{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:PBKD3KW44OCKGBJQ7T2QJROT72","short_pith_number":"pith:PBKD3KW4","canonical_record":{"source":{"id":"2606.29094","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-27T21:21:53Z","cross_cats_sorted":[],"title_canon_sha256":"a179881b7b8bb3a4b19dcb63aff120c32db4addfca6278b75d472e4e917e537a","abstract_canon_sha256":"62324d86462342092c466f7f2a07dd82be21ab7e043bab20033d6975929bc5ae"},"schema_version":"1.0"},"canonical_sha256":"78543daadce384a30530fcf504c5d3fe83c13dd422d0894cfbd9bb00f9ea305f","source":{"kind":"arxiv","id":"2606.29094","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.29094","created_at":"2026-06-30T01:17:52Z"},{"alias_kind":"arxiv_version","alias_value":"2606.29094v1","created_at":"2026-06-30T01:17:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29094","created_at":"2026-06-30T01:17:52Z"},{"alias_kind":"pith_short_12","alias_value":"PBKD3KW44OCK","created_at":"2026-06-30T01:17:52Z"},{"alias_kind":"pith_short_16","alias_value":"PBKD3KW44OCKGBJQ","created_at":"2026-06-30T01:17:52Z"},{"alias_kind":"pith_short_8","alias_value":"PBKD3KW4","created_at":"2026-06-30T01:17:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:PBKD3KW44OCKGBJQ7T2QJROT72","target":"record","payload":{"canonical_record":{"source":{"id":"2606.29094","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-27T21:21:53Z","cross_cats_sorted":[],"title_canon_sha256":"a179881b7b8bb3a4b19dcb63aff120c32db4addfca6278b75d472e4e917e537a","abstract_canon_sha256":"62324d86462342092c466f7f2a07dd82be21ab7e043bab20033d6975929bc5ae"},"schema_version":"1.0"},"canonical_sha256":"78543daadce384a30530fcf504c5d3fe83c13dd422d0894cfbd9bb00f9ea305f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:52.633385Z","signature_b64":"7DXyR+wz1LlmQ2vGjYEbrWV9Ehz7Amwec0jGa7Om7guMYtOS6fO+sUv2LQ72hFPy02QyQYI5oyczxvT+uCIgBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78543daadce384a30530fcf504c5d3fe83c13dd422d0894cfbd9bb00f9ea305f","last_reissued_at":"2026-06-30T01:17:52.632838Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:52.632838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.29094","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":"2026-06-30T01:17:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"75VWYv6DpT6W3F77u3lnNuPjOR1SlcylENmwxwGofat8iCtytOgtzdm1J2nGrmiSUKa0Mt3DP0ITvqN4ibepDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T18:24:14.542255Z"},"content_sha256":"a5752165808c047122e91f97beb002ae2071eb2350fc6cdf2a2eee1a663ed3dd","schema_version":"1.0","event_id":"sha256:a5752165808c047122e91f97beb002ae2071eb2350fc6cdf2a2eee1a663ed3dd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:PBKD3KW44OCKGBJQ7T2QJROT72","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DiLaServe: High SLO Attainment Serving for Diffusion Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Benjamin Yuanyang Hong, Kiet Pham, Shivaram Venkataraman, Tzu-Tao Chang","submitted_at":"2026-06-27T21:21:53Z","abstract_excerpt":"Diffusion language models (DLMs) have recently emerged as a promising alternative to conventional autoregressive language models. By generating multiple tokens in parallel during each denoising step, they offer higher inference throughput while maintaining competitive quality. However, realizing these throughput gains while meeting latency SLOs in a serving system requires addressing challenges introduced by DLMs' unique characteristics. These include navigating the speed-quality tradeoff created by confidence-based denoising, choosing appropriate parallelization levels across model instances "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29094","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/2606.29094/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":"2026-06-30T01:17:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JKoyNLI+8SzfM8tnDUkKWK1BuXTg+TgY9w/SE3JdR/jdb0ABh2whv8T4BI0Li1Z6zQTQo1nU02hH6tpzXD2XDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T18:24:14.542653Z"},"content_sha256":"78bfe7101abf1b361e6061669e01c3d6c9d1597a2208f0243ded438e2fa5db99","schema_version":"1.0","event_id":"sha256:78bfe7101abf1b361e6061669e01c3d6c9d1597a2208f0243ded438e2fa5db99"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PBKD3KW44OCKGBJQ7T2QJROT72/bundle.json","state_url":"https://pith.science