{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:QGJWDC6VAUATIMKL4VNKYTMYLO","short_pith_number":"pith:QGJWDC6V","canonical_record":{"source":{"id":"2110.03742","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-24T20:42:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"539361cda6551b2c7958e14d3f12041067ca096f5e64dd3922d57865661be3fb","abstract_canon_sha256":"d9e8f69ffdb24a3f1f4724fbdd3411bcddc30ddda2d2910cf009b2388749b958"},"schema_version":"1.0"},"canonical_sha256":"8193618bd5050134314be55aac4d985b81aba8b65d0c8b69275287d7784d8b3d","source":{"kind":"arxiv","id":"2110.03742","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.03742","created_at":"2026-07-05T03:20:46Z"},{"alias_kind":"arxiv_version","alias_value":"2110.03742v1","created_at":"2026-07-05T03:20:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03742","created_at":"2026-07-05T03:20:46Z"},{"alias_kind":"pith_short_12","alias_value":"QGJWDC6VAUAT","created_at":"2026-07-05T03:20:46Z"},{"alias_kind":"pith_short_16","alias_value":"QGJWDC6VAUATIMKL","created_at":"2026-07-05T03:20:46Z"},{"alias_kind":"pith_short_8","alias_value":"QGJWDC6V","created_at":"2026-07-05T03:20:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:QGJWDC6VAUATIMKL4VNKYTMYLO","target":"record","payload":{"canonical_record":{"source":{"id":"2110.03742","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-24T20:42:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"539361cda6551b2c7958e14d3f12041067ca096f5e64dd3922d57865661be3fb","abstract_canon_sha256":"d9e8f69ffdb24a3f1f4724fbdd3411bcddc30ddda2d2910cf009b2388749b958"},"schema_version":"1.0"},"canonical_sha256":"8193618bd5050134314be55aac4d985b81aba8b65d0c8b69275287d7784d8b3d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:20:46.762052Z","signature_b64":"jW0wyfVk0O4gwgIvVurTiw2RUzvl2Q4mqOru1/wEao4FjQftWrk2+RWbHrhGVwMsQeBG3Xh1B7BtNtN9LnVwCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8193618bd5050134314be55aac4d985b81aba8b65d0c8b69275287d7784d8b3d","last_reissued_at":"2026-07-05T03:20:46.761583Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:20:46.761583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.03742","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":"2026-07-05T03:20:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7Gmx6ZsiO7vg+nqBt1asFgbCfv1xJczWmHBvJtI/fY9w51GyIjv8l2iKISqwzo9I6wkP7H6f8fjN04w5qr1NBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:48:43.367446Z"},"content_sha256":"d02e7969c50627912966d0be3eebe1bf025601628873329dc18197cc300f4f05","schema_version":"1.0","event_id":"sha256:d02e7969c50627912966d0be3eebe1bf025601628873329dc18197cc300f4f05"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:QGJWDC6VAUATIMKL4VNKYTMYLO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ankur Bapna, Dmitry Lepikhin, Maxim Krikun, Minh-Thang Luong, Orhan Firat, Sneha Kudugunta, Yanping Huang","submitted_at":"2021-09-24T20:42:16Z","abstract_excerpt":"Sparse Mixture-of-Experts (MoE) has been a successful approach for scaling multilingual translation models to billions of parameters without a proportional increase in training computation. However, MoE models are prohibitively large and practitioners often resort to methods such as distillation for serving. In this work, we investigate routing strategies at different granularity (token, sentence, task) in MoE models to bypass distillation. Experiments on WMT and a web-scale dataset suggest that task-level routing (task-MoE) enables us to extract smaller, ready-to-deploy sub-networks from larg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03742","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/2110.03742/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":"2026-07-05T03:20:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P4NLpw0V2bPigiWl1wuQTIh1kk+jBOPCtJvU0ar3Z6/YLJyF7bVgIxiuNMk36byvtHSP73MZ9nNpTuYLyiS8CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:48:43.367954Z"},"content_sha256":"ad66fba9224cf793dde9126d4e8521d31773b45805303a22e7c9f25c80e71946","schema_version":"1.0","event_id":"sha256:ad66fba9224cf793dde9126d4e8521d31773b45805303a22e7c9f25c80e71946"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QGJWDC6VAUATIMKL4VNKYTMYLO/bundle.json","state_url":"https://pith.science/pith/QGJWDC6VAUATIMKL4VNKYTMYLO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QGJWDC6VAUATIMKL4VNKYTMYLO/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":"2026-08-09T07:48:43Z","links":{"resolver":"https://pith.science/pith/QGJWDC6VAUATIMKL4VNKYTMYLO","bundle":"https://pith.science/pith/QGJWDC6VAUATIMKL4VNKYTMYLO/bundle.json","state":"https://pith.science/pith/QGJWDC6VAUATIMKL4VNKYTMYLO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QGJWDC6VAUATIMKL4VNKYTMYLO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:QGJWDC6VAUATIMKL4VNKYTMYLO","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":"d9e8f69ffdb24a3f1f4724fbdd3411bcddc30ddda2d2910cf009b2388749b958","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-24T20:42:16Z","title_canon_sha256":"539361cda6551b2c7958e14d3f12041067ca096f5e64dd3922d57865661be3fb"},"schema_version":"1.0","source":{"id":"2110.03742","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.03742","created_at":"2026-07-05T03:20:46Z"},{"alias_kind":"arxiv_version","alias_value":"2110.03742v1","created_at":"2026-07-05T03:20:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03742","created_at":"2026-07-05T03:20:46Z"},{"alias_kind":"pith_short_12","alias_value":"QGJWDC6VAUAT","created_at":"2026-07-05T03:20:46Z"},{"alias_kind":"pith_short_16","alias_value":"QGJWDC6VAUATIMKL","created_at":"2026-07-05T03:20:46Z"},{"alias_kind":"pith_short_8","alias_value":"QGJWDC6V","created_at":"2026-07-05T03:20:46Z"}],"graph_snapshots":[{"event_id":"sha256:ad66fba9224cf793dde9126d4e8521d31773b45805303a22e7c9f25c80e71946","target":"graph","created_at":"2026-07-05T03:20:46Z","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/2110.03742/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sparse Mixture-of-Experts (MoE) has been a successful approach for scaling multilingual translation models to billions of parameters without a proportional increase in training computation. However, MoE models are prohibitively large and practitioners often resort to methods such as distillation for serving. In this work, we investigate routing strategies at different granularity (token, sentence, task) in MoE models to bypass distillation. Experiments on WMT and a web-scale dataset suggest that task-level routing (task-MoE) enables us to extract smaller, ready-to-deploy sub-networks from larg","authors_text":"Ankur Bapna, Dmitry Lepikhin, Maxim Krikun, Minh-Thang Luong, Orhan Firat, Sneha Kudugunta, Yanping Huang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-24T20:42:16Z","title":"Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03742","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:d02e7969c50627912966d0be3eebe1bf025601628873329dc18197cc300f4f05","target":"record","created_at":"2026-07-05T03:20:46Z","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":"d9e8f69ffdb24a3f1f4724fbdd3411bcddc30ddda2d2910cf009b2388749b958","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-24T20:42:16Z","title_canon_sha256":"539361cda6551b2c7958e14d3f12041067ca096f5e64dd3922d57865661be3fb"},"schema_version":"1.0","source":{"id":"2110.03742","kind":"arxiv","version":1}},"canonical_sha256":"8193618bd5050134314be55aac4d985b81aba8b65d0c8b69275287d7784d8b3d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8193618bd5050134314be55aac4d985b81aba8b65d0c8b69275287d7784d8b3d","first_computed_at":"2026-07-05T03:20:46.761583Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:20:46.761583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jW0wyfVk0O4gwgIvVurTiw2RUzvl2Q4mqOru1/wEao4FjQftWrk2+RWbHrhGVwMsQeBG3Xh1B7BtNtN9LnVwCw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:20:46.762052Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.03742","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d02e7969c50627912966d0be3eebe1bf025601628873329dc18197cc300f4f05","sha256:ad66fba9224cf793dde9126d4e8521d31773b45805303a22e7c9f25c80e71946"],"state_sha256":"951c06e8e6b9ca936be654b17596ba05441ac57873a5d7bb7d2bd56a3f6f1b27"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d+wzKPsTDDUEazWm8q2XzAxp6ge3IrAsCoNxpYO2wCaauAC9yPKtM+WcriEqiOcIXl1AmAzDBV6uJd2Pu7m4AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T07:48:43.373748Z","bundle_sha256":"55bd4ead8f16023ceb3a9837c0d76b8e3347fbba1e0677428acb09237c2c371c"}}