{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:DBHOAQEYUAU7L7KCXWHPMLDY3M","short_pith_number":"pith:DBHOAQEY","canonical_record":{"source":{"id":"2501.01028","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-02T03:17:51Z","cross_cats_sorted":[],"title_canon_sha256":"00f89c23d528466a5a821077081df95d830c4d0ed5389e7dc66e1fbf73596af6","abstract_canon_sha256":"6d1fe9ca1aaadd9397c1cda34d650c42b6f6139457221d4dffe9e4719bfa0f5c"},"schema_version":"1.0"},"canonical_sha256":"184ee04098a029f5fd42bd8ef62c78db11ab4a6dca38137287347cc9874dcec3","source":{"kind":"arxiv","id":"2501.01028","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.01028","created_at":"2026-07-05T10:01:18Z"},{"alias_kind":"arxiv_version","alias_value":"2501.01028v4","created_at":"2026-07-05T10:01:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01028","created_at":"2026-07-05T10:01:18Z"},{"alias_kind":"pith_short_12","alias_value":"DBHOAQEYUAU7","created_at":"2026-07-05T10:01:18Z"},{"alias_kind":"pith_short_16","alias_value":"DBHOAQEYUAU7L7KC","created_at":"2026-07-05T10:01:18Z"},{"alias_kind":"pith_short_8","alias_value":"DBHOAQEY","created_at":"2026-07-05T10:01:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:DBHOAQEYUAU7L7KCXWHPMLDY3M","target":"record","payload":{"canonical_record":{"source":{"id":"2501.01028","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-02T03:17:51Z","cross_cats_sorted":[],"title_canon_sha256":"00f89c23d528466a5a821077081df95d830c4d0ed5389e7dc66e1fbf73596af6","abstract_canon_sha256":"6d1fe9ca1aaadd9397c1cda34d650c42b6f6139457221d4dffe9e4719bfa0f5c"},"schema_version":"1.0"},"canonical_sha256":"184ee04098a029f5fd42bd8ef62c78db11ab4a6dca38137287347cc9874dcec3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:18.997964Z","signature_b64":"CrfHc8Co481Mp/45TctQ9ECGgZofH1jUntjOwRmKjMII4xiBd7QV58VfSNQBQ3jT7ISFiQCltpPKh3vWaj5qCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"184ee04098a029f5fd42bd8ef62c78db11ab4a6dca38137287347cc9874dcec3","last_reissued_at":"2026-07-05T10:01:18.997496Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:18.997496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.01028","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:01:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8STC9FeTIkv1MAWf5zpGJSX3bpiV82/ZxQ5YuEn6/Ct9qqo9dRTeNBAqR8lh6T3aHE4MEhuCm03pxLgbpAogDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:49:31.117352Z"},"content_sha256":"a7263c27e740c2638af40f0788e4f13334b46e889bc77921325e5474a8f5f395","schema_version":"1.0","event_id":"sha256:a7263c27e740c2638af40f0788e4f13334b46e889bc77921325e5474a8f5f395"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:DBHOAQEYUAU7L7KCXWHPMLDY3M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baotian Hu, Dongfang Li, Haofen Wang, Jun Yu, Min Zhang, Qian Chen, Shaolin Ye, Xinping Zhao, Xinshuo Hu, Xinyuan Wei, Zetian Sun, Zhenyu Liu, Zifei Shan","submitted_at":"2025-01-02T03:17:51Z","abstract_excerpt":"As retrieval-augmented generation prevails in large language models, embedding models are becoming increasingly crucial. Despite the growing number of general embedding models, prior work often overlooks the critical role of training data quality. In this work, we introduce KaLM-Embedding, a general multilingual embedding model that leverages a large quantity of cleaner, more diverse, and domain-specific training data. Our model has been trained with key techniques proven to enhance performance: (1) persona-based synthetic data to create diversified examples distilled from LLMs, (2) ranking co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01028","kind":"arxiv","version":4},"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/2501.01028/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":"2026-07-05T10:01:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KjimvW8hae4UCMSyKT3l/kogMipvbMMJbtbciUeKXx8Qfo9bvmakESlEPWBqyLJX0arqe856mYwOmuqAoBW0Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:49:31.117919Z"},"content_sha256":"2efc35bee3ddc98c206f7efe52138038200fee30f93879839fe1f567aa3f711d","schema_version":"1.0","event_id":"sha256:2efc35bee3ddc98c206f7efe52138038200fee30f93879839fe1f567aa3f711d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DBHOAQEYUAU7L7KCXWHPMLDY3M/bundle.json","state_url":"https://pith.science/pith/DBHOAQEYUAU7L7KCXWHPMLDY3M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DBHOAQEYUAU7L7KCXWHPMLDY3M/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":"2026-08-05T09:49:31Z","links":{"resolver":"https://pith.science/pith/DBHOAQEYUAU7L7KCXWHPMLDY3M","bundle":"https://pith.science/pith/DBHOAQEYUAU7L7KCXWHPMLDY3M/bundle.json","state":"https://pith.science/pith/DBHOAQEYUAU7L7KCXWHPMLDY3M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DBHOAQEYUAU7L7KCXWHPMLDY3M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DBHOAQEYUAU7L7KCXWHPMLDY3M","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":"6d1fe9ca1aaadd9397c1cda34d650c42b6f6139457221d4dffe9e4719bfa0f5c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-02T03:17:51Z","title_canon_sha256":"00f89c23d528466a5a821077081df95d830c4d0ed5389e7dc66e1fbf73596af6"},"schema_version":"1.0","source":{"id":"2501.01028","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.01028","created_at":"2026-07-05T10:01:18Z"},{"alias_kind":"arxiv_version","alias_value":"2501.01028v4","created_at":"2026-07-05T10:01:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01028","created_at":"2026-07-05T10:01:18Z"},{"alias_kind":"pith_short_12","alias_value":"DBHOAQEYUAU7","created_at":"2026-07-05T10:01:18Z"},{"alias_kind":"pith_short_16","alias_value":"DBHOAQEYUAU7L7KC","created_at":"2026-07-05T10:01:18Z"},{"alias_kind":"pith_short_8","alias_value":"DBHOAQEY","created_at":"2026-07-05T10:01:18Z"}],"graph_snapshots":[{"event_id":"sha256:2efc35bee3ddc98c206f7efe52138038200fee30f93879839fe1f567aa3f711d","target":"graph","created_at":"2026-07-05T10:01:18Z","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/2501.01028/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As retrieval-augmented generation prevails in large language models, embedding models are becoming increasingly crucial. Despite the growing number of general embedding models, prior work often overlooks the critical role of training data quality. In this work, we introduce KaLM-Embedding, a general multilingual embedding model that leverages a large quantity of cleaner, more diverse, and domain-specific training data. Our model has been trained with key techniques proven to enhance performance: (1) persona-based synthetic data to create diversified examples distilled from LLMs, (2) ranking co","authors_text":"Baotian Hu, Dongfang Li, Haofen Wang, Jun Yu, Min Zhang, Qian Chen, Shaolin Ye, Xinping Zhao, Xinshuo Hu, Xinyuan Wei, Zetian Sun, Zhenyu Liu, Zifei Shan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-02T03:17:51Z","title":"KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01028","kind":"arxiv","version":4},"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:a7263c27e740c2638af40f0788e4f13334b46e889bc77921325e5474a8f5f395","target":"record","created_at":"2026-07-05T10:01:18Z","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":"6d1fe9ca1aaadd9397c1cda34d650c42b6f6139457221d4dffe9e4719bfa0f5c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-02T03:17:51Z","title_canon_sha256":"00f89c23d528466a5a821077081df95d830c4d0ed5389e7dc66e1fbf73596af6"},"schema_version":"1.0","source":{"id":"2501.01028","kind":"arxiv","version":4}},"canonical_sha256":"184ee04098a029f5fd42bd8ef62c78db11ab4a6dca38137287347cc9874dcec3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"184ee04098a029f5fd42bd8ef62c78db11ab4a6dca38137287347cc9874dcec3","first_computed_at":"2026-07-05T10:01:18.997496Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:01:18.997496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CrfHc8Co481Mp/45TctQ9ECGgZofH1jUntjOwRmKjMII4xiBd7QV58VfSNQBQ3jT7ISFiQCltpPKh3vWaj5qCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:01:18.997964Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.01028","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7263c27e740c2638af40f0788e4f13334b46e889bc77921325e5474a8f5f395","sha256:2efc35bee3ddc98c206f7efe52138038200fee30f93879839fe1f567aa3f711d"],"state_sha256":"f580482aaf4fdc6a73a6ccf38e7c909133420096e9bc72731fff4e1da58b54c0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W8V+yEK6Nh5rvo1KoHlc1diupu33++cJg/HlgphXh5PyBqO4O4MJw4RNWqlGePw5lnAkO6KlYyyTH0zgojGtDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T09:49:31.122014Z","bundle_sha256":"6db3957bb6e3698b9e64e1b2b69b702e0d28b2a9cfe2dbcab8d9acb5b320e33b"}}