{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:D64X646QX3R2AOT7LRFXFHOKHR","short_pith_number":"pith:D64X646Q","canonical_record":{"source":{"id":"2606.19534","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T19:27:55Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"c85f785688fc3272829b601bd986d844e9a4bd676d313ec550bff8390f5d1ed1","abstract_canon_sha256":"24a94da4075de9d88f1be56096a4517df2ec155d965d7db410190cd8bcd58af9"},"schema_version":"1.0"},"canonical_sha256":"1fb97f73d0bee3a03a7f5c4b729dca3c653a9ffb22c3dea1d01f8dd6418b03e0","source":{"kind":"arxiv","id":"2606.19534","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.19534","created_at":"2026-06-19T16:12:28Z"},{"alias_kind":"arxiv_version","alias_value":"2606.19534v1","created_at":"2026-06-19T16:12:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19534","created_at":"2026-06-19T16:12:28Z"},{"alias_kind":"pith_short_12","alias_value":"D64X646QX3R2","created_at":"2026-06-19T16:12:28Z"},{"alias_kind":"pith_short_16","alias_value":"D64X646QX3R2AOT7","created_at":"2026-06-19T16:12:28Z"},{"alias_kind":"pith_short_8","alias_value":"D64X646Q","created_at":"2026-06-19T16:12:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:D64X646QX3R2AOT7LRFXFHOKHR","target":"record","payload":{"canonical_record":{"source":{"id":"2606.19534","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T19:27:55Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"c85f785688fc3272829b601bd986d844e9a4bd676d313ec550bff8390f5d1ed1","abstract_canon_sha256":"24a94da4075de9d88f1be56096a4517df2ec155d965d7db410190cd8bcd58af9"},"schema_version":"1.0"},"canonical_sha256":"1fb97f73d0bee3a03a7f5c4b729dca3c653a9ffb22c3dea1d01f8dd6418b03e0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:28.072652Z","signature_b64":"vTZXwz5NpnP88kuFzIw+6gK17IkMxpQ6BpFCjhbvLgpTLNPQXKGzRsdZFuDmTa5ik0bEQEPb5i//Ki9f9k2NCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1fb97f73d0bee3a03a7f5c4b729dca3c653a9ffb22c3dea1d01f8dd6418b03e0","last_reissued_at":"2026-06-19T16:12:28.072295Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:28.072295Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.19534","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":"2026-06-19T16:12:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eVdD9kDJOYVVJ3i92S3P6W9CG0Lwb+DwPeYbvR6UVFJnHfa+4GHYmzq6LUIWCrqa64QVfeutPbf4EFiYUnTvCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T04:58:58.213289Z"},"content_sha256":"8a950db5758204d83149bce9d40bca9c1bbe3ba43033bde5a9b3861af567078e","schema_version":"1.0","event_id":"sha256:8a950db5758204d83149bce9d40bca9c1bbe3ba43033bde5a9b3861af567078e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:D64X646QX3R2AOT7LRFXFHOKHR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Haochen Wang, Jacky Mai, Jason Li, Jinbin Bai, Ling Yang, Tao Zhang, Ye Tian, Yihan Wang, Yueyi Sun, Yuhao Wang, Yunhai Tong","submitted_at":"2026-06-17T19:27:55Z","abstract_excerpt":"Multimodal large language models (MLLMs) have achieved remarkable progress in visual understanding tasks. However, most existing MLLMs rely on autoregressive generation, which limits their efficiency for perception tasks that require captioning multiple regions. In this work, we propose PerceptionDLM, a multimodal diffusion language model optimized for efficient parallel region perception. Built upon PerceptionDLM-Base, a strong foundational baseline that achieves state-of-the-art performance among open-source diffusion MLLMs, our architecture fully leverages the parallel decoding nature of DL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19534","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/2606.19534/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":"2026-06-19T16:12:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zPA/7ic7zclbQJZ5sywMdsggA2I7eJf0vQmiPseerumRF08CYveAtBTAxeLE+1WCESI/nlO/ylZ1pxU0Wx4lAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T04:58:58.213951Z"},"content_sha256":"aeee020497ca8abda64c889a6cd6bf6b20bbe6fee8c155ef30a0e1533b337cbb","schema_version":"1.0","event_id":"sha256:aeee020497ca8abda64c889a6cd6bf6b20bbe6fee8c155ef30a0e1533b337cbb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D64X646QX3R2AOT7LRFXFHOKHR/bundle.json","state_url":"https://pith.science/pith