{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CIC6WCA2WO6L4ZNW36B7HDRISU","short_pith_number":"pith:CIC6WCA2","canonical_record":{"source":{"id":"2504.14666","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-20T16:14:28Z","cross_cats_sorted":[],"title_canon_sha256":"8ca2ea51f97613492fbb020c1dd8f4d353ccb15452dc0e04914cd266448c6713","abstract_canon_sha256":"d63a9c435ff0302d4d3929fd1a8ee3b13d6ad65b9859fec2de8f8d32ba7fe986"},"schema_version":"1.0"},"canonical_sha256":"1205eb081ab3bcbe65b6df83f38e2895131b4c9efc4d9f52962bc3701fe8a846","source":{"kind":"arxiv","id":"2504.14666","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.14666","created_at":"2026-07-05T10:51:48Z"},{"alias_kind":"arxiv_version","alias_value":"2504.14666v1","created_at":"2026-07-05T10:51:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14666","created_at":"2026-07-05T10:51:48Z"},{"alias_kind":"pith_short_12","alias_value":"CIC6WCA2WO6L","created_at":"2026-07-05T10:51:48Z"},{"alias_kind":"pith_short_16","alias_value":"CIC6WCA2WO6L4ZNW","created_at":"2026-07-05T10:51:48Z"},{"alias_kind":"pith_short_8","alias_value":"CIC6WCA2","created_at":"2026-07-05T10:51:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CIC6WCA2WO6L4ZNW36B7HDRISU","target":"record","payload":{"canonical_record":{"source":{"id":"2504.14666","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-20T16:14:28Z","cross_cats_sorted":[],"title_canon_sha256":"8ca2ea51f97613492fbb020c1dd8f4d353ccb15452dc0e04914cd266448c6713","abstract_canon_sha256":"d63a9c435ff0302d4d3929fd1a8ee3b13d6ad65b9859fec2de8f8d32ba7fe986"},"schema_version":"1.0"},"canonical_sha256":"1205eb081ab3bcbe65b6df83f38e2895131b4c9efc4d9f52962bc3701fe8a846","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:48.622146Z","signature_b64":"7djT5vXveZIk9JCA0tnAWOn5QN6Q78N5O1gw7NOwSjZlgxtSNEj/F9NpPk4/yW1EzybbzYT+6bYY8Qc+ZqI3Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1205eb081ab3bcbe65b6df83f38e2895131b4c9efc4d9f52962bc3701fe8a846","last_reissued_at":"2026-07-05T10:51:48.621588Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:48.621588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.14666","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":"2026-07-05T10:51:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UWp4xDguG4KmilWJhwP3BfxVCtHoe/bG0xqY9ine2O6A7S4a04YiwVIgWDos55nqdoXrOFqGfRyi0SjntbpjBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T19:47:59.319400Z"},"content_sha256":"8ad0d956a6c73160a41e10f6400d6c173fa6e6099ee238cbe276c52bd797f9b8","schema_version":"1.0","event_id":"sha256:8ad0d956a6c73160a41e10f6400d6c173fa6e6099ee238cbe276c52bd797f9b8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CIC6WCA2WO6L4ZNW36B7HDRISU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanwang Zhang, Juncheng Li, Kaihang Pan, Liyu Jia, Siliang Tang, Tenglong Ao, Wang Lin, Wei Zhao, Zhongqi Yue","submitted_at":"2025-04-20T16:14:28Z","abstract_excerpt":"Recent endeavors in Multimodal Large Language Models (MLLMs) aim to unify visual comprehension and generation by combining LLM and diffusion models, the state-of-the-art in each task, respectively. Existing approaches rely on spatial visual tokens, where image patches are encoded and arranged according to a spatial order (e.g., raster scan). However, we show that spatial tokens lack the recursive structure inherent to languages, hence form an impossible language for LLM to master. In this paper, we build a proper visual language by leveraging diffusion timesteps to learn discrete, recursive vi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14666","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/2504.14666/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":"2026-07-05T10:51:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CtxhMyD4NNQ84Dprv4GD1wk1A+IVCMM6EII4EssYLlxHfNhEtdquvwlCkiD5KCDZ3L7cBVP34SrLs1mysRogDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T19:47:59.319950Z"},"content_sha256":"6ba52155c150e984ac09ff1b4308ce310fa96e1a5ce043352b268ec6513193a9","schema_version":"1.0","event_id":"sha256:6ba52155c150e984ac09ff1b4308ce310fa96e1a5ce043352b268ec6513193a9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CIC6WCA2WO6L4ZNW36B7HDRISU/bundle.json","state_url":"https://pith.science/pith/CIC6WCA2WO6L4ZNW36B7