{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MKL32UG7SHJEUPZXP76UM6EL5O","short_pith_number":"pith:MKL32UG7","canonical_record":{"source":{"id":"2407.01126","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T09:45:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ddcca4d6020569be5a55c98f446e09a8282211ba47735673d115c7a5f22b8114","abstract_canon_sha256":"e8256926a017b600ea66933db73ed0bd46c8ec4c7fa94e1e47a18e236fb5f0f1"},"schema_version":"1.0"},"canonical_sha256":"6297bd50df91d24a3f377ffd46788beba16cc81249e1c2302ce1dfed52f3cace","source":{"kind":"arxiv","id":"2407.01126","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.01126","created_at":"2026-07-05T08:38:43Z"},{"alias_kind":"arxiv_version","alias_value":"2407.01126v1","created_at":"2026-07-05T08:38:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01126","created_at":"2026-07-05T08:38:43Z"},{"alias_kind":"pith_short_12","alias_value":"MKL32UG7SHJE","created_at":"2026-07-05T08:38:43Z"},{"alias_kind":"pith_short_16","alias_value":"MKL32UG7SHJEUPZX","created_at":"2026-07-05T08:38:43Z"},{"alias_kind":"pith_short_8","alias_value":"MKL32UG7","created_at":"2026-07-05T08:38:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MKL32UG7SHJEUPZXP76UM6EL5O","target":"record","payload":{"canonical_record":{"source":{"id":"2407.01126","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T09:45:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ddcca4d6020569be5a55c98f446e09a8282211ba47735673d115c7a5f22b8114","abstract_canon_sha256":"e8256926a017b600ea66933db73ed0bd46c8ec4c7fa94e1e47a18e236fb5f0f1"},"schema_version":"1.0"},"canonical_sha256":"6297bd50df91d24a3f377ffd46788beba16cc81249e1c2302ce1dfed52f3cace","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:43.538769Z","signature_b64":"iJklvITImbcDVzXiH+2u4SiGDYUrjb8GDlJlG8nreqhzPvU86PRTakgBMGMtEptw+MV5+1ekNncFXPX3/esFAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6297bd50df91d24a3f377ffd46788beba16cc81249e1c2302ce1dfed52f3cace","last_reissued_at":"2026-07-05T08:38:43.538351Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:43.538351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.01126","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":"2026-07-05T08:38:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JZ27FPas3LJEP/JQJu1gxc/ZV2C4EF2AS/NhcEmA+fJOeXcsZmy6hQGZzA9TbrqjDIM2XGwaJ/hl7nSCFXg0BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:55:56.771508Z"},"content_sha256":"17d916628fce26d33126c0a8d53667e7d0bf6b4aa2bc3a81d2898ce23fc8639a","schema_version":"1.0","event_id":"sha256:17d916628fce26d33126c0a8d53667e7d0bf6b4aa2bc3a81d2898ce23fc8639a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MKL32UG7SHJEUPZXP76UM6EL5O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Investigating the potential of Sparse Mixtures-of-Experts for multi-domain neural machine translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alexandre B\\'erard, Jean-Luc Meunier, Nadezhda Chirkova, Vassilina Nikoulina","submitted_at":"2024-07-01T09:45:22Z","abstract_excerpt":"We focus on multi-domain Neural Machine Translation, with the goal of developing efficient models which can handle data from various domains seen during training and are robust to domains unseen during training. We hypothesize that Sparse Mixture-of-Experts (SMoE) models are a good fit for this task, as they enable efficient model scaling, which helps to accommodate a variety of multi-domain data, and allow flexible sharing of parameters between domains, potentially enabling knowledge transfer between similar domains and limiting negative transfer. We conduct a series of experiments aimed at v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01126","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/2407.01126/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":"2026-07-05T08:38:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7dgqeRuu5+u5JeydlnnopRYhn/+fSuE1rlfiICnK/gZOopXaCHhcPGUmJ8aMBf+6ewAVl9kwimutHbta2iZwDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:55:56.772130Z"},"content_sha256":"57cc90af440d7ccbcec250f1a002469eeb39271839c0b095fe3c21e10c662461","schema_version":"1.0","event_id":"sha256:57cc90af440d7ccbcec250f1a002469eeb39271839c0b095fe3c21e10c662461"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MKL32UG7SHJEUPZXP76UM6EL5O/bundle.json","state_url":"https://pith.science