{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VNNUH3EO6V37XHFXAWHDIEUR6X","short_pith_number":"pith:VNNUH3EO","canonical_record":{"source":{"id":"2608.03480","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-04T11:17:54Z","cross_cats_sorted":[],"title_canon_sha256":"15fdb287b82e93356db4f6497166f8046ff0aa3f39a2d2b56f2f057b059e9661","abstract_canon_sha256":"77491b63c629bffb01fc552ac68a71380dc3926292fee59439958b6b17427aae"},"schema_version":"1.0"},"canonical_sha256":"ab5b43ec8ef577fb9cb7058e341291f5edf9ebf2cfecf7ada45052c9fda52609","source":{"kind":"arxiv","id":"2608.03480","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03480","created_at":"2026-08-05T01:35:55Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03480v1","created_at":"2026-08-05T01:35:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03480","created_at":"2026-08-05T01:35:55Z"},{"alias_kind":"pith_short_12","alias_value":"VNNUH3EO6V37","created_at":"2026-08-05T01:35:55Z"},{"alias_kind":"pith_short_16","alias_value":"VNNUH3EO6V37XHFX","created_at":"2026-08-05T01:35:55Z"},{"alias_kind":"pith_short_8","alias_value":"VNNUH3EO","created_at":"2026-08-05T01:35:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VNNUH3EO6V37XHFXAWHDIEUR6X","target":"record","payload":{"canonical_record":{"source":{"id":"2608.03480","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-04T11:17:54Z","cross_cats_sorted":[],"title_canon_sha256":"15fdb287b82e93356db4f6497166f8046ff0aa3f39a2d2b56f2f057b059e9661","abstract_canon_sha256":"77491b63c629bffb01fc552ac68a71380dc3926292fee59439958b6b17427aae"},"schema_version":"1.0"},"canonical_sha256":"ab5b43ec8ef577fb9cb7058e341291f5edf9ebf2cfecf7ada45052c9fda52609","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T01:35:55.944769Z","signature_b64":"1mZq9K3zaizYOW3zel722BvDzw3XNkODmXHMqRFqnoG8+3e29wHtUwt4C51IBPlEVAZ/fzXbGd15A7tQC8UgCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab5b43ec8ef577fb9cb7058e341291f5edf9ebf2cfecf7ada45052c9fda52609","last_reissued_at":"2026-08-05T01:35:55.943328Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T01:35:55.943328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.03480","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":"2026-08-05T01:35:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dKAMwaXT2ePUibMECY6pmS+5vaV6sYlnfw1FeZWAA4fJhlLoFB2cFTebuj6Rn643b7gbWobYVf+mz9Mmliy1AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T09:32:43.073141Z"},"content_sha256":"ad1ad307e8fe0d19be67e23a2ccc2215ccaca00f71aac3ba91faad700e49ee1e","schema_version":"1.0","event_id":"sha256:ad1ad307e8fe0d19be67e23a2ccc2215ccaca00f71aac3ba91faad700e49ee1e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VNNUH3EO6V37XHFXAWHDIEUR6X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Multilingual Neural Machine Translation via Corpus-Driven Vocabulary Pruning: An English-Arabic Case Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmed Amine Aliane, Hassina Aliane, Nasredine Semmar","submitted_at":"2026-08-04T11:17:54Z","abstract_excerpt":"The adoption of large pre-trained multilingual models for neural machine translation (MNMT) faces a major challenge: excessive memory and computational consumption due to overly large vocabularies and embedding layers. Although existing compression methods like pruning, quantization and knowledge distillation reduce parameter redundancy, they mainly preserve the structure of the original vocabulary, thereby leaving a major source of inefficiency unresolved. We propose in this paper a general optimization framework that combines a vocabulary pruning method with a targeted fine-tuning protocol f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03480","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/2608.03480/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":"2026-08-05T01:35:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZzZ3gMj84WU6EjC71p5oEjDfL144k9GhmJqxU8e33z4hwRWG5YQaHxLH4z0uTtD2t0Hjm/MoU10cZWWblU5bDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T09:32:43.073665Z"},"content_sha256":"0504a809118bceccac8e8f5359b607a3259899836b0565ddc7765780af4230dc","schema_version":"1.0","event_id":"sha256:0504a809118bceccac8e8f5359b607a3259899836b0565ddc7765780af4230dc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VNNUH3EO6V37XHFXAWHDIEUR6X/bundle.json","state_url":"https://pith.science/