{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:RJ5KQ76BH5F4Z5TMGWWZU4WFF4","short_pith_number":"pith:RJ5KQ76B","canonical_record":{"source":{"id":"2306.07610","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-13T08:08:08Z","cross_cats_sorted":[],"title_canon_sha256":"d13dcf446e9d604a11431b25342aab50c4522dc66e478b2bddbddc9cb3157faa","abstract_canon_sha256":"d4a6b66f09215d23ca39a6a47b3cdb5793c61f28db0779f7bf27b00347cc0fe1"},"schema_version":"1.0"},"canonical_sha256":"8a7aa87fc13f4bccf66c35ad9a72c52f348a32a91e42520ca834ccb0450e5f2f","source":{"kind":"arxiv","id":"2306.07610","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.07610","created_at":"2026-07-05T06:20:06Z"},{"alias_kind":"arxiv_version","alias_value":"2306.07610v1","created_at":"2026-07-05T06:20:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07610","created_at":"2026-07-05T06:20:06Z"},{"alias_kind":"pith_short_12","alias_value":"RJ5KQ76BH5F4","created_at":"2026-07-05T06:20:06Z"},{"alias_kind":"pith_short_16","alias_value":"RJ5KQ76BH5F4Z5TM","created_at":"2026-07-05T06:20:06Z"},{"alias_kind":"pith_short_8","alias_value":"RJ5KQ76B","created_at":"2026-07-05T06:20:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:RJ5KQ76BH5F4Z5TMGWWZU4WFF4","target":"record","payload":{"canonical_record":{"source":{"id":"2306.07610","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-13T08:08:08Z","cross_cats_sorted":[],"title_canon_sha256":"d13dcf446e9d604a11431b25342aab50c4522dc66e478b2bddbddc9cb3157faa","abstract_canon_sha256":"d4a6b66f09215d23ca39a6a47b3cdb5793c61f28db0779f7bf27b00347cc0fe1"},"schema_version":"1.0"},"canonical_sha256":"8a7aa87fc13f4bccf66c35ad9a72c52f348a32a91e42520ca834ccb0450e5f2f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:20:06.780631Z","signature_b64":"06uVuwN96ayRsT1YVLoo4fOaXnsI2U3K9pg3X4nUWz6Tdt0TugZgdjoDwVmsfZIVJ8eEtqY+IZZvOmTKvusUAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a7aa87fc13f4bccf66c35ad9a72c52f348a32a91e42520ca834ccb0450e5f2f","last_reissued_at":"2026-07-05T06:20:06.780253Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:20:06.780253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.07610","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":"2026-07-05T06:20:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5dy6OGJR1rdpy+mWYgBwCecETjtFAIjQNpMPbk7wTpelbcgsnE65+RPXn5SSf5Gk3v4htfstBK/uFwu9p0XhCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:53:15.082089Z"},"content_sha256":"1cb2984e9a347c8dfae9e9351b9415419e1723f6a7e146718e7028605e44fb83","schema_version":"1.0","event_id":"sha256:1cb2984e9a347c8dfae9e9351b9415419e1723f6a7e146718e7028605e44fb83"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:RJ5KQ76BH5F4Z5TMGWWZU4WFF4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Soft Language Clustering for Multilingual Model Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Binghuai Lin, Fandong Meng, Jiali Zeng, Jie Zhou, Yi Jing, Yongjing Yin, Yufan Jiang, Yunbo Cao","submitted_at":"2023-06-13T08:08:08Z","abstract_excerpt":"Multilingual pre-trained language models have demonstrated impressive (zero-shot) cross-lingual transfer abilities, however, their performance is hindered when the target language has distant typology from source languages or when pre-training data is limited in size. In this paper, we propose XLM-P, which contextually retrieves prompts as flexible guidance for encoding instances conditionally. Our XLM-P enables (1) lightweight modeling of language-invariant and language-specific knowledge across languages, and (2) easy integration with other multilingual pre-training methods. On the tasks of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07610","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/2306.07610/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":"2026-07-05T06:20:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/gaGnoiTLVIKwFYxFAXSSB1QYnCceHoVZ+Fz0XbEvwqIxnrNEIQ7ECliGyTK3vQqrj0fyuLQ1lu1fMglvOsxBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:53:15.082480Z"},"content_sha256":"162950f65e5d489a6b0988f84d0f832fdac05338bc90ed16abda955dcbf3b959","schema_version":"1.0","event_id":"sha256:162950f65e5d489a6b0988f84d0f832fdac05338bc90ed16abda955dcbf3b959"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RJ5KQ76BH5F4Z5TMGWWZU4WFF4/bundle.json","state_url":"https://pith.science