/D64X646QX3R2AOT7LRFXFHOKHR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D64X646QX3R2AOT7LRFXFHOKHR/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":"2026-07-04T04:58:58Z","links":{"resolver":"https://pith.science/pith/D64X646QX3R2AOT7LRFXFHOKHR","bundle":"https://pith.science/pith/D64X646QX3R2AOT7LRFXFHOKHR/bundle.json","state":"https://pith.science/pith/D64X646QX3R2AOT7LRFXFHOKHR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D64X646QX3R2AOT7LRFXFHOKHR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:D64X646QX3R2AOT7LRFXFHOKHR","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":"24a94da4075de9d88f1be56096a4517df2ec155d965d7db410190cd8bcd58af9","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T19:27:55Z","title_canon_sha256":"c85f785688fc3272829b601bd986d844e9a4bd676d313ec550bff8390f5d1ed1"},"schema_version":"1.0","source":{"id":"2606.19534","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.19534","created_at":"2026-06-19T16:12:28Z"},{"alias_kind":"arxiv_version","alias_value":"2606.19534v1","created_at":"2026-06-19T16:12:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19534","created_at":"2026-06-19T16:12:28Z"},{"alias_kind":"pith_short_12","alias_value":"D64X646QX3R2","created_at":"2026-06-19T16:12:28Z"},{"alias_kind":"pith_short_16","alias_value":"D64X646QX3R2AOT7","created_at":"2026-06-19T16:12:28Z"},{"alias_kind":"pith_short_8","alias_value":"D64X646Q","created_at":"2026-06-19T16:12:28Z"}],"graph_snapshots":[{"event_id":"sha256:aeee020497ca8abda64c889a6cd6bf6b20bbe6fee8c155ef30a0e1533b337cbb","target":"graph","created_at":"2026-06-19T16:12:28Z","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/2606.19534/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) have achieved remarkable progress in visual understanding tasks. However, most existing MLLMs rely on autoregressive generation, which limits their efficiency for perception tasks that require captioning multiple regions. In this work, we propose PerceptionDLM, a multimodal diffusion language model optimized for efficient parallel region perception. Built upon PerceptionDLM-Base, a strong foundational baseline that achieves state-of-the-art performance among open-source diffusion MLLMs, our architecture fully leverages the parallel decoding nature of DL","authors_text":"Haochen Wang, Jacky Mai, Jason Li, Jinbin Bai, Ling Yang, Tao Zhang, Ye Tian, Yihan Wang, Yueyi Sun, Yuhao Wang, Yunhai Tong","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T19:27:55Z","title":"PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19534","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":"sha256:8a950db5758204d83149bce9d40bca9c1bbe3ba43033bde5a9b3861af567078e","target":"record","created_at":"2026-06-19T16:12:28Z","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":"24a94da4075de9d88f1be56096a4517df2ec155d965d7db410190cd8bcd58af9","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T19:27:55Z","title_canon_sha256":"c85f785688fc3272829b601bd986d844e9a4bd676d313ec550bff8390f5d1ed1"},"schema_version":"1.0","source":{"id":"2606.19534","kind":"arxiv","version":1}},"canonical_sha256":"1fb97f73d0bee3a03a7f5c4b729dca3c653a9ffb22c3dea1d01f8dd6418b03e0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1fb97f73d0bee3a03a7f5c4b729dca3c653a9ffb22c3dea1d01f8dd6418b03e0","first_computed_at":"2026-06-19T16:12:28.072295Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:12:28.072295Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vTZXwz5NpnP88kuFzIw+6gK17IkMxpQ6BpFCjhbvLgpTLNPQXKGzRsdZFuDmTa5ik0bEQEPb5i//Ki9f9k2NCQ==","signature_status":"signed_v1","signed_at":"2026-06-19T16:12:28.072652Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.19534","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a950db5758204d83149bce9d40bca9c1bbe3ba43033bde5a9b3861af567078e","sha256:aeee020497ca8abda64c889a6cd6bf6b20bbe6fee8c155ef30a0e1533b337cbb"],"state_sha256":"1b33103500d88791a15f7e15e8c0f5460c55e515cad929f7312534c28d3a0e2b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NT4BPwfYVOhuFaaBk+NvA7uzJhNkqLi/naUyAwBGuZVlnie/j6RzaQtmbxpxfG5EZ/9skL4Gjo2U1KBwh+vJBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T04:58:58.217326Z","bundle_sha256":"3674ec0171b753328360599f70ed9411266bd76e50445872fe7b8ecaf578df4e"}}