{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:OR4HZNQUPUOVNEFV3LOFBKIGCR","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":"f448af31b3a38fec30a1f6121c05cdf86f4b4c4efc57000d14db59fc91e22386","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-26T15:40:24Z","title_canon_sha256":"fa46b7d7329cdb338b5afff53fe03a268e5ba3285cd78a473d110fa228e15b85"},"schema_version":"1.0","source":{"id":"2210.14793","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.14793","created_at":"2026-07-05T05:10:49Z"},{"alias_kind":"arxiv_version","alias_value":"2210.14793v1","created_at":"2026-07-05T05:10:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.14793","created_at":"2026-07-05T05:10:49Z"},{"alias_kind":"pith_short_12","alias_value":"OR4HZNQUPUOV","created_at":"2026-07-05T05:10:49Z"},{"alias_kind":"pith_short_16","alias_value":"OR4HZNQUPUOVNEFV","created_at":"2026-07-05T05:10:49Z"},{"alias_kind":"pith_short_8","alias_value":"OR4HZNQU","created_at":"2026-07-05T05:10:49Z"}],"graph_snapshots":[{"event_id":"sha256:dc51359c062d13e7ad201f04ac2d611c9ee6fb21861c7c695cfb85bc1eaaf6f7","target":"graph","created_at":"2026-07-05T05:10:49Z","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/2210.14793/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-task learning (MTL) encapsulates multiple learned tasks in a single model and often lets those tasks learn better jointly. However, when deploying MTL onto those real-world systems that are often resource-constrained or latency-sensitive, two prominent challenges arise: (i) during training, simultaneously optimizing all tasks is often difficult due to gradient conflicts across tasks; (ii) at inference, current MTL regimes have to activate nearly the entire model even to just execute a single task. Yet most real systems demand only one or two tasks at each moment, and switch between tasks","authors_text":"Cong Hao, Hanxue Liang, Kai Zou, Rishov Sarkar, Tianlong Chen, Yu Cheng, Zhangyang Wang, Zhiwen Fan, Ziyu Jiang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-26T15:40:24Z","title":"M$^3$ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.14793","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:d31b2001e98d9df9b806ff9bcfae3b1b3f7b93c2ec6b4eb2f7e23d3517044445","target":"record","created_at":"2026-07-05T05:10:49Z","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":"f448af31b3a38fec30a1f6121c05cdf86f4b4c4efc57000d14db59fc91e22386","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-26T15:40:24Z","title_canon_sha256":"fa46b7d7329cdb338b5afff53fe03a268e5ba3285cd78a473d110fa228e15b85"},"schema_version":"1.0","source":{"id":"2210.14793","kind":"arxiv","version":1}},"canonical_sha256":"74787cb6147d1d5690b5dadc50a906147364e8930fa2ac69ef00385e23873a8b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"74787cb6147d1d5690b5dadc50a906147364e8930fa2ac69ef00385e23873a8b","first_computed_at":"2026-07-05T05:10:49.786785Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:10:49.786785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hKwAS6SnTmY2V3NwI1dJAl2GLhEFXZ8/SfRmrKgIEHjDQVjrN5/ncsd0/1Tb4A7K2vVwi8X5JMteCD8YyyIaCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:10:49.787201Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.14793","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d31b2001e98d9df9b806ff9bcfae3b1b3f7b93c2ec6b4eb2f7e23d3517044445","sha256:dc51359c062d13e7ad201f04ac2d611c9ee6fb21861c7c695cfb85bc1eaaf6f7"],"state_sha256":"8c2285226699e6ebc0842d88625726c63b28b5e504c9a9432587beed11fb6e86"}