{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DXRDPWMD27C2B5MHJ3LSDGBXFP","short_pith_number":"pith:DXRDPWMD","canonical_record":{"source":{"id":"2409.18199","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-26T18:29:10Z","cross_cats_sorted":[],"title_canon_sha256":"b6dd40b010457bf1b1747819b2deafca91c85436efc3d1837456c7417bdda842","abstract_canon_sha256":"8fe38aa96d68e5d0c13ae9b87a4f08751ffedd79ac862d6b2f7fdc106f92beb8"},"schema_version":"1.0"},"canonical_sha256":"1de237d983d7c5a0f5874ed72198372be7cc0055166c30b10178f928d024089e","source":{"kind":"arxiv","id":"2409.18199","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.18199","created_at":"2026-07-05T11:07:04Z"},{"alias_kind":"arxiv_version","alias_value":"2409.18199v2","created_at":"2026-07-05T11:07:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.18199","created_at":"2026-07-05T11:07:04Z"},{"alias_kind":"pith_short_12","alias_value":"DXRDPWMD27C2","created_at":"2026-07-05T11:07:04Z"},{"alias_kind":"pith_short_16","alias_value":"DXRDPWMD27C2B5MH","created_at":"2026-07-05T11:07:04Z"},{"alias_kind":"pith_short_8","alias_value":"DXRDPWMD","created_at":"2026-07-05T11:07:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DXRDPWMD27C2B5MHJ3LSDGBXFP","target":"record","payload":{"canonical_record":{"source":{"id":"2409.18199","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-26T18:29:10Z","cross_cats_sorted":[],"title_canon_sha256":"b6dd40b010457bf1b1747819b2deafca91c85436efc3d1837456c7417bdda842","abstract_canon_sha256":"8fe38aa96d68e5d0c13ae9b87a4f08751ffedd79ac862d6b2f7fdc106f92beb8"},"schema_version":"1.0"},"canonical_sha256":"1de237d983d7c5a0f5874ed72198372be7cc0055166c30b10178f928d024089e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:04.771334Z","signature_b64":"hN8cvm4MEzakvVy8el9FlstgfhTp+LcQmwlINkXA1uM0pZXBvFCfV+n7EOs6ehSC7d5nkd5xb04dJM70zLmTDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1de237d983d7c5a0f5874ed72198372be7cc0055166c30b10178f928d024089e","last_reissued_at":"2026-07-05T11:07:04.770861Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:04.770861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.18199","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:07:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lljzJDgtbJmx7n2F1+9ogWiIm13np6sRxpwqOEyJI8ZN51izwavWEg4mWvAPtK2o5ai3T1KCvl+wFqkxZmywDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T00:18:02.211172Z"},"content_sha256":"badd39094534bbb2db570ed777393cbce83e514ab03d45b0aac10392b92ae5ca","schema_version":"1.0","event_id":"sha256:badd39094534bbb2db570ed777393cbce83e514ab03d45b0aac10392b92ae5ca"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DXRDPWMD27C2B5MHJ3LSDGBXFP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LangSAMP: Language-Script Aware Multilingual Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chunlan Ma, Haotian Ye, Hinrich Sch\\\"utze, Mingyang Wang, Yihong Liu","submitted_at":"2024-09-26T18:29:10Z","abstract_excerpt":"Recent multilingual pretrained language models (mPLMs) often avoid using language embeddings -- learnable vectors assigned to individual languages. However, this places a significant burden on token representations to encode all language-specific information, which may hinder language neutrality. To address this limitation, we propose Language-Script Aware Multilingual Pretraining (LangSAMP), a method that incorporates both language and script embeddings to enhance representation learning. Specifically, we integrate these embeddings into the output of the Transformer blocks before passing the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.18199","kind":"arxiv","version":2},"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/2409.18199/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":"2026-07-05T11:07:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GblmZykq78SRklmq7ElfLxV/KzyVvuQcfbEraoncZn8dcJygHxoRmo1EVw8Lhvpb3aKM0Z8qUKf+bfkaI4zzAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T00:18:02.212059Z"},"content_sha256":"508e79c34137d50881b538a5a5a0293a7888434303b2475abf1c3a6314b5599b","schema_version":"1.0","event_id":"sha256:508e79c34137d50881b538a5a5a0293a7888434303b2475abf1c3a6314b5599b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DXRDPWMD27C2B5MHJ3LSDGBXFP/bundle.json","state_url":