26.868664Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.20467","last_updated":"2026-05-19T06:27:58Z","snapshot_observed_at":"2026-08-08T06:33:24.325410Z","submitted_at":"2026-05-19T06:27:58Z","title":"DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-02T13:42:26.868664Z"},"links":{"citing_paper":"/paper/2607.20467"},"observation_digest":"sha256:3575483fa7ba73d91f90aae2aef216b0f9b9344a510e2cf98e390f481c4482a4","observation_id":"5a7b0a9b-a5e4-4166-adb6-a5daa4291b88","resolution":{"observed_at":"2026-08-02T13:42:26.868664Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T13:42:26.952910Z","title":"However, DC-Leap demonstrates its robustness in this constrained scenario, successfully delivering additional throughput gains with comparable accuracy","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.20467","last_updated":"2026-05-19T06:27:58Z","snapshot_observed_at":"2026-08-08T06:33:24.325410Z","submitted_at":"2026-05-19T06:27:58Z","title":"DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-02T13:42:26.952910Z"},"links":{"citing_paper":"/paper/2607.20467"},"observation_digest":"sha256:31a11812d6fb1b68b9cbd128658e413bed86e792b5a2f60c00e1ac24a8f497d2","observation_id":"5b974f93-96ce-4cb2-9f71-9e71d44c84a1","resolution":{"observed_at":"2026-08-02T13:42:26.952910Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2511.21631","last_updated":"2025-11-27T12:16:54Z","snapshot_observed_at":"2026-07-06T22:37:03.716474Z","submitted_at":"2025-11-26T17:59:08Z","title":"Qwen3-VL Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2511.21631","snapshot_observed_at":"2026-08-02T13:42:23.907037Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.20467","last_updated":"2026-05-19T06:27:58Z","snapshot_observed_at":"2026-08-08T06:33:24.325410Z","submitted_at":"2026-05-19T06:27:58Z","title":"DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-02T13:42:23.907037Z"},"links":{"cited_paper":"/paper/2511.21631","citing_paper":"/paper/2607.20467"},"observation_digest":"sha256:56e7226bbe08e56d34907e2a075e8c7fd7c0f328b4398edb50c22c140b420d58","observation_id":"6316b7d5-bfbf-4565-9b3e-cca229163550","resolution":{"observed_at":"2026-08-02T13:42:23.907037Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.04921","last_updated":"2025-07-06T14:40:27Z","snapshot_observed_at":"2026-08-07T15:49:03.741523Z","submitted_at":"2025-05-08T03:35:23Z","title":"Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.04921","snapshot_observed_at":"2026-08-02T13:42:25.191504Z","title":"Eagle: Specula- tive sampling requires rethinking feature uncertainty","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.20467","last_updated":"2026-05-19T06:27:58Z","snapshot_observed_at":"2026-08-08T06:33:24.325410Z","submitted_at":"2026-05-19T06:27:58Z","title":"DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-02T13:42:25.191504Z"},"links":{"cited_paper":"/paper/2505.04921","citing_paper":"/paper/2607.20467"},"observation_digest":"sha256:ba26192f29b67fede087cee9c5d0418920a6adfa8d1142d2d2cb647eb4b823ac","observation_id":"6f897abd-8868-4151-b05f-2845cbbfeee4","resolution":{"observed_at":"2026-08-02T13:42:25.191504Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2107.03374","last_updated":"2021-07-14T17:16:02Z","snapshot_observed_at":"2026-08-08T11:58:24.516369Z","submitted_at":"2021-07-07T17:41:24Z","title":"Evaluating Large Language Models Trained on Code","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.03374","snapshot_observed_at":"2026-08-02T13:42:24.131133Z","title":"P., Kaplan, J., Edwards, H., Burda, Y ., Joseph, N., and Greg