{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FSTWMURWAHTUR3Y5TOLPL2VIUX","short_pith_number":"pith:FSTWMURW","canonical_record":{"source":{"id":"2410.18634","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-24T10:47:30Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"95ea19812ef904283958e8ab451b8be4871f593cf87c09d672ecf6a3601b1bb6","abstract_canon_sha256":"2e98db7ac5c52206999f4df2c3583bb713ce29b194d1acd6f2bedd8a7d17803f"},"schema_version":"1.0"},"canonical_sha256":"2ca766523601e748ef1d9b96f5eaa8a5eaa00e81911f23598a14a87ef4e42e48","source":{"kind":"arxiv","id":"2410.18634","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.18634","created_at":"2026-07-05T09:30:22Z"},{"alias_kind":"arxiv_version","alias_value":"2410.18634v2","created_at":"2026-07-05T09:30:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18634","created_at":"2026-07-05T09:30:22Z"},{"alias_kind":"pith_short_12","alias_value":"FSTWMURWAHTU","created_at":"2026-07-05T09:30:22Z"},{"alias_kind":"pith_short_16","alias_value":"FSTWMURWAHTUR3Y5","created_at":"2026-07-05T09:30:22Z"},{"alias_kind":"pith_short_8","alias_value":"FSTWMURW","created_at":"2026-07-05T09:30:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FSTWMURWAHTUR3Y5TOLPL2VIUX","target":"record","payload":{"canonical_record":{"source":{"id":"2410.18634","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-24T10:47:30Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"95ea19812ef904283958e8ab451b8be4871f593cf87c09d672ecf6a3601b1bb6","abstract_canon_sha256":"2e98db7ac5c52206999f4df2c3583bb713ce29b194d1acd6f2bedd8a7d17803f"},"schema_version":"1.0"},"canonical_sha256":"2ca766523601e748ef1d9b96f5eaa8a5eaa00e81911f23598a14a87ef4e42e48","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:22.857826Z","signature_b64":"Zg+C49zAYUbCxGKkNCR71TfX59YY74DRO1+kP5oJoeBNtdddBimraCp+olFHJl7nI/nvtq3RfdEAXygxFaSDDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ca766523601e748ef1d9b96f5eaa8a5eaa00e81911f23598a14a87ef4e42e48","last_reissued_at":"2026-07-05T09:30:22.857249Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:22.857249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.18634","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":"2026-07-05T09:30:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"crlzh8KeyobhS/zDuAV4S6b25zPZSFLWNs3DmMHJC4LbBHWfaqbDBmqVwgdcMw2Y849NxngIQNQ3caSsTV9FBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:22:51.045442Z"},"content_sha256":"21c4b7b8fc77b4a3d297427702e523235c75071af9a7cf7c0cead1ea128501b6","schema_version":"1.0","event_id":"sha256:21c4b7b8fc77b4a3d297427702e523235c75071af9a7cf7c0cead1ea128501b6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FSTWMURWAHTUR3Y5TOLPL2VIUX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Little Giants: Synthesizing High-Quality Embedding Data at Scale","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Furu Wei, Haonan Chen, Liang Wang, Nan Yang, Yutao Zhu, Zhicheng Dou, Ziliang Zhao","submitted_at":"2024-10-24T10:47:30Z","abstract_excerpt":"Synthetic data generation has become an increasingly popular way of training models without the need for large, manually labeled datasets. For tasks like text embedding, synthetic data offers diverse and scalable training examples, significantly reducing the cost of human annotation. However, most current approaches rely heavily on proprietary models like GPT-4, which are expensive and inefficient for generating large-scale embedding data. In this paper, we introduce SPEED, a framework that aligns open-source small models (8B) to efficiently generate large-scale synthetic embedding data. Throu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18634","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/2410.18634/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":"2026-07-05T09:30:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NQe6DwuuZxMSNGzL8ixnyrFya61m14zZ1mgEqORIp8W6tFp9uCXchxyPzbLGwtFYhgnHQjdGus07TQ2FWrGJDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:22:51.046026Z"},"content_sha256":"cacfcbb738c628cc8373da1442155e9625aba7829fb894b3d816d3950c55d642","schema_version":"1.0","event_id":"sha256:cacfcbb738c628cc8373da1442155e9625aba7829fb894b3d816d3950c55d642"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FSTWMURWAHTUR3Y5TOLPL2VIUX/bundle.json","state_url":"https://pith.science/pith/FSTWMURWAHTUR3Y5TOLPL2VIUX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FSTWMURWAHTUR3Y5TOLPL2VIUX/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":"2026-08-05T22:22:51Z","links":{"resolver":"https://pith.science/pith/FSTWMURWAHTUR3Y5TOLPL2VIUX","bundle":"https://pith.science/pith/FSTWMURWAHTUR3Y5TOLPL2VIUX/bundle.json","state":"https://pith.science/pith/FSTWMURWAHTUR3Y5TOLPL2VIUX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FSTWMURWAHTUR3Y5TOLPL2VIUX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FSTWMURWAHTUR3Y5TOLPL2VIUX","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":"2e98db7ac5c52206999f4df2c3583bb713ce29b194d1acd6f2bedd8a7d17803f","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-24T10:47:30Z","title_canon_sha256":"95ea19812ef904283958e8ab451b8be4871f593cf87c09d672ecf6a3601b1bb6"},"schema_version":"1.0","source":{"id":"2410.18634","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.18634","created_at":"2026-07-05T09:30:22Z"},{"alias_kind":"arxiv_version","alias_value":"2410.18634v2","created_at":"2026-07-05T09:30:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18634","created_at":"2026-07-05T09:30:22Z"},{"alias_kind":"pith_short_12","alias_value":"FSTWMURWAHTU","created_at":"2026-07-05T09:30:22Z"},{"alias_kind":"pith_short_16","alias_value":"FSTWMURWAHTUR3Y5","created_at":"2026-07-05T09:30:22Z"},{"alias_kind":"pith_short_8","alias_value":"FSTWMURW","created_at":"2026-07-05T09:30:22Z"}],"graph_snapshots":[{"event_id":"sha256:cacfcbb738c628cc8373da1442155e9625aba7829fb894b3d816d3950c55d642","target":"graph","created_at":"2026-07-05T09:30:22Z","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/2410.18634/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Synthetic data generation has become an increasingly popular way of training models without the need for large, manually labeled datasets. For tasks like text embedding, synthetic data offers diverse and scalable training examples, significantly reducing the cost of human annotation. However, most current approaches rely heavily on proprietary models like GPT-4, which are expensive and inefficient for generating large-scale embedding data. In this paper, we introduce SPEED, a framework that aligns open-source small models (8B) to efficiently generate large-scale synthetic embedding data. Throu","authors_text":"Furu Wei, Haonan Chen, Liang Wang, Nan Yang, Yutao Zhu, Zhicheng Dou, Ziliang Zhao","cross_cats":["cs.AI","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-24T10:47:30Z","title":"Little Giants: Synthesizing High-Quality Embedding Data at Scale"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18634","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":"sha256:21c4b7b8fc77b4a3d297427702e523235c75071af9a7cf7c0cead1ea128501b6","target":"record","created_at":"2026-07-05T09:30:22Z","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":"2e98db7ac5c52206999f4df2c3583bb713ce29b194d1acd6f2bedd8a7d17803f","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-24T10:47:30Z","title_canon_sha256":"95ea19812ef904283958e8ab451b8be4871f593cf87c09d672ecf6a3601b1bb6"},"schema_version":"1.0","source":{"id":"2410.18634","kind":"arxiv","version":2}},"canonical_sha256":"2ca766523601e748ef1d9b96f5eaa8a5eaa00e81911f23598a14a87ef4e42e48","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2ca766523601e748ef1d9b96f5eaa8a5eaa00e81911f23598a14a87ef4e42e48","first_computed_at":"2026-07-05T09:30:22.857249Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:30:22.857249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zg+C49zAYUbCxGKkNCR71TfX59YY74DRO1+kP5oJoeBNtdddBimraCp+olFHJl7nI/nvtq3RfdEAXygxFaSDDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:30:22.857826Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.18634","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:21c4b7b8fc77b4a3d297427702e523235c75071af9a7cf7c0cead1ea128501b6","sha256:cacfcbb738c628cc8373da1442155e9625aba7829fb894b3d816d3950c55d642"],"state_sha256":"9a2fe00c84e9f0893692c3c8e3986916dbde58288727178314e7e3cb20dfdcde"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OEKleygcrWw4bb/jXDmWc+KusMB4e0VMTsXI0LxjJcAcmtNN7j6HLDgySHWDDRV5oyd2hvKN+wVP5tIeKRMIAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T22:22:51.051824Z","bundle_sha256":"81b25d6ab8ea8b398471fd3c4d79441a0e9e535a58ef81a23d8c65ae14bea331"}}