{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DREQDZOTRSM7XBJQ5DYFXFCYY7","short_pith_number":"pith:DREQDZOT","canonical_record":{"source":{"id":"2408.15710","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-28T11:18:06Z","cross_cats_sorted":[],"title_canon_sha256":"22520668e9dc00d15ec655bf76d8ac9b91b845b2f77baa01f8a91e2e6d2099df","abstract_canon_sha256":"2ae66844fa05d9a7ac5d854c85bc30f750d01bdec699c10254eb67f96c55271a"},"schema_version":"1.0"},"canonical_sha256":"1c4901e5d38c99fb8530e8f05b9458c7e47be940b7d1c6f42c8c89305b364847","source":{"kind":"arxiv","id":"2408.15710","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.15710","created_at":"2026-07-05T09:00:39Z"},{"alias_kind":"arxiv_version","alias_value":"2408.15710v2","created_at":"2026-07-05T09:00:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15710","created_at":"2026-07-05T09:00:39Z"},{"alias_kind":"pith_short_12","alias_value":"DREQDZOTRSM7","created_at":"2026-07-05T09:00:39Z"},{"alias_kind":"pith_short_16","alias_value":"DREQDZOTRSM7XBJQ","created_at":"2026-07-05T09:00:39Z"},{"alias_kind":"pith_short_8","alias_value":"DREQDZOT","created_at":"2026-07-05T09:00:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DREQDZOTRSM7XBJQ5DYFXFCYY7","target":"record","payload":{"canonical_record":{"source":{"id":"2408.15710","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-28T11:18:06Z","cross_cats_sorted":[],"title_canon_sha256":"22520668e9dc00d15ec655bf76d8ac9b91b845b2f77baa01f8a91e2e6d2099df","abstract_canon_sha256":"2ae66844fa05d9a7ac5d854c85bc30f750d01bdec699c10254eb67f96c55271a"},"schema_version":"1.0"},"canonical_sha256":"1c4901e5d38c99fb8530e8f05b9458c7e47be940b7d1c6f42c8c89305b364847","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:00:39.130679Z","signature_b64":"HFKUrU0YiMK9L9rtwoCm5BVYVv0b6FnB5sMlE6DaEjeH1fV+3dUomsTDo/55LxdZ7p2IwJ1ZQEU2zhRzD5GUCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c4901e5d38c99fb8530e8f05b9458c7e47be940b7d1c6f42c8c89305b364847","last_reissued_at":"2026-07-05T09:00:39.130241Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:00:39.130241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.15710","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":"2026-07-05T09:00:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zyOTbNiGGGYOiK3K0rZy/hDnUjnxv3+5cpRRJlh+5kSdXF3E9Ae3j+ln3/AMeRnAmTT717e6C+yCoP4dA8S2DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T13:56:30.645919Z"},"content_sha256":"38d8670159b93e6ad6546fbe2fe86b25c3663c62046cf236b9c3487d7bdbea21","schema_version":"1.0","event_id":"sha256:38d8670159b93e6ad6546fbe2fe86b25c3663c62046cf236b9c3487d7bdbea21"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DREQDZOTRSM7XBJQ5DYFXFCYY7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Conan-embedding: General Text Embedding with More and Better Negative Samples","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Shiyu Li, Shizhe Chen, Xi Chen, Yang Tang","submitted_at":"2024-08-28T11:18:06Z","abstract_excerpt":"With the growing popularity of RAG, the capabilities of embedding models are gaining increasing attention. Embedding models are primarily trained through contrastive loss learning, with negative examples being a key component. Previous work has proposed various hard negative mining strategies, but these strategies are typically employed as preprocessing steps. In this paper, we propose the conan-embedding model, which maximizes the utilization of more and higher-quality negative examples. Specifically, since the model's ability to handle preprocessed negative examples evolves during training, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15710","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/2408.15710/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":"2026-07-05T09:00:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rHOpms8TN/FUjDnau0bhOFcMMT8xUWp5K3kFHKA7M/KlTUIFWNy3CWABqwzOr3fFm+mYwTbWqV0eSB/7H7QXCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T13:56:30.646861Z"},"content_sha256":"f79d747e42988a9a2da47725e4fa62de274acb1a261da05ae14d7760c82433c1","schema_version":"1.0","event_id":"sha256:f79d747e42988a9a2da47725e4fa62de274acb1a261da05ae14d7760c82433c1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DREQDZOTRSM7XBJQ5DYFXFCYY7/bundle.json","state_url":"https://pith