Brockman, e","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.20467","last_updated":"2026-05-19T06:27:58Z","snapshot_observed_at":"2026-08-08T06:33:24.325410Z","submitted_at":"2026-05-19T06:27:58Z","title":"DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-02T13:42:24.131133Z"},"links":{"cited_paper":"/paper/2107.03374","citing_paper":"/paper/2607.20467"},"observation_digest":"sha256:7ec6a8b219c99a9b7b9112ce6db92573e28aa4064b58921cba52f0e77c69265b","observation_id":"b379e167-72ef-40d7-a137-b1dc49ec511a","resolution":{"observed_at":"2026-08-02T13:42:24.131133Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.01318","last_updated":"2023-02-02T18:44:11Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-02-02T18:44:11Z","title":"Accelerating Large Language Model Decoding with Speculative Sampling","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.01318","snapshot_observed_at":"2026-08-02T13:42:23.971116Z","title":"Accelerating large language model decoding with speculative sampling.arXiv preprint arXiv:2302.01318,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.20467","last_updated":"2026-05-19T06:27:58Z","snapshot_observed_at":"2026-08-08T06:33:24.325410Z","submitted_at":"2026-05-19T06:27:58Z","title":"DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-02T13:42:23.971116Z"},"links":{"cited_paper":"/paper/2302.01318","citing_paper":"/paper/2607.20467"},"observation_digest":"sha256:62aea9d16e38c52cd01e9988dc1a0df1ef74370f47b33eb72bc8ee41fc8a831a","observation_id":"b395f8f5-2b10-4bf2-9241-81353502650e","resolution":{"observed_at":"2026-08-02T13:42:23.971116Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.14168","last_updated":"2021-11-18T00:23:45Z","snapshot_observed_at":"2026-08-07T01:45:38.840969Z","submitted_at":"2021-10-27T04:49:45Z","title":"Training Verifiers to Solve Math Word Problems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.14168","snapshot_observed_at":"2026-08-02T13:42:24.365769Z","title":"dparallel: Learnable parallel decoding for dllms","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.20467","last_updated":"2026-05-19T06:27:58Z","snapshot_observed_at":"2026-08-08T06:33:24.325410Z","submitted_at":"2026-05-19T06:27:58Z","title":"DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-02T13:42:24.365769Z"},"links":{"cited_paper":"/paper/2110.14168","citing_paper":"/paper/2607.20467"},"observation_digest":"sha256:98f36dd796d9ae63c061ba51f6908d77f2a2971d4a5c0375e0432e9276a9fb96","observation_id":"87ca3e62-7d12-4f6a-91e1-09e546d7f30d","resolution":{"observed_at":"2026-08-02T13:42:24.365769Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.06825","last_updated":"2023-10-10T17:54:58Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-10-10T17:54:58Z","title":"Mistral 7B","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.06825","snapshot_observed_at":"2026-08-02T13:42:24.721990Z","title":"Q., Sablayrolles, A., Mensch, A., Bamford, C., Chaplot, D","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.20467","last_updated":"2026-05-19T06:27:58Z","snapshot_observed_at":"2026-08-08T06:33:24.325410Z","submitted_at":"2026-05-19T06:27:58Z","title":"DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding","version":1},"reference_index":2026,"source":"pdf_text","source_observed_at":"2026-08-02T13:42:24.721990Z"},"links":{"cited_paper":"/paper/2310.06825","citing_paper":"/paper/2607.20467"},"observation_digest":"sha256:67e2775948014284a26a10ee8d07574ef77f8c274373db3f98669b1dcfd1053f","observation_id":"4e88c7fc-7d55-4859-9e5a-15190ac30d4b","resolution":{"observed_at":"2026-08-02T13:42:24.721990Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.20467","last_updated":"2026-05-19T06:27:58Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-08T06:33:24.325410Z","submitted_at":"2026-05-19T06:27:58Z","title":"DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding"},"reference_resolution":{"displayed":30,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":30,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":30},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 0 inbound Pith citation observations for arXiv:2607.20467."}