/pith/RJ5KQ76BH5F4Z5TMGWWZU4WFF4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RJ5KQ76BH5F4Z5TMGWWZU4WFF4/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":"2026-08-03T15:53:15Z","links":{"resolver":"https://pith.science/pith/RJ5KQ76BH5F4Z5TMGWWZU4WFF4","bundle":"https://pith.science/pith/RJ5KQ76BH5F4Z5TMGWWZU4WFF4/bundle.json","state":"https://pith.science/pith/RJ5KQ76BH5F4Z5TMGWWZU4WFF4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RJ5KQ76BH5F4Z5TMGWWZU4WFF4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RJ5KQ76BH5F4Z5TMGWWZU4WFF4","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":"d4a6b66f09215d23ca39a6a47b3cdb5793c61f28db0779f7bf27b00347cc0fe1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-13T08:08:08Z","title_canon_sha256":"d13dcf446e9d604a11431b25342aab50c4522dc66e478b2bddbddc9cb3157faa"},"schema_version":"1.0","source":{"id":"2306.07610","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.07610","created_at":"2026-07-05T06:20:06Z"},{"alias_kind":"arxiv_version","alias_value":"2306.07610v1","created_at":"2026-07-05T06:20:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07610","created_at":"2026-07-05T06:20:06Z"},{"alias_kind":"pith_short_12","alias_value":"RJ5KQ76BH5F4","created_at":"2026-07-05T06:20:06Z"},{"alias_kind":"pith_short_16","alias_value":"RJ5KQ76BH5F4Z5TM","created_at":"2026-07-05T06:20:06Z"},{"alias_kind":"pith_short_8","alias_value":"RJ5KQ76B","created_at":"2026-07-05T06:20:06Z"}],"graph_snapshots":[{"event_id":"sha256:162950f65e5d489a6b0988f84d0f832fdac05338bc90ed16abda955dcbf3b959","target":"graph","created_at":"2026-07-05T06:20:06Z","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/2306.07610/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multilingual pre-trained language models have demonstrated impressive (zero-shot) cross-lingual transfer abilities, however, their performance is hindered when the target language has distant typology from source languages or when pre-training data is limited in size. In this paper, we propose XLM-P, which contextually retrieves prompts as flexible guidance for encoding instances conditionally. Our XLM-P enables (1) lightweight modeling of language-invariant and language-specific knowledge across languages, and (2) easy integration with other multilingual pre-training methods. On the tasks of ","authors_text":"Binghuai Lin, Fandong Meng, Jiali Zeng, Jie Zhou, Yi Jing, Yongjing Yin, Yufan Jiang, Yunbo Cao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-13T08:08:08Z","title":"Soft Language Clustering for Multilingual Model Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07610","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":"sha256:1cb2984e9a347c8dfae9e9351b9415419e1723f6a7e146718e7028605e44fb83","target":"record","created_at":"2026-07-05T06:20:06Z","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":"d4a6b66f09215d23ca39a6a47b3cdb5793c61f28db0779f7bf27b00347cc0fe1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-13T08:08:08Z","title_canon_sha256":"d13dcf446e9d604a11431b25342aab50c4522dc66e478b2bddbddc9cb3157faa"},"schema_version":"1.0","source":{"id":"2306.07610","kind":"arxiv","version":1}},"canonical_sha256":"8a7aa87fc13f4bccf66c35ad9a72c52f348a32a91e42520ca834ccb0450e5f2f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a7aa87fc13f4bccf66c35ad9a72c52f348a32a91e42520ca834ccb0450e5f2f","first_computed_at":"2026-07-05T06:20:06.780253Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:20:06.780253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"06uVuwN96ayRsT1YVLoo4fOaXnsI2U3K9pg3X4nUWz6Tdt0TugZgdjoDwVmsfZIVJ8eEtqY+IZZvOmTKvusUAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:20:06.780631Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.07610","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1cb2984e9a347c8dfae9e9351b9415419e1723f6a7e146718e7028605e44fb83","sha256:162950f65e5d489a6b0988f84d0f832fdac05338bc90ed16abda955dcbf3b959"],"state_sha256":"f2829f75f8d2afc4da91f2e245f18a3ba213d6d608afe2511d30dcad4e758e18"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CyPtY6D6PBlBD2rGw6bqAxnYQ22Q+dm/gX6OXw8oS11tFKoroEg8jI/NOVq1yZ/BVcZn/BaqRAZz5ID1CwsLBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T15:53:15.085523Z","bundle_sha256":"41ba5fb2a0e8887a9ce27843205589b8bb92076fdf0ebe139003cb0927e86073"}}