{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ITT5SR2SNSU4JVNI62U2LCHB6T","short_pith_number":"pith:ITT5SR2S","canonical_record":{"source":{"id":"2406.05496","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-08T15:30:46Z","cross_cats_sorted":[],"title_canon_sha256":"212b343c03931bf4b3ee5e33e3e332ae5b9116c2469489bc4096f0153062370c","abstract_canon_sha256":"79dd09c58977e8c35e37eaa2158f1cca816ed1e4077fced2f9f04935e6456d2b"},"schema_version":"1.0"},"canonical_sha256":"44e7d947526ca9c4d5a8f6a9a588e1f4e6cdd86c561bd8e258b80b767b779505","source":{"kind":"arxiv","id":"2406.05496","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.05496","created_at":"2026-07-05T08:29:06Z"},{"alias_kind":"arxiv_version","alias_value":"2406.05496v1","created_at":"2026-07-05T08:29:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.05496","created_at":"2026-07-05T08:29:06Z"},{"alias_kind":"pith_short_12","alias_value":"ITT5SR2SNSU4","created_at":"2026-07-05T08:29:06Z"},{"alias_kind":"pith_short_16","alias_value":"ITT5SR2SNSU4JVNI","created_at":"2026-07-05T08:29:06Z"},{"alias_kind":"pith_short_8","alias_value":"ITT5SR2S","created_at":"2026-07-05T08:29:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ITT5SR2SNSU4JVNI62U2LCHB6T","target":"record","payload":{"canonical_record":{"source":{"id":"2406.05496","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-08T15:30:46Z","cross_cats_sorted":[],"title_canon_sha256":"212b343c03931bf4b3ee5e33e3e332ae5b9116c2469489bc4096f0153062370c","abstract_canon_sha256":"79dd09c58977e8c35e37eaa2158f1cca816ed1e4077fced2f9f04935e6456d2b"},"schema_version":"1.0"},"canonical_sha256":"44e7d947526ca9c4d5a8f6a9a588e1f4e6cdd86c561bd8e258b80b767b779505","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:06.535127Z","signature_b64":"N+YvCFZXWbsLSQJBtSOHtOH/fEzyOTpIYNQNngvrq9uCoR9uqFV1BFwrh1OkZjJI4NDYqh/JpsiEidmuV+baBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44e7d947526ca9c4d5a8f6a9a588e1f4e6cdd86c561bd8e258b80b767b779505","last_reissued_at":"2026-07-05T08:29:06.534672Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:06.534672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.05496","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":"2026-07-05T08:29:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G1EqeAyYq/9Tkiy0nVYCEV3x6PEoAC9OHqxC5xP0AE40NWooLScqgTQTXP8OROOg/8E0Yw77tfP7nx989NNSCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T00:43:01.289024Z"},"content_sha256":"886246c0e02141090c3bf7bf51f4bc8f8b46b65fd4a6f391565d26d8a660ed06","schema_version":"1.0","event_id":"sha256:886246c0e02141090c3bf7bf51f4bc8f8b46b65fd4a6f391565d26d8a660ed06"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ITT5SR2SNSU4JVNI62U2LCHB6T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generalist Multimodal AI: A Review of Architectures, Challenges and Opportunities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Henry Kvinge, Ian Stewart, Karl Pazdernik, Sai Munikoti, Sameera Horawalavithana, Sandra E Thompson, Tegan Emerson","submitted_at":"2024-06-08T15:30:46Z","abstract_excerpt":"Multimodal models are expected to be a critical component to future advances in artificial intelligence. This field is starting to grow rapidly with a surge of new design elements motivated by the success of foundation models in natural language processing (NLP) and vision. It is widely hoped that further extending the foundation models to multiple modalities (e.g., text, image, video, sensor, time series, graph, etc.) will ultimately lead to generalist multimodal models, i.e. one model across different data modalities and tasks. However, there is little research that systematically analyzes r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.05496","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/2406.05496/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":"2026-07-05T08:29:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b1CRhHpTZsanlBwRfmJBiMeDEtPtmsFPe750a1IOuL7ayQffc8iNKZXvEZ5UXPn7WHmV6UIwaQ+A8yHjwCVyAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T00:43:01.289941Z"},"content_sha256":"6e6951aa51bd363c1ab311c3ac0f62a44f351d90660f930940758e63e94eda15","schema_version":"1.0","event_id":"sha256:6e6951aa51bd363c1ab311c3ac0f62a44f351d90660f930940758e63e94eda15"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ITT5SR2SNSU4JVNI62U2LCHB6T/bundle.json","state_url":"https://pith.