{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:JHZZL3AQIZX5TX4GRHGVC4HH4H","short_pith_number":"pith:JHZZL3AQ","canonical_record":{"source":{"id":"2312.00968","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-01T23:04:27Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c8468aa07d98db680c6e1a12d0559d019d391e4e572c35238ef69655aa4f7b89","abstract_canon_sha256":"b4aac12cf9cff5e7a66bcbdeeec54091e616ad8100319feb76b2e9cd49ed1679"},"schema_version":"1.0"},"canonical_sha256":"49f395ec10466fd9df8689cd5170e7e1e248f3cca28e1c18126f5608db8f1557","source":{"kind":"arxiv","id":"2312.00968","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.00968","created_at":"2026-07-05T08:03:46Z"},{"alias_kind":"arxiv_version","alias_value":"2312.00968v2","created_at":"2026-07-05T08:03:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.00968","created_at":"2026-07-05T08:03:46Z"},{"alias_kind":"pith_short_12","alias_value":"JHZZL3AQIZX5","created_at":"2026-07-05T08:03:46Z"},{"alias_kind":"pith_short_16","alias_value":"JHZZL3AQIZX5TX4G","created_at":"2026-07-05T08:03:46Z"},{"alias_kind":"pith_short_8","alias_value":"JHZZL3AQ","created_at":"2026-07-05T08:03:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:JHZZL3AQIZX5TX4GRHGVC4HH4H","target":"record","payload":{"canonical_record":{"source":{"id":"2312.00968","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-01T23:04:27Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c8468aa07d98db680c6e1a12d0559d019d391e4e572c35238ef69655aa4f7b89","abstract_canon_sha256":"b4aac12cf9cff5e7a66bcbdeeec54091e616ad8100319feb76b2e9cd49ed1679"},"schema_version":"1.0"},"canonical_sha256":"49f395ec10466fd9df8689cd5170e7e1e248f3cca28e1c18126f5608db8f1557","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:46.372416Z","signature_b64":"K5DlYajMu50ARHm5tf0iLQ2uJhs+zf7pJL5vu0AgMPaauwrgxBY1q2gbUThIOW1d8uHPoFD2cvdrkvoi2mDLCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49f395ec10466fd9df8689cd5170e7e1e248f3cca28e1c18126f5608db8f1557","last_reissued_at":"2026-07-05T08:03:46.371947Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:46.371947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.00968","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:03:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kzk6SUvsHSGL6R0BUw2GIoKTSBlDiTe+RXIqzzApTr9Hc7QIblh+IorB0dMZWrfSTXMEBpBUbG080qMxo87OBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T18:10:25.689072Z"},"content_sha256":"e78a674428795c293451c1bbaf90e383c256bff127d8dc6a7a72f0764b20a82a","schema_version":"1.0","event_id":"sha256:e78a674428795c293451c1bbaf90e383c256bff127d8dc6a7a72f0764b20a82a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:JHZZL3AQIZX5TX4GRHGVC4HH4H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Bo Pang, Jialin Wu, Radu Soricut, Xia Hu, Yaqing Wang","submitted_at":"2023-12-01T23:04:27Z","abstract_excerpt":"Large multi-modal models (LMMs) exhibit remarkable performance across numerous tasks. However, generalist LMMs often suffer from performance degradation when tuned over a large collection of tasks. Recent research suggests that Mixture of Experts (MoE) architectures are useful for instruction tuning, but for LMMs of parameter size around O(50-100B), the prohibitive cost of replicating and storing the expert models severely limits the number of experts we can use. We propose Omni-SMoLA, an architecture that uses the Soft MoE approach to (softly) mix many multimodal low rank experts, and avoids "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.00968","kind":"arxiv","version":2},"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/2312.00968/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":"2026-07-05T08:03:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DZoC/ywC7VX7wNlLF6M9ke7W2hzAuCdQCRuKubKeW4f1KxISdkN1tcrZ2MwCRnXDGm4t3/W3fBGpFVj8xjh6CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T18:10:25.690099Z"},"content_sha256":"6450f948363fc5445c5c5ded37d8f15cc8c58fb67d4c9e4151e3c37ac8783eb7","schema_version":"1.0","event_id":"sha256:6450f948363fc5445c5c5ded37d8f15cc8c58fb67d4c9e4151e3c37ac8783eb7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JHZZL3AQIZX5TX4GRHGVC4HH4H/bundle.json","state_url":"https://pith.science/pith/JHZZL3AQIZX5TX4GRHGVC4HH4H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JHZZL3AQIZX5TX4GRHGVC4HH4H/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":"2026-08-14T18:10:25Z","links":{"resolver":"https://pith.science/pith/JHZZL3AQIZX5TX4GRHGVC4HH4H","bundle":"https://pith.science/pith/JHZZL3AQIZX5TX4GRHGVC4HH4H/bundle.json","state":"https://pith.science/pith/JHZZL3AQIZX5TX4GRHGVC4HH4H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JHZZL3AQIZX5TX4GRHGVC4HH4H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JHZZL3AQIZX5TX4GRHGVC4HH4H","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":"b4aac12cf9cff5e7a66bcbdeeec54091e616ad8100319feb76b2e9cd49ed1679","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-01T23:04:27Z","title_canon_sha256":"c8468aa07d98db680c6e1a12d0559d019d391e4e572c35238ef69655aa4f7b89"},"schema_version":"1.0","source":{"id":"2312.00968","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.00968","created_at":"2026-07-05T08:03:46Z"},{"alias_kind":"arxiv_version","alias_value":"2312.00968v2","created_at":"2026-07-05T08:03:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.00968","created_at":"2026-07-05T08:03:46Z"},{"alias_kind":"pith_short_12","alias_value":"JHZZL3AQIZX5","created_at":"2026-07-05T08:03:46Z"},{"alias_kind":"pith_short_16","alias_value":"JHZZL3AQIZX5TX4G","created_at":"2026-07-05T08:03:46Z"},{"alias_kind":"pith_short_8","alias_value":"JHZZL3AQ","created_at":"2026-07-05T08:03:46Z"}],"graph_snapshots":[{"event_id":"sha256:6450f948363fc5445c5c5ded37d8f15cc8c58fb67d4c9e4151e3c37ac8783eb7","target":"graph","created_at":"2026-07-05T08:03:46Z","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/2312.00968/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large multi-modal models (LMMs) exhibit remarkable performance across numerous tasks. However, generalist LMMs often suffer from performance degradation when tuned over a large collection of tasks. Recent research suggests that Mixture of Experts (MoE) architectures are useful for instruction tuning, but for LMMs of parameter size around O(50-100B), the prohibitive cost of replicating and storing the expert models severely limits the number of experts we can use. We propose Omni-SMoLA, an architecture that uses the Soft MoE approach to (softly) mix many multimodal low rank experts, and avoids ","authors_text":"Bo Pang, Jialin Wu, Radu Soricut, Xia Hu, Yaqing Wang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-01T23:04:27Z","title":"Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.00968","kind":"arxiv","version":2},"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:e78a674428795c293451c1bbaf90e383c256bff127d8dc6a7a72f0764b20a82a","target":"record","created_at":"2026-07-05T08:03:46Z","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":"b4aac12cf9cff5e7a66bcbdeeec54091e616ad8100319feb76b2e9cd49ed1679","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-01T23:04:27Z","title_canon_sha256":"c8468aa07d98db680c6e1a12d0559d019d391e4e572c35238ef69655aa4f7b89"},"schema_version":"1.0","source":{"id":"2312.00968","kind":"arxiv","version":2}},"canonical_sha256":"49f395ec10466fd9df8689cd5170e7e1e248f3cca28e1c18126f5608db8f1557","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"49f395ec10466fd9df8689cd5170e7e1e248f3cca28e1c18126f5608db8f1557","first_computed_at":"2026-07-05T08:03:46.371947Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:03:46.371947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K5DlYajMu50ARHm5tf0iLQ2uJhs+zf7pJL5vu0AgMPaauwrgxBY1q2gbUThIOW1d8uHPoFD2cvdrkvoi2mDLCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:03:46.372416Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.00968","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e78a674428795c293451c1bbaf90e383c256bff127d8dc6a7a72f0764b20a82a","sha256:6450f948363fc5445c5c5ded37d8f15cc8c58fb67d4c9e4151e3c37ac8783eb7"],"state_sha256":"95288fe0ce5e3d171f7ad6da2d0ea72ecbf8989d7dd7c91753cc3ad99afdaecb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iAXoqlgw4ZsBZmPqOAWx6k+H8BClyPRMSmOSCWLWcXVIUbVulgV/wPy0MOgEgOWN/1nY+2lRtY3HDxYfH7BoAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T18:10:25.697657Z","bundle_sha256":"3f4b632d1fe504d1270ca5a0fdf9a8b9fbef7a1acb62acaad8fbd0da0c4c4a6a"}}