/pith/MKL32UG7SHJEUPZXP76UM6EL5O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MKL32UG7SHJEUPZXP76UM6EL5O/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":"2026-08-09T05:55:56Z","links":{"resolver":"https://pith.science/pith/MKL32UG7SHJEUPZXP76UM6EL5O","bundle":"https://pith.science/pith/MKL32UG7SHJEUPZXP76UM6EL5O/bundle.json","state":"https://pith.science/pith/MKL32UG7SHJEUPZXP76UM6EL5O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MKL32UG7SHJEUPZXP76UM6EL5O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MKL32UG7SHJEUPZXP76UM6EL5O","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":"e8256926a017b600ea66933db73ed0bd46c8ec4c7fa94e1e47a18e236fb5f0f1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T09:45:22Z","title_canon_sha256":"ddcca4d6020569be5a55c98f446e09a8282211ba47735673d115c7a5f22b8114"},"schema_version":"1.0","source":{"id":"2407.01126","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.01126","created_at":"2026-07-05T08:38:43Z"},{"alias_kind":"arxiv_version","alias_value":"2407.01126v1","created_at":"2026-07-05T08:38:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01126","created_at":"2026-07-05T08:38:43Z"},{"alias_kind":"pith_short_12","alias_value":"MKL32UG7SHJE","created_at":"2026-07-05T08:38:43Z"},{"alias_kind":"pith_short_16","alias_value":"MKL32UG7SHJEUPZX","created_at":"2026-07-05T08:38:43Z"},{"alias_kind":"pith_short_8","alias_value":"MKL32UG7","created_at":"2026-07-05T08:38:43Z"}],"graph_snapshots":[{"event_id":"sha256:57cc90af440d7ccbcec250f1a002469eeb39271839c0b095fe3c21e10c662461","target":"graph","created_at":"2026-07-05T08:38:43Z","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/2407.01126/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We focus on multi-domain Neural Machine Translation, with the goal of developing efficient models which can handle data from various domains seen during training and are robust to domains unseen during training. We hypothesize that Sparse Mixture-of-Experts (SMoE) models are a good fit for this task, as they enable efficient model scaling, which helps to accommodate a variety of multi-domain data, and allow flexible sharing of parameters between domains, potentially enabling knowledge transfer between similar domains and limiting negative transfer. We conduct a series of experiments aimed at v","authors_text":"Alexandre B\\'erard, Jean-Luc Meunier, Nadezhda Chirkova, Vassilina Nikoulina","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T09:45:22Z","title":"Investigating the potential of Sparse Mixtures-of-Experts for multi-domain neural machine translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01126","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":"sha256:17d916628fce26d33126c0a8d53667e7d0bf6b4aa2bc3a81d2898ce23fc8639a","target":"record","created_at":"2026-07-05T08:38:43Z","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":"e8256926a017b600ea66933db73ed0bd46c8ec4c7fa94e1e47a18e236fb5f0f1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T09:45:22Z","title_canon_sha256":"ddcca4d6020569be5a55c98f446e09a8282211ba47735673d115c7a5f22b8114"},"schema_version":"1.0","source":{"id":"2407.01126","kind":"arxiv","version":1}},"canonical_sha256":"6297bd50df91d24a3f377ffd46788beba16cc81249e1c2302ce1dfed52f3cace","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6297bd50df91d24a3f377ffd46788beba16cc81249e1c2302ce1dfed52f3cace","first_computed_at":"2026-07-05T08:38:43.538351Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:38:43.538351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iJklvITImbcDVzXiH+2u4SiGDYUrjb8GDlJlG8nreqhzPvU86PRTakgBMGMtEptw+MV5+1ekNncFXPX3/esFAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:38:43.538769Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.01126","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:17d916628fce26d33126c0a8d53667e7d0bf6b4aa2bc3a81d2898ce23fc8639a","sha256:57cc90af440d7ccbcec250f1a002469eeb39271839c0b095fe3c21e10c662461"],"state_sha256":"cd2a81678ac71d1d8f35887af51bf5bb510d33d0d249847d4f10e4a5bfc79401"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oYliErD/BIt8Frl2SD4DDWjfWyiwcwioW2VIpOdB5GQqIhPlIykmRBLzVglUCUKRpzZIPRRCnMNhNn3qA/4OCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T05:55:56.775744Z","bundle_sha256":"3018458ffc2c8edd84b9103e47e287cd8f5cf63fdce186d4e5e3c9ebd9e79b0b"}}