pith/VNNUH3EO6V37XHFXAWHDIEUR6X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VNNUH3EO6V37XHFXAWHDIEUR6X/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":"2026-08-09T09:32:43Z","links":{"resolver":"https://pith.science/pith/VNNUH3EO6V37XHFXAWHDIEUR6X","bundle":"https://pith.science/pith/VNNUH3EO6V37XHFXAWHDIEUR6X/bundle.json","state":"https://pith.science/pith/VNNUH3EO6V37XHFXAWHDIEUR6X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VNNUH3EO6V37XHFXAWHDIEUR6X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VNNUH3EO6V37XHFXAWHDIEUR6X","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":"77491b63c629bffb01fc552ac68a71380dc3926292fee59439958b6b17427aae","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-04T11:17:54Z","title_canon_sha256":"15fdb287b82e93356db4f6497166f8046ff0aa3f39a2d2b56f2f057b059e9661"},"schema_version":"1.0","source":{"id":"2608.03480","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03480","created_at":"2026-08-05T01:35:55Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03480v1","created_at":"2026-08-05T01:35:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03480","created_at":"2026-08-05T01:35:55Z"},{"alias_kind":"pith_short_12","alias_value":"VNNUH3EO6V37","created_at":"2026-08-05T01:35:55Z"},{"alias_kind":"pith_short_16","alias_value":"VNNUH3EO6V37XHFX","created_at":"2026-08-05T01:35:55Z"},{"alias_kind":"pith_short_8","alias_value":"VNNUH3EO","created_at":"2026-08-05T01:35:55Z"}],"graph_snapshots":[{"event_id":"sha256:0504a809118bceccac8e8f5359b607a3259899836b0565ddc7765780af4230dc","target":"graph","created_at":"2026-08-05T01:35:55Z","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/2608.03480/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The adoption of large pre-trained multilingual models for neural machine translation (MNMT) faces a major challenge: excessive memory and computational consumption due to overly large vocabularies and embedding layers. Although existing compression methods like pruning, quantization and knowledge distillation reduce parameter redundancy, they mainly preserve the structure of the original vocabulary, thereby leaving a major source of inefficiency unresolved. We propose in this paper a general optimization framework that combines a vocabulary pruning method with a targeted fine-tuning protocol f","authors_text":"Ahmed Amine Aliane, Hassina Aliane, Nasredine Semmar","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-04T11:17:54Z","title":"Efficient Multilingual Neural Machine Translation via Corpus-Driven Vocabulary Pruning: An English-Arabic Case Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03480","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:ad1ad307e8fe0d19be67e23a2ccc2215ccaca00f71aac3ba91faad700e49ee1e","target":"record","created_at":"2026-08-05T01:35:55Z","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":"77491b63c629bffb01fc552ac68a71380dc3926292fee59439958b6b17427aae","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-04T11:17:54Z","title_canon_sha256":"15fdb287b82e93356db4f6497166f8046ff0aa3f39a2d2b56f2f057b059e9661"},"schema_version":"1.0","source":{"id":"2608.03480","kind":"arxiv","version":1}},"canonical_sha256":"ab5b43ec8ef577fb9cb7058e341291f5edf9ebf2cfecf7ada45052c9fda52609","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ab5b43ec8ef577fb9cb7058e341291f5edf9ebf2cfecf7ada45052c9fda52609","first_computed_at":"2026-08-05T01:35:55.943328Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T01:35:55.943328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1mZq9K3zaizYOW3zel722BvDzw3XNkODmXHMqRFqnoG8+3e29wHtUwt4C51IBPlEVAZ/fzXbGd15A7tQC8UgCA==","signature_status":"signed_v1","signed_at":"2026-08-05T01:35:55.944769Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.03480","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ad1ad307e8fe0d19be67e23a2ccc2215ccaca00f71aac3ba91faad700e49ee1e","sha256:0504a809118bceccac8e8f5359b607a3259899836b0565ddc7765780af4230dc"],"state_sha256":"25ccfb428b972ee03fcf12c409494aec8c3a27fb760c56daf816ce4208ccbcb8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DjMKxrpF9Nv7agmT/epQJfpJbMzYxpS5RqkRStXPYInUMp4bdASz0Vu2U70cKk0EIwCirmU7cg0C170AJiuPCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T09:32:43.077098Z","bundle_sha256":"61e83cf0d4fcbf5f512bf05ad0dc0532186f7f183f98c0ecc4b9e6e4a909863e"}}