/pith/PBKD3KW44OCKGBJQ7T2QJROT72/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PBKD3KW44OCKGBJQ7T2QJROT72/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":"2026-06-30T18:24:14Z","links":{"resolver":"https://pith.science/pith/PBKD3KW44OCKGBJQ7T2QJROT72","bundle":"https://pith.science/pith/PBKD3KW44OCKGBJQ7T2QJROT72/bundle.json","state":"https://pith.science/pith/PBKD3KW44OCKGBJQ7T2QJROT72/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PBKD3KW44OCKGBJQ7T2QJROT72/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PBKD3KW44OCKGBJQ7T2QJROT72","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":"62324d86462342092c466f7f2a07dd82be21ab7e043bab20033d6975929bc5ae","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-27T21:21:53Z","title_canon_sha256":"a179881b7b8bb3a4b19dcb63aff120c32db4addfca6278b75d472e4e917e537a"},"schema_version":"1.0","source":{"id":"2606.29094","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.29094","created_at":"2026-06-30T01:17:52Z"},{"alias_kind":"arxiv_version","alias_value":"2606.29094v1","created_at":"2026-06-30T01:17:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29094","created_at":"2026-06-30T01:17:52Z"},{"alias_kind":"pith_short_12","alias_value":"PBKD3KW44OCK","created_at":"2026-06-30T01:17:52Z"},{"alias_kind":"pith_short_16","alias_value":"PBKD3KW44OCKGBJQ","created_at":"2026-06-30T01:17:52Z"},{"alias_kind":"pith_short_8","alias_value":"PBKD3KW4","created_at":"2026-06-30T01:17:52Z"}],"graph_snapshots":[{"event_id":"sha256:78bfe7101abf1b361e6061669e01c3d6c9d1597a2208f0243ded438e2fa5db99","target":"graph","created_at":"2026-06-30T01:17:52Z","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/2606.29094/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion language models (DLMs) have recently emerged as a promising alternative to conventional autoregressive language models. By generating multiple tokens in parallel during each denoising step, they offer higher inference throughput while maintaining competitive quality. However, realizing these throughput gains while meeting latency SLOs in a serving system requires addressing challenges introduced by DLMs' unique characteristics. These include navigating the speed-quality tradeoff created by confidence-based denoising, choosing appropriate parallelization levels across model instances ","authors_text":"Benjamin Yuanyang Hong, Kiet Pham, Shivaram Venkataraman, Tzu-Tao Chang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-27T21:21:53Z","title":"DiLaServe: High SLO Attainment Serving for Diffusion Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29094","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:a5752165808c047122e91f97beb002ae2071eb2350fc6cdf2a2eee1a663ed3dd","target":"record","created_at":"2026-06-30T01:17:52Z","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":"62324d86462342092c466f7f2a07dd82be21ab7e043bab20033d6975929bc5ae","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-27T21:21:53Z","title_canon_sha256":"a179881b7b8bb3a4b19dcb63aff120c32db4addfca6278b75d472e4e917e537a"},"schema_version":"1.0","source":{"id":"2606.29094","kind":"arxiv","version":1}},"canonical_sha256":"78543daadce384a30530fcf504c5d3fe83c13dd422d0894cfbd9bb00f9ea305f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"78543daadce384a30530fcf504c5d3fe83c13dd422d0894cfbd9bb00f9ea305f","first_computed_at":"2026-06-30T01:17:52.632838Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T01:17:52.632838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7DXyR+wz1LlmQ2vGjYEbrWV9Ehz7Amwec0jGa7Om7guMYtOS6fO+sUv2LQ72hFPy02QyQYI5oyczxvT+uCIgBQ==","signature_status":"signed_v1","signed_at":"2026-06-30T01:17:52.633385Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.29094","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a5752165808c047122e91f97beb002ae2071eb2350fc6cdf2a2eee1a663ed3dd","sha256:78bfe7101abf1b361e6061669e01c3d6c9d1597a2208f0243ded438e2fa5db99"],"state_sha256":"dd27ad7caaf6cc102fa448ecbf879eaa91cc270690667712a912ef8a884d8f72"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SG1P6XWvoKZEu7MV2e8E2VoT0dON89K/TDFtIGSrUKmb7CXp1ULKZOGeI/YERQT8C+nD49UqE7bqFpJCbw/eAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T18:24:14.544740Z","bundle_sha256":"150b6fe639b333c4682738aa60495a8f0295d77887ceb97384ce0a59bca69734"}}