.science/pith/DREQDZOTRSM7XBJQ5DYFXFCYY7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DREQDZOTRSM7XBJQ5DYFXFCYY7/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":"2026-08-06T13:56:30Z","links":{"resolver":"https://pith.science/pith/DREQDZOTRSM7XBJQ5DYFXFCYY7","bundle":"https://pith.science/pith/DREQDZOTRSM7XBJQ5DYFXFCYY7/bundle.json","state":"https://pith.science/pith/DREQDZOTRSM7XBJQ5DYFXFCYY7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DREQDZOTRSM7XBJQ5DYFXFCYY7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DREQDZOTRSM7XBJQ5DYFXFCYY7","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":"2ae66844fa05d9a7ac5d854c85bc30f750d01bdec699c10254eb67f96c55271a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-28T11:18:06Z","title_canon_sha256":"22520668e9dc00d15ec655bf76d8ac9b91b845b2f77baa01f8a91e2e6d2099df"},"schema_version":"1.0","source":{"id":"2408.15710","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.15710","created_at":"2026-07-05T09:00:39Z"},{"alias_kind":"arxiv_version","alias_value":"2408.15710v2","created_at":"2026-07-05T09:00:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15710","created_at":"2026-07-05T09:00:39Z"},{"alias_kind":"pith_short_12","alias_value":"DREQDZOTRSM7","created_at":"2026-07-05T09:00:39Z"},{"alias_kind":"pith_short_16","alias_value":"DREQDZOTRSM7XBJQ","created_at":"2026-07-05T09:00:39Z"},{"alias_kind":"pith_short_8","alias_value":"DREQDZOT","created_at":"2026-07-05T09:00:39Z"}],"graph_snapshots":[{"event_id":"sha256:f79d747e42988a9a2da47725e4fa62de274acb1a261da05ae14d7760c82433c1","target":"graph","created_at":"2026-07-05T09:00:39Z","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/2408.15710/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the growing popularity of RAG, the capabilities of embedding models are gaining increasing attention. Embedding models are primarily trained through contrastive loss learning, with negative examples being a key component. Previous work has proposed various hard negative mining strategies, but these strategies are typically employed as preprocessing steps. In this paper, we propose the conan-embedding model, which maximizes the utilization of more and higher-quality negative examples. Specifically, since the model's ability to handle preprocessed negative examples evolves during training, ","authors_text":"Shiyu Li, Shizhe Chen, Xi Chen, Yang Tang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-28T11:18:06Z","title":"Conan-embedding: General Text Embedding with More and Better Negative Samples"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15710","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":"sha256:38d8670159b93e6ad6546fbe2fe86b25c3663c62046cf236b9c3487d7bdbea21","target":"record","created_at":"2026-07-05T09:00:39Z","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":"2ae66844fa05d9a7ac5d854c85bc30f750d01bdec699c10254eb67f96c55271a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-28T11:18:06Z","title_canon_sha256":"22520668e9dc00d15ec655bf76d8ac9b91b845b2f77baa01f8a91e2e6d2099df"},"schema_version":"1.0","source":{"id":"2408.15710","kind":"arxiv","version":2}},"canonical_sha256":"1c4901e5d38c99fb8530e8f05b9458c7e47be940b7d1c6f42c8c89305b364847","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1c4901e5d38c99fb8530e8f05b9458c7e47be940b7d1c6f42c8c89305b364847","first_computed_at":"2026-07-05T09:00:39.130241Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:00:39.130241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HFKUrU0YiMK9L9rtwoCm5BVYVv0b6FnB5sMlE6DaEjeH1fV+3dUomsTDo/55LxdZ7p2IwJ1ZQEU2zhRzD5GUCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:00:39.130679Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.15710","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:38d8670159b93e6ad6546fbe2fe86b25c3663c62046cf236b9c3487d7bdbea21","sha256:f79d747e42988a9a2da47725e4fa62de274acb1a261da05ae14d7760c82433c1"],"state_sha256":"990111bb283312c616f30595c4301a8f5b4939295e35d8d22ca5452040859163"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mWoNTfsWKU2RHkdhM7igeCT4tVsxu4INrseajo33CSqCbTKU+S+eVa4DZGXf5YAJJ5/V8otivGR9YjGixO02AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T13:56:30.654412Z","bundle_sha256":"47518bf4c565768904f3b7a5079e93fc121a5b27b47a7be33ceb125aa1b1a786"}}