"https://pith.science/pith/DXRDPWMD27C2B5MHJ3LSDGBXFP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DXRDPWMD27C2B5MHJ3LSDGBXFP/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":"2026-08-08T00:18:02Z","links":{"resolver":"https://pith.science/pith/DXRDPWMD27C2B5MHJ3LSDGBXFP","bundle":"https://pith.science/pith/DXRDPWMD27C2B5MHJ3LSDGBXFP/bundle.json","state":"https://pith.science/pith/DXRDPWMD27C2B5MHJ3LSDGBXFP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DXRDPWMD27C2B5MHJ3LSDGBXFP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DXRDPWMD27C2B5MHJ3LSDGBXFP","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":"8fe38aa96d68e5d0c13ae9b87a4f08751ffedd79ac862d6b2f7fdc106f92beb8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-26T18:29:10Z","title_canon_sha256":"b6dd40b010457bf1b1747819b2deafca91c85436efc3d1837456c7417bdda842"},"schema_version":"1.0","source":{"id":"2409.18199","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.18199","created_at":"2026-07-05T11:07:04Z"},{"alias_kind":"arxiv_version","alias_value":"2409.18199v2","created_at":"2026-07-05T11:07:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.18199","created_at":"2026-07-05T11:07:04Z"},{"alias_kind":"pith_short_12","alias_value":"DXRDPWMD27C2","created_at":"2026-07-05T11:07:04Z"},{"alias_kind":"pith_short_16","alias_value":"DXRDPWMD27C2B5MH","created_at":"2026-07-05T11:07:04Z"},{"alias_kind":"pith_short_8","alias_value":"DXRDPWMD","created_at":"2026-07-05T11:07:04Z"}],"graph_snapshots":[{"event_id":"sha256:508e79c34137d50881b538a5a5a0293a7888434303b2475abf1c3a6314b5599b","target":"graph","created_at":"2026-07-05T11:07:04Z","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/2409.18199/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent multilingual pretrained language models (mPLMs) often avoid using language embeddings -- learnable vectors assigned to individual languages. However, this places a significant burden on token representations to encode all language-specific information, which may hinder language neutrality. To address this limitation, we propose Language-Script Aware Multilingual Pretraining (LangSAMP), a method that incorporates both language and script embeddings to enhance representation learning. Specifically, we integrate these embeddings into the output of the Transformer blocks before passing the ","authors_text":"Chunlan Ma, Haotian Ye, Hinrich Sch\\\"utze, Mingyang Wang, Yihong Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-26T18:29:10Z","title":"LangSAMP: Language-Script Aware Multilingual Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.18199","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:badd39094534bbb2db570ed777393cbce83e514ab03d45b0aac10392b92ae5ca","target":"record","created_at":"2026-07-05T11:07:04Z","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":"8fe38aa96d68e5d0c13ae9b87a4f08751ffedd79ac862d6b2f7fdc106f92beb8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-26T18:29:10Z","title_canon_sha256":"b6dd40b010457bf1b1747819b2deafca91c85436efc3d1837456c7417bdda842"},"schema_version":"1.0","source":{"id":"2409.18199","kind":"arxiv","version":2}},"canonical_sha256":"1de237d983d7c5a0f5874ed72198372be7cc0055166c30b10178f928d024089e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1de237d983d7c5a0f5874ed72198372be7cc0055166c30b10178f928d024089e","first_computed_at":"2026-07-05T11:07:04.770861Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:04.770861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hN8cvm4MEzakvVy8el9FlstgfhTp+LcQmwlINkXA1uM0pZXBvFCfV+n7EOs6ehSC7d5nkd5xb04dJM70zLmTDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:04.771334Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.18199","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:badd39094534bbb2db570ed777393cbce83e514ab03d45b0aac10392b92ae5ca","sha256:508e79c34137d50881b538a5a5a0293a7888434303b2475abf1c3a6314b5599b"],"state_sha256":"662a21cf29887928ef54c909d30e8c3e042da4166d388954e5c025f16a2f3c09"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+IzInZQRnR5jEen2xc8RObk6A2VEbtmd7vko7RNzO5y36o01AYCF2AhDAKHTN6lgS0UCrycTA2Gfg40O0VpVDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T00:18:02.237401Z","bundle_sha256":"a0ec7b3902b41126a1283d1c08bea070dc86db5122cbb7da282c1f008f8ba089"}}