{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LBR2YVVNQSJX7OPVVKNSI5XVH7","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":"8814608ed3430a5b43f24eaea5fe6d9948d6889b9a61f21a757615a644cf7056","cross_cats_sorted":["cs.AI","cs.LG","cs.MM","eess.IV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-10T17:22:06Z","title_canon_sha256":"ba2efb89e8a905cb72868e2b2133a7b9c9dfa02a54d1b42816f09b5409b6d8c8"},"schema_version":"1.0","source":{"id":"2305.06324","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.06324","created_at":"2026-07-05T07:22:17Z"},{"alias_kind":"arxiv_version","alias_value":"2305.06324v2","created_at":"2026-07-05T07:22:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.06324","created_at":"2026-07-05T07:22:17Z"},{"alias_kind":"pith_short_12","alias_value":"LBR2YVVNQSJX","created_at":"2026-07-05T07:22:17Z"},{"alias_kind":"pith_short_16","alias_value":"LBR2YVVNQSJX7OPV","created_at":"2026-07-05T07:22:17Z"},{"alias_kind":"pith_short_8","alias_value":"LBR2YVVN","created_at":"2026-07-05T07:22:17Z"}],"graph_snapshots":[{"event_id":"sha256:402fdee111dcdf9f6d3dbee93db93ca26606605b7b408de91d955b2888f679c8","target":"graph","created_at":"2026-07-05T07:22:17Z","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/2305.06324/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present Integrated Multimodal Perception (IMP), a simple and scalable multimodal multi-task training and modeling approach. IMP integrates multimodal inputs including image, video, text, and audio into a single Transformer encoder with minimal modality-specific components. IMP makes use of a novel design that combines Alternating Gradient Descent (AGD) and Mixture-of-Experts (MoE) for efficient model and task scaling. We conduct extensive empirical studies and reveal the following key insights: 1) Performing gradient descent updates by alternating on diverse modalities, loss functions, and ","authors_text":"Dan Kondratyuk, Hartwig Adam, Hassan Akbari, Huisheng Wang, Rachel Hornung, Yin Cui","cross_cats":["cs.AI","cs.LG","cs.MM","eess.IV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-10T17:22:06Z","title":"Alternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal Perception"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.06324","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":"sha256:44a63cdf66f3079c18db7e9d7a20df67e262650f392cbe24265b0d980fd17f5b","target":"record","created_at":"2026-07-05T07:22:17Z","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":"8814608ed3430a5b43f24eaea5fe6d9948d6889b9a61f21a757615a644cf7056","cross_cats_sorted":["cs.AI","cs.LG","cs.MM","eess.IV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-10T17:22:06Z","title_canon_sha256":"ba2efb89e8a905cb72868e2b2133a7b9c9dfa02a54d1b42816f09b5409b6d8c8"},"schema_version":"1.0","source":{"id":"2305.06324","kind":"arxiv","version":2}},"canonical_sha256":"5863ac56ad84937fb9f5aa9b2476f53feb1aad507630a77b584c7b4b7fed07e0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5863ac56ad84937fb9f5aa9b2476f53feb1aad507630a77b584c7b4b7fed07e0","first_computed_at":"2026-07-05T07:22:17.744081Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:22:17.744081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VJiwoNZGRETNdJ9FwegzRwQc87TlTFopNtRLTePOHQTd9bCkLqfkavouy0WhaCYG/zfd5Lb3Lfz41NlSmwLlDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:22:17.744565Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.06324","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:44a63cdf66f3079c18db7e9d7a20df67e262650f392cbe24265b0d980fd17f5b","sha256:402fdee111dcdf9f6d3dbee93db93ca26606605b7b408de91d955b2888f679c8"],"state_sha256":"96c6cf57ca5c8bcb7a3a285c383075f562fbca5198c5b34cff5d00aaaa2f2034"}