{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MGWANPOAL4ORNF2QCJWXSKZFZB","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":"bbab00c34b33394c0b6b65f2d1a9308824ed7318c02b5de5d17af50a445103aa","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-24T16:03:57Z","title_canon_sha256":"0c0e3dfbf7a7da0e0feb393a3c67529352b6eafd8e7c48cccd2b46a53d93ff47"},"schema_version":"1.0","source":{"id":"2310.15961","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.15961","created_at":"2026-07-05T09:10:43Z"},{"alias_kind":"arxiv_version","alias_value":"2310.15961v2","created_at":"2026-07-05T09:10:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.15961","created_at":"2026-07-05T09:10:43Z"},{"alias_kind":"pith_short_12","alias_value":"MGWANPOAL4OR","created_at":"2026-07-05T09:10:43Z"},{"alias_kind":"pith_short_16","alias_value":"MGWANPOAL4ORNF2Q","created_at":"2026-07-05T09:10:43Z"},{"alias_kind":"pith_short_8","alias_value":"MGWANPOA","created_at":"2026-07-05T09:10:43Z"}],"graph_snapshots":[{"event_id":"sha256:b634f85706d19b84ec8c2dafb1fa93aa47bc1c18323f1b558a2bce5c27e97987","target":"graph","created_at":"2026-07-05T09:10:43Z","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/2310.15961/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mixture of Experts (MoE) models based on Transformer architecture are pushing the boundaries of language and vision tasks. The allure of these models lies in their ability to substantially increase the parameter count without a corresponding increase in FLOPs. Most widely adopted MoE models are discontinuous with respect to their parameters - often referred to as sparse. At the same time, existing continuous MoE designs either lag behind their sparse counterparts or are incompatible with autoregressive decoding. Motivated by the observation that the adaptation of fully continuous methods has b","authors_text":"Jakub Krajewski, Jan Ludziejewski, Kamil Ciebiera, Krystian Kr\\'ol, Maciej Pi\\'oro, Marek Cygan, Micha{\\l} Krutul, Sebastian Jaszczur, Szymon Antoniak, Tomasz Odrzyg\\'o\\'zd\\'z","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-24T16:03:57Z","title":"Mixture of Tokens: Continuous MoE through Cross-Example Aggregation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.15961","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":"sha256:8c84d09972780a08ede3644736a863b603e6479a9aaea93d9b2eeff50307d4e5","target":"record","created_at":"2026-07-05T09:10:43Z","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":"bbab00c34b33394c0b6b65f2d1a9308824ed7318c02b5de5d17af50a445103aa","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-24T16:03:57Z","title_canon_sha256":"0c0e3dfbf7a7da0e0feb393a3c67529352b6eafd8e7c48cccd2b46a53d93ff47"},"schema_version":"1.0","source":{"id":"2310.15961","kind":"arxiv","version":2}},"canonical_sha256":"61ac06bdc05f1d169750126d792b25c8531f7dd72daf1e83210840951bc8ad86","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"61ac06bdc05f1d169750126d792b25c8531f7dd72daf1e83210840951bc8ad86","first_computed_at":"2026-07-05T09:10:43.074727Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:10:43.074727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1KCaOmW46z46OvQj1hxY0lEFoGKKG57ECtepMokhnrCp1FVBtjV+DoCfQQ/c0gYayrEGI8OLHm5sWPJ/r8KTAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:10:43.075166Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.15961","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c84d09972780a08ede3644736a863b603e6479a9aaea93d9b2eeff50307d4e5","sha256:b634f85706d19b84ec8c2dafb1fa93aa47bc1c18323f1b558a2bce5c27e97987"],"state_sha256":"d7f67f25d8f85f9c6839f0e326021048fc214c08ad2119becd9a6bca38fa5429"}