{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:I5GT5NTG7GJSKP2T3ZGPRFRSNP","short_pith_number":"pith:I5GT5NTG","canonical_record":{"source":{"id":"2311.09732","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-16T10:03:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6d34117a15197e7356328afd365841d29aa42c45a9b0775a5058214046e1293d","abstract_canon_sha256":"86787893a39df60160d31fe32c6ae5eae1404c3725ef0ad1e2cebbb3411a1d01"},"schema_version":"1.0"},"canonical_sha256":"474d3eb666f993253f53de4cf896326bf6a197939f21802ab33ccc9fc024044d","source":{"kind":"arxiv","id":"2311.09732","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.09732","created_at":"2026-07-05T07:13:32Z"},{"alias_kind":"arxiv_version","alias_value":"2311.09732v1","created_at":"2026-07-05T07:13:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09732","created_at":"2026-07-05T07:13:32Z"},{"alias_kind":"pith_short_12","alias_value":"I5GT5NTG7GJS","created_at":"2026-07-05T07:13:32Z"},{"alias_kind":"pith_short_16","alias_value":"I5GT5NTG7GJSKP2T","created_at":"2026-07-05T07:13:32Z"},{"alias_kind":"pith_short_8","alias_value":"I5GT5NTG","created_at":"2026-07-05T07:13:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:I5GT5NTG7GJSKP2T3ZGPRFRSNP","target":"record","payload":{"canonical_record":{"source":{"id":"2311.09732","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-16T10:03:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6d34117a15197e7356328afd365841d29aa42c45a9b0775a5058214046e1293d","abstract_canon_sha256":"86787893a39df60160d31fe32c6ae5eae1404c3725ef0ad1e2cebbb3411a1d01"},"schema_version":"1.0"},"canonical_sha256":"474d3eb666f993253f53de4cf896326bf6a197939f21802ab33ccc9fc024044d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:13:32.182774Z","signature_b64":"MCrZBjrHmasNin+2myXbKIST5h2mbSebLoXwinomZE7JJnKNH81MWwKaVa0/E24mTJg5J61NbDQheSPj3dkaCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"474d3eb666f993253f53de4cf896326bf6a197939f21802ab33ccc9fc024044d","last_reissued_at":"2026-07-05T07:13:32.182216Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:13:32.182216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.09732","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":"2026-07-05T07:13:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/nUOmsYVW0vXVY9ARfvGTHO8MgXBsJdc2ONnN3w1rhDOFZ5xCqvDwc6hgDf7lHUiVh63a+J0zZEnd2O3izeQBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:33:44.802221Z"},"content_sha256":"0e5759e3f61acc13979c838fd41ab1e62f884279bebdf69f4468066206284b47","schema_version":"1.0","event_id":"sha256:0e5759e3f61acc13979c838fd41ab1e62f884279bebdf69f4468066206284b47"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:I5GT5NTG7GJSKP2T3ZGPRFRSNP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Source Prompt: Coordinated Pre-training of Language Models on Diverse Corpora from Multiple Sources","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dakuan Lu, Hengkui Wu, Jiaqing Liang, Ken Chen, ruiji zhang, Xintao Wang, Yanghua Xiao, Yingsi Xin, Yipei Xu, Yipeng Geng","submitted_at":"2023-11-16T10:03:26Z","abstract_excerpt":"Pre-trained language models (PLMs) have established the new paradigm in the field of NLP. For more powerful PLMs, one of the most popular and successful way is to continuously scale up sizes of the models and the pre-training corpora. These large corpora are generally obtained by converging smaller ones from multiple sources, they are thus growing increasingly diverse. However, the side-effects of these colossal converged corpora remain understudied. In this paper, we identify the disadvantage of heterogeneous corpora from multiple sources for pre-training PLMs. Towards coordinated pre-trainin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09732","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/2311.09732/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":"2026-07-05T07:13:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0kd74WJ8m2atFOWCQcya+rLN9gRiT0kMMGucaNadCX1I5dRm+6FbozeYVc2x51Xbuks5gBfNMGcH4wbG0EF5BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:33:44.803376Z"},"content_sha256":"cd1b0e3df3bc96895cc741cc00ad0143721143d70b6a73f6f5ecf7ec5f8c842d","schema_version":"1.0","event_id":"sha256:cd1b0e3df3bc96895cc741cc00ad0143721143d70b6a73f6f5ecf7ec5f8c842d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I5GT5NTG7GJSKP2T3ZGPRFRSNP/bundle.json","state_url":"https://pith