{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:T7SKSNNP64FJ2PWC3DP72GCMWY","short_pith_number":"pith:T7SKSNNP","canonical_record":{"source":{"id":"2508.05954","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-08T02:38:47Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"cd0147f205a90636d0eb6e4cc430fa2069a7d2d3b9e087d9d292f04ed4295c25","abstract_canon_sha256":"0dc209a848998000f672e4254a66994d2c42d90b2fb7360445cfa64704207911"},"schema_version":"1.0"},"canonical_sha256":"9fe4a935aff70a9d3ec2d8dffd184cb620549bb284908c16a583c3eb42bd60c7","source":{"kind":"arxiv","id":"2508.05954","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.05954","created_at":"2026-07-05T11:50:46Z"},{"alias_kind":"arxiv_version","alias_value":"2508.05954v1","created_at":"2026-07-05T11:50:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.05954","created_at":"2026-07-05T11:50:46Z"},{"alias_kind":"pith_short_12","alias_value":"T7SKSNNP64FJ","created_at":"2026-07-05T11:50:46Z"},{"alias_kind":"pith_short_16","alias_value":"T7SKSNNP64FJ2PWC","created_at":"2026-07-05T11:50:46Z"},{"alias_kind":"pith_short_8","alias_value":"T7SKSNNP","created_at":"2026-07-05T11:50:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:T7SKSNNP64FJ2PWC3DP72GCMWY","target":"record","payload":{"canonical_record":{"source":{"id":"2508.05954","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-08T02:38:47Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"cd0147f205a90636d0eb6e4cc430fa2069a7d2d3b9e087d9d292f04ed4295c25","abstract_canon_sha256":"0dc209a848998000f672e4254a66994d2c42d90b2fb7360445cfa64704207911"},"schema_version":"1.0"},"canonical_sha256":"9fe4a935aff70a9d3ec2d8dffd184cb620549bb284908c16a583c3eb42bd60c7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:50:46.337937Z","signature_b64":"9E3ZgMYjR5GkbdDfXmsPLjZ636Hujrh5G/rriIr7k93WwsYnIPRg/0D78cYWArGy6+s2LmWUgMocYdlmYqMiAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fe4a935aff70a9d3ec2d8dffd184cb620549bb284908c16a583c3eb42bd60c7","last_reissued_at":"2026-07-05T11:50:46.337393Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:50:46.337393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.05954","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":"2026-07-05T11:50:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IJ4yQMP9JbiYjADTs3XA1YNU/Oo049zdDfx4pZuoXhyI5cqeqJ21nQ//xnBomwlD/JzQv655G37FwL5Ow4nqAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:04:43.366794Z"},"content_sha256":"464e41b729b97a2e013494333623e360e41f06a3961ef8028bbae405b1a0b281","schema_version":"1.0","event_id":"sha256:464e41b729b97a2e013494333623e360e41f06a3961ef8028bbae405b1a0b281"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:T7SKSNNP64FJ2PWC3DP72GCMWY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Amir Zadeh, Chuan Li, Han Lin, Jaemin Cho, Mohit Bansal","submitted_at":"2025-08-08T02:38:47Z","abstract_excerpt":"There is growing interest in integrating high-fidelity visual synthesis capabilities into large language models (LLMs) without compromising their strong reasoning capabilities. Existing methods that directly train LLMs or bridge LLMs and diffusion models usually suffer from costly training since the backbone LLMs have not seen image representations during pretraining. We present Bifrost-1, a unified framework that bridges pretrained multimodal LLMs (MLLMs) and diffusion models using patch-level CLIP image embeddings as latent variables, which are natively aligned with the MLLM's CLIP visual en"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.05954","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/2508.05954/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":"2026-07-05T11:50:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MT0FpgG9oJNoSHB9QYC80qu4JJSbywWggbI14Q7bkcFmofd0hEVlTuDNiAJpOHyIZ+4ar0chMs7XhzY4UZBiBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:04:43.367331Z"},"content_sha256":"59bc15129e038ea68052af6c16c963a90275482d033367460d74171f3751c622","schema_version":"1.0","event_id":"sha256:59bc15129e038ea68052af6c16c963a90275482d033367460d74171f3751c622"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T7SKSNNP64FJ2PWC3DP72GCMWY/bundle.json","state_url":"https://pith.science/pith/T7SKSNNP64FJ2