science/pith/ITT5SR2SNSU4JVNI62U2LCHB6T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ITT5SR2SNSU4JVNI62U2LCHB6T/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":"2026-08-15T00:43:01Z","links":{"resolver":"https://pith.science/pith/ITT5SR2SNSU4JVNI62U2LCHB6T","bundle":"https://pith.science/pith/ITT5SR2SNSU4JVNI62U2LCHB6T/bundle.json","state":"https://pith.science/pith/ITT5SR2SNSU4JVNI62U2LCHB6T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ITT5SR2SNSU4JVNI62U2LCHB6T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ITT5SR2SNSU4JVNI62U2LCHB6T","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":"79dd09c58977e8c35e37eaa2158f1cca816ed1e4077fced2f9f04935e6456d2b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-08T15:30:46Z","title_canon_sha256":"212b343c03931bf4b3ee5e33e3e332ae5b9116c2469489bc4096f0153062370c"},"schema_version":"1.0","source":{"id":"2406.05496","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.05496","created_at":"2026-07-05T08:29:06Z"},{"alias_kind":"arxiv_version","alias_value":"2406.05496v1","created_at":"2026-07-05T08:29:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.05496","created_at":"2026-07-05T08:29:06Z"},{"alias_kind":"pith_short_12","alias_value":"ITT5SR2SNSU4","created_at":"2026-07-05T08:29:06Z"},{"alias_kind":"pith_short_16","alias_value":"ITT5SR2SNSU4JVNI","created_at":"2026-07-05T08:29:06Z"},{"alias_kind":"pith_short_8","alias_value":"ITT5SR2S","created_at":"2026-07-05T08:29:06Z"}],"graph_snapshots":[{"event_id":"sha256:6e6951aa51bd363c1ab311c3ac0f62a44f351d90660f930940758e63e94eda15","target":"graph","created_at":"2026-07-05T08:29:06Z","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/2406.05496/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal models are expected to be a critical component to future advances in artificial intelligence. This field is starting to grow rapidly with a surge of new design elements motivated by the success of foundation models in natural language processing (NLP) and vision. It is widely hoped that further extending the foundation models to multiple modalities (e.g., text, image, video, sensor, time series, graph, etc.) will ultimately lead to generalist multimodal models, i.e. one model across different data modalities and tasks. However, there is little research that systematically analyzes r","authors_text":"Henry Kvinge, Ian Stewart, Karl Pazdernik, Sai Munikoti, Sameera Horawalavithana, Sandra E Thompson, Tegan Emerson","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-08T15:30:46Z","title":"Generalist Multimodal AI: A Review of Architectures, Challenges and Opportunities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.05496","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":"sha256:886246c0e02141090c3bf7bf51f4bc8f8b46b65fd4a6f391565d26d8a660ed06","target":"record","created_at":"2026-07-05T08:29:06Z","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":"79dd09c58977e8c35e37eaa2158f1cca816ed1e4077fced2f9f04935e6456d2b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-08T15:30:46Z","title_canon_sha256":"212b343c03931bf4b3ee5e33e3e332ae5b9116c2469489bc4096f0153062370c"},"schema_version":"1.0","source":{"id":"2406.05496","kind":"arxiv","version":1}},"canonical_sha256":"44e7d947526ca9c4d5a8f6a9a588e1f4e6cdd86c561bd8e258b80b767b779505","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"44e7d947526ca9c4d5a8f6a9a588e1f4e6cdd86c561bd8e258b80b767b779505","first_computed_at":"2026-07-05T08:29:06.534672Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:29:06.534672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N+YvCFZXWbsLSQJBtSOHtOH/fEzyOTpIYNQNngvrq9uCoR9uqFV1BFwrh1OkZjJI4NDYqh/JpsiEidmuV+baBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:29:06.535127Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.05496","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:886246c0e02141090c3bf7bf51f4bc8f8b46b65fd4a6f391565d26d8a660ed06","sha256:6e6951aa51bd363c1ab311c3ac0f62a44f351d90660f930940758e63e94eda15"],"state_sha256":"464aed67d5196bb06a7c6f0c33254e3e1f56ad137e101a5d7b9ac16336a00166"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uByyAbM9hGOYQFF/VfOmOE5tKWrZRN0RwK/ZZrW1zoZMbSkE3ImDxROB+NlsepmagaXPEbpPZxOj6tiWQ3bxDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T00:43:01.298067Z","bundle_sha256":"e56c75b4b767c0f41c7e81c554595fe956ece8ae844a2d7694ed02ae07790c76"}}