.science/pith/I5GT5NTG7GJSKP2T3ZGPRFRSNP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I5GT5NTG7GJSKP2T3ZGPRFRSNP/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":"2026-08-03T17:33:44Z","links":{"resolver":"https://pith.science/pith/I5GT5NTG7GJSKP2T3ZGPRFRSNP","bundle":"https://pith.science/pith/I5GT5NTG7GJSKP2T3ZGPRFRSNP/bundle.json","state":"https://pith.science/pith/I5GT5NTG7GJSKP2T3ZGPRFRSNP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I5GT5NTG7GJSKP2T3ZGPRFRSNP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:I5GT5NTG7GJSKP2T3ZGPRFRSNP","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":"86787893a39df60160d31fe32c6ae5eae1404c3725ef0ad1e2cebbb3411a1d01","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-16T10:03:26Z","title_canon_sha256":"6d34117a15197e7356328afd365841d29aa42c45a9b0775a5058214046e1293d"},"schema_version":"1.0","source":{"id":"2311.09732","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.09732","created_at":"2026-07-05T07:13:32Z"},{"alias_kind":"arxiv_version","alias_value":"2311.09732v1","created_at":"2026-07-05T07:13:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09732","created_at":"2026-07-05T07:13:32Z"},{"alias_kind":"pith_short_12","alias_value":"I5GT5NTG7GJS","created_at":"2026-07-05T07:13:32Z"},{"alias_kind":"pith_short_16","alias_value":"I5GT5NTG7GJSKP2T","created_at":"2026-07-05T07:13:32Z"},{"alias_kind":"pith_short_8","alias_value":"I5GT5NTG","created_at":"2026-07-05T07:13:32Z"}],"graph_snapshots":[{"event_id":"sha256:cd1b0e3df3bc96895cc741cc00ad0143721143d70b6a73f6f5ecf7ec5f8c842d","target":"graph","created_at":"2026-07-05T07:13:32Z","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/2311.09732/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained language models (PLMs) have established the new paradigm in the field of NLP. For more powerful PLMs, one of the most popular and successful way is to continuously scale up sizes of the models and the pre-training corpora. These large corpora are generally obtained by converging smaller ones from multiple sources, they are thus growing increasingly diverse. However, the side-effects of these colossal converged corpora remain understudied. In this paper, we identify the disadvantage of heterogeneous corpora from multiple sources for pre-training PLMs. Towards coordinated pre-trainin","authors_text":"Dakuan Lu, Hengkui Wu, Jiaqing Liang, Ken Chen, ruiji zhang, Xintao Wang, Yanghua Xiao, Yingsi Xin, Yipei Xu, Yipeng Geng","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-16T10:03:26Z","title":"Source Prompt: Coordinated Pre-training of Language Models on Diverse Corpora from Multiple Sources"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09732","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":"sha256:0e5759e3f61acc13979c838fd41ab1e62f884279bebdf69f4468066206284b47","target":"record","created_at":"2026-07-05T07:13:32Z","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":"86787893a39df60160d31fe32c6ae5eae1404c3725ef0ad1e2cebbb3411a1d01","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-16T10:03:26Z","title_canon_sha256":"6d34117a15197e7356328afd365841d29aa42c45a9b0775a5058214046e1293d"},"schema_version":"1.0","source":{"id":"2311.09732","kind":"arxiv","version":1}},"canonical_sha256":"474d3eb666f993253f53de4cf896326bf6a197939f21802ab33ccc9fc024044d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"474d3eb666f993253f53de4cf896326bf6a197939f21802ab33ccc9fc024044d","first_computed_at":"2026-07-05T07:13:32.182216Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:13:32.182216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MCrZBjrHmasNin+2myXbKIST5h2mbSebLoXwinomZE7JJnKNH81MWwKaVa0/E24mTJg5J61NbDQheSPj3dkaCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:13:32.182774Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.09732","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e5759e3f61acc13979c838fd41ab1e62f884279bebdf69f4468066206284b47","sha256:cd1b0e3df3bc96895cc741cc00ad0143721143d70b6a73f6f5ecf7ec5f8c842d"],"state_sha256":"22decc75ebd079b9817552082bcdd729099efe62f7b86bcddce1570ed4017174"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zIK4MvdJAFdUWkn4yV7BSuZSh/tpEuL02uxL2CTDZb2mFff93rOAnI1WuQJjGEzbwshMLfGJ1jZnPDoA5g16Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T17:33:44.808875Z","bundle_sha256":"09d39bc087f76e78360a4a14815b2d933834a7a633f1443725494573612b27cb"}}