PWC3DP72GCMWY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T7SKSNNP64FJ2PWC3DP72GCMWY/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":"2026-08-05T07:04:43Z","links":{"resolver":"https://pith.science/pith/T7SKSNNP64FJ2PWC3DP72GCMWY","bundle":"https://pith.science/pith/T7SKSNNP64FJ2PWC3DP72GCMWY/bundle.json","state":"https://pith.science/pith/T7SKSNNP64FJ2PWC3DP72GCMWY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T7SKSNNP64FJ2PWC3DP72GCMWY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:T7SKSNNP64FJ2PWC3DP72GCMWY","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":"0dc209a848998000f672e4254a66994d2c42d90b2fb7360445cfa64704207911","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-08T02:38:47Z","title_canon_sha256":"cd0147f205a90636d0eb6e4cc430fa2069a7d2d3b9e087d9d292f04ed4295c25"},"schema_version":"1.0","source":{"id":"2508.05954","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.05954","created_at":"2026-07-05T11:50:46Z"},{"alias_kind":"arxiv_version","alias_value":"2508.05954v1","created_at":"2026-07-05T11:50:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.05954","created_at":"2026-07-05T11:50:46Z"},{"alias_kind":"pith_short_12","alias_value":"T7SKSNNP64FJ","created_at":"2026-07-05T11:50:46Z"},{"alias_kind":"pith_short_16","alias_value":"T7SKSNNP64FJ2PWC","created_at":"2026-07-05T11:50:46Z"},{"alias_kind":"pith_short_8","alias_value":"T7SKSNNP","created_at":"2026-07-05T11:50:46Z"}],"graph_snapshots":[{"event_id":"sha256:59bc15129e038ea68052af6c16c963a90275482d033367460d74171f3751c622","target":"graph","created_at":"2026-07-05T11:50:46Z","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/2508.05954/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There is growing interest in integrating high-fidelity visual synthesis capabilities into large language models (LLMs) without compromising their strong reasoning capabilities. Existing methods that directly train LLMs or bridge LLMs and diffusion models usually suffer from costly training since the backbone LLMs have not seen image representations during pretraining. We present Bifrost-1, a unified framework that bridges pretrained multimodal LLMs (MLLMs) and diffusion models using patch-level CLIP image embeddings as latent variables, which are natively aligned with the MLLM's CLIP visual en","authors_text":"Amir Zadeh, Chuan Li, Han Lin, Jaemin Cho, Mohit Bansal","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-08T02:38:47Z","title":"Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.05954","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":"sha256:464e41b729b97a2e013494333623e360e41f06a3961ef8028bbae405b1a0b281","target":"record","created_at":"2026-07-05T11:50:46Z","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":"0dc209a848998000f672e4254a66994d2c42d90b2fb7360445cfa64704207911","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-08T02:38:47Z","title_canon_sha256":"cd0147f205a90636d0eb6e4cc430fa2069a7d2d3b9e087d9d292f04ed4295c25"},"schema_version":"1.0","source":{"id":"2508.05954","kind":"arxiv","version":1}},"canonical_sha256":"9fe4a935aff70a9d3ec2d8dffd184cb620549bb284908c16a583c3eb42bd60c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9fe4a935aff70a9d3ec2d8dffd184cb620549bb284908c16a583c3eb42bd60c7","first_computed_at":"2026-07-05T11:50:46.337393Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:50:46.337393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9E3ZgMYjR5GkbdDfXmsPLjZ636Hujrh5G/rriIr7k93WwsYnIPRg/0D78cYWArGy6+s2LmWUgMocYdlmYqMiAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:50:46.337937Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.05954","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:464e41b729b97a2e013494333623e360e41f06a3961ef8028bbae405b1a0b281","sha256:59bc15129e038ea68052af6c16c963a90275482d033367460d74171f3751c622"],"state_sha256":"637ef3ef13d23014b5bbb4082bb76811810e341af913449cc49b51db5e819446"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RFwqQ2+ay2SjxY6FgFCpPOXwFfBxA7J5BfB+wlX1kLPrhr1/nhIcxrg7YTuWFI5JYYE08V5NKvYjONyh2EcACQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T07:04:43.372113Z","bundle_sha256":"f9d5b10a564012fb9b0f978aabbb53c25873b088bc9346e793fba09eaf8b9dcc"}}