{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:B3BTNA67QO6Q4W2E6W7TSST6MQ","short_pith_number":"pith:B3BTNA67","canonical_record":{"source":{"id":"2605.25343","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T01:57:43Z","cross_cats_sorted":[],"title_canon_sha256":"72768bf83dc02400406e2eb8bd48677659518e1c4508e199b08b40c9f05ef3e9","abstract_canon_sha256":"2ca67dcd05e0e243e63a969ed8a8e0022953bc052514b68dd9fdaa4f76f1f1c9"},"schema_version":"1.0"},"canonical_sha256":"0ec33683df83bd0e5b44f5bf394a7e640a0a88e2a85392f41c3adae9342c76c7","source":{"kind":"arxiv","id":"2605.25343","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.25343","created_at":"2026-05-26T02:04:29Z"},{"alias_kind":"arxiv_version","alias_value":"2605.25343v1","created_at":"2026-05-26T02:04:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25343","created_at":"2026-05-26T02:04:29Z"},{"alias_kind":"pith_short_12","alias_value":"B3BTNA67QO6Q","created_at":"2026-05-26T02:04:29Z"},{"alias_kind":"pith_short_16","alias_value":"B3BTNA67QO6Q4W2E","created_at":"2026-05-26T02:04:29Z"},{"alias_kind":"pith_short_8","alias_value":"B3BTNA67","created_at":"2026-05-26T02:04:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:B3BTNA67QO6Q4W2E6W7TSST6MQ","target":"record","payload":{"canonical_record":{"source":{"id":"2605.25343","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T01:57:43Z","cross_cats_sorted":[],"title_canon_sha256":"72768bf83dc02400406e2eb8bd48677659518e1c4508e199b08b40c9f05ef3e9","abstract_canon_sha256":"2ca67dcd05e0e243e63a969ed8a8e0022953bc052514b68dd9fdaa4f76f1f1c9"},"schema_version":"1.0"},"canonical_sha256":"0ec33683df83bd0e5b44f5bf394a7e640a0a88e2a85392f41c3adae9342c76c7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:04:29.816725Z","signature_b64":"9fZA+iTUWZKv+ZMU8a0f9j7FR28T2MAfc/Yww9CqcyZrHq38WwwQ8We7/2llHeVYxJIuKjGCyv3Rd8BtoQHGCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ec33683df83bd0e5b44f5bf394a7e640a0a88e2a85392f41c3adae9342c76c7","last_reissued_at":"2026-05-26T02:04:29.816151Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:04:29.816151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.25343","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":"2026-05-26T02:04:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yXOzpLfPGPcjqSs4QloXIKuafCYhLjUH5x2LkQJFlk+Nsq1Kndm+TunyV+Y1AtsLk5q5xUINP2c0dcvOMzvJAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T15:48:45.945763Z"},"content_sha256":"95c0ef87f91837d08b21efa34a9b7f7c9cfbb2b7f95dc15898eff4600e5c2bda","schema_version":"1.0","event_id":"sha256:95c0ef87f91837d08b21efa34a9b7f7c9cfbb2b7f95dc15898eff4600e5c2bda"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:B3BTNA67QO6Q4W2E6W7TSST6MQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Toward Native Multimodal Modeling: A Roadmap","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Biao Liu, Bo Ke, Difan Zou, Di Yin, Haopeng Wang, Junnan Dong, Junru Lu, Keyu Chen, Linhao Luo, Qiufeng Wang, Renzhao Liang, Ruizhi Qiao, Siyu An, Weizhi Fei, Xiao Huang, Xing Sun, Yinghui Li, Yixuan Yang, Yunhang Shen, Zheng Yuan, Zichao Yu","submitted_at":"2026-05-25T01:57:43Z","abstract_excerpt":"Multimodal modeling represents a vital step from modality-agnostic reasoning toward world modeling. While early approaches predominantly rely on late-fusion that assembles encoders and frozen language backbones with output heads, recent efforts have shifted the paradigm toward native multimodal modeling (NMM) with the intrinsic integration of modalities for superior multimodal performance. Despite its potential, the design space of native architectures remains insufficiently defined. In this paper, we present the community with a formalized roadmap for this transition. Specifically, we formall"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25343","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/2605.25343/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":"2026-05-26T02:04:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uQjxMENCZ0TO7FnZUtR/BHJ6y3pTVaxGaBt8mfllhfG6RFGnmJ4SIF7pvw9WilsgPhHCkhSOsjONAAdb2LatBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T15:48:45.946505Z"},"content_sha256":"94941623aa46d7e235b5be25c3a407cf92cdd9e552dc386436a4d196c8098be7","schema_version":"1.0","event_id":"sha256:94941623aa46d7e235b5be25c3a407cf92cdd9e552dc386436a4d196c8098be7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B3BTNA67QO6Q4W2E6W7TSST6MQ/bundle.json","state_url":"https://pith.science/pith/B3BTNA67QO6Q4W2E6W7TSST6MQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B3BTNA67QO6Q4W2E6W7TSST6MQ/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":"2026-05-31T15:48:45Z","links":{"resolver":"https://pith.science/pith/B3BTNA67QO6Q4W2E6W7TSST6MQ","bundle":"https://pith.science/pith/B3BTNA67QO6Q4W2E6W7TSST6MQ/bundle.json","state":"https://pith.science/pith/B3BTNA67QO6Q4W2E6W7TSST6MQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B3BTNA67QO6Q4W2E6W7TSST6MQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:B3BTNA67QO6Q4W2E6W7TSST6MQ","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":"2ca67dcd05e0e243e63a969ed8a8e0022953bc052514b68dd9fdaa4f76f1f1c9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T01:57:43Z","title_canon_sha256":"72768bf83dc02400406e2eb8bd48677659518e1c4508e199b08b40c9f05ef3e9"},"schema_version":"1.0","source":{"id":"2605.25343","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.25343","created_at":"2026-05-26T02:04:29Z"},{"alias_kind":"arxiv_version","alias_value":"2605.25343v1","created_at":"2026-05-26T02:04:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25343","created_at":"2026-05-26T02:04:29Z"},{"alias_kind":"pith_short_12","alias_value":"B3BTNA67QO6Q","created_at":"2026-05-26T02:04:29Z"},{"alias_kind":"pith_short_16","alias_value":"B3BTNA67QO6Q4W2E","created_at":"2026-05-26T02:04:29Z"},{"alias_kind":"pith_short_8","alias_value":"B3BTNA67","created_at":"2026-05-26T02:04:29Z"}],"graph_snapshots":[{"event_id":"sha256:94941623aa46d7e235b5be25c3a407cf92cdd9e552dc386436a4d196c8098be7","target":"graph","created_at":"2026-05-26T02:04:29Z","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/2605.25343/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal modeling represents a vital step from modality-agnostic reasoning toward world modeling. While early approaches predominantly rely on late-fusion that assembles encoders and frozen language backbones with output heads, recent efforts have shifted the paradigm toward native multimodal modeling (NMM) with the intrinsic integration of modalities for superior multimodal performance. Despite its potential, the design space of native architectures remains insufficiently defined. In this paper, we present the community with a formalized roadmap for this transition. Specifically, we formall","authors_text":"Biao Liu, Bo Ke, Difan Zou, Di Yin, Haopeng Wang, Junnan Dong, Junru Lu, Keyu Chen, Linhao Luo, Qiufeng Wang, Renzhao Liang, Ruizhi Qiao, Siyu An, Weizhi Fei, Xiao Huang, Xing Sun, Yinghui Li, Yixuan Yang, Yunhang Shen, Zheng Yuan, Zichao Yu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T01:57:43Z","title":"Toward Native Multimodal Modeling: A Roadmap"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25343","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":"sha256:95c0ef87f91837d08b21efa34a9b7f7c9cfbb2b7f95dc15898eff4600e5c2bda","target":"record","created_at":"2026-05-26T02:04:29Z","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":"2ca67dcd05e0e243e63a969ed8a8e0022953bc052514b68dd9fdaa4f76f1f1c9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T01:57:43Z","title_canon_sha256":"72768bf83dc02400406e2eb8bd48677659518e1c4508e199b08b40c9f05ef3e9"},"schema_version":"1.0","source":{"id":"2605.25343","kind":"arxiv","version":1}},"canonical_sha256":"0ec33683df83bd0e5b44f5bf394a7e640a0a88e2a85392f41c3adae9342c76c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0ec33683df83bd0e5b44f5bf394a7e640a0a88e2a85392f41c3adae9342c76c7","first_computed_at":"2026-05-26T02:04:29.816151Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:04:29.816151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9fZA+iTUWZKv+ZMU8a0f9j7FR28T2MAfc/Yww9CqcyZrHq38WwwQ8We7/2llHeVYxJIuKjGCyv3Rd8BtoQHGCA==","signature_status":"signed_v1","signed_at":"2026-05-26T02:04:29.816725Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.25343","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:95c0ef87f91837d08b21efa34a9b7f7c9cfbb2b7f95dc15898eff4600e5c2bda","sha256:94941623aa46d7e235b5be25c3a407cf92cdd9e552dc386436a4d196c8098be7"],"state_sha256":"56f85dc5d12eec86edac0ef59ec6c57f6545d97cdfacc2e4e8d49856c835d555"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mKcV/IdiBXeuLOQD8wV9pNe2z3ruwObwyIW3rWZbTRIwuVHR6PxvoJTg+q2EnvieUvcT6XaQqgFHNLxJnoUBAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T15:48:45.950466Z","bundle_sha256":"8d409efd98a6b1ebafd7ee0e2809cf31f6c75c2a7271cc2aa657e6d71f09e806"}}