HDRISU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CIC6WCA2WO6L4ZNW36B7HDRISU/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":"2026-08-09T19:47:59Z","links":{"resolver":"https://pith.science/pith/CIC6WCA2WO6L4ZNW36B7HDRISU","bundle":"https://pith.science/pith/CIC6WCA2WO6L4ZNW36B7HDRISU/bundle.json","state":"https://pith.science/pith/CIC6WCA2WO6L4ZNW36B7HDRISU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CIC6WCA2WO6L4ZNW36B7HDRISU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CIC6WCA2WO6L4ZNW36B7HDRISU","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":"d63a9c435ff0302d4d3929fd1a8ee3b13d6ad65b9859fec2de8f8d32ba7fe986","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-20T16:14:28Z","title_canon_sha256":"8ca2ea51f97613492fbb020c1dd8f4d353ccb15452dc0e04914cd266448c6713"},"schema_version":"1.0","source":{"id":"2504.14666","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.14666","created_at":"2026-07-05T10:51:48Z"},{"alias_kind":"arxiv_version","alias_value":"2504.14666v1","created_at":"2026-07-05T10:51:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14666","created_at":"2026-07-05T10:51:48Z"},{"alias_kind":"pith_short_12","alias_value":"CIC6WCA2WO6L","created_at":"2026-07-05T10:51:48Z"},{"alias_kind":"pith_short_16","alias_value":"CIC6WCA2WO6L4ZNW","created_at":"2026-07-05T10:51:48Z"},{"alias_kind":"pith_short_8","alias_value":"CIC6WCA2","created_at":"2026-07-05T10:51:48Z"}],"graph_snapshots":[{"event_id":"sha256:6ba52155c150e984ac09ff1b4308ce310fa96e1a5ce043352b268ec6513193a9","target":"graph","created_at":"2026-07-05T10:51:48Z","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/2504.14666/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent endeavors in Multimodal Large Language Models (MLLMs) aim to unify visual comprehension and generation by combining LLM and diffusion models, the state-of-the-art in each task, respectively. Existing approaches rely on spatial visual tokens, where image patches are encoded and arranged according to a spatial order (e.g., raster scan). However, we show that spatial tokens lack the recursive structure inherent to languages, hence form an impossible language for LLM to master. In this paper, we build a proper visual language by leveraging diffusion timesteps to learn discrete, recursive vi","authors_text":"Hanwang Zhang, Juncheng Li, Kaihang Pan, Liyu Jia, Siliang Tang, Tenglong Ao, Wang Lin, Wei Zhao, Zhongqi Yue","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-20T16:14:28Z","title":"Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14666","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":"sha256:8ad0d956a6c73160a41e10f6400d6c173fa6e6099ee238cbe276c52bd797f9b8","target":"record","created_at":"2026-07-05T10:51:48Z","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":"d63a9c435ff0302d4d3929fd1a8ee3b13d6ad65b9859fec2de8f8d32ba7fe986","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-20T16:14:28Z","title_canon_sha256":"8ca2ea51f97613492fbb020c1dd8f4d353ccb15452dc0e04914cd266448c6713"},"schema_version":"1.0","source":{"id":"2504.14666","kind":"arxiv","version":1}},"canonical_sha256":"1205eb081ab3bcbe65b6df83f38e2895131b4c9efc4d9f52962bc3701fe8a846","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1205eb081ab3bcbe65b6df83f38e2895131b4c9efc4d9f52962bc3701fe8a846","first_computed_at":"2026-07-05T10:51:48.621588Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:51:48.621588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7djT5vXveZIk9JCA0tnAWOn5QN6Q78N5O1gw7NOwSjZlgxtSNEj/F9NpPk4/yW1EzybbzYT+6bYY8Qc+ZqI3Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:51:48.622146Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.14666","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ad0d956a6c73160a41e10f6400d6c173fa6e6099ee238cbe276c52bd797f9b8","sha256:6ba52155c150e984ac09ff1b4308ce310fa96e1a5ce043352b268ec6513193a9"],"state_sha256":"63a3a8d27f4c102b0e8bf06c2376179043fdbd0cb6276cab56dc3a88c5021d04"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dOBejgs2A19MyeCjM5GVGDmq0XFeXCOLyeRyU6MbVyPGgSZQ1AC3pUiK10ZmqMOjEXV31qk3NIEYJmCCAN2ADg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T19:47:59.323216Z","bundle_sha256":"9ff8eb98bb2551b84933c7c2206be944feaf33a719b67b308c9c7b26ecc3cc4f"}}