{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BS62WIYD43W2U5UCJ5XFVXVVIR","short_pith_number":"pith:BS62WIYD","canonical_record":{"source":{"id":"2509.06184","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-07T19:28:52Z","cross_cats_sorted":[],"title_canon_sha256":"542711450bf6625dd653cbb2e55eaa569dcced6467da704b4e921898023cecc1","abstract_canon_sha256":"983e3a81c6ceeb83ecfd71bd3dee2550b6e7df580468355a5484bf31a7e7df9b"},"schema_version":"1.0"},"canonical_sha256":"0cbdab2303e6edaa76824f6e5adeb5444ff2ef58ab1ef80e9e59e947bfe8f434","source":{"kind":"arxiv","id":"2509.06184","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.06184","created_at":"2026-07-05T12:06:31Z"},{"alias_kind":"arxiv_version","alias_value":"2509.06184v1","created_at":"2026-07-05T12:06:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06184","created_at":"2026-07-05T12:06:31Z"},{"alias_kind":"pith_short_12","alias_value":"BS62WIYD43W2","created_at":"2026-07-05T12:06:31Z"},{"alias_kind":"pith_short_16","alias_value":"BS62WIYD43W2U5UC","created_at":"2026-07-05T12:06:31Z"},{"alias_kind":"pith_short_8","alias_value":"BS62WIYD","created_at":"2026-07-05T12:06:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BS62WIYD43W2U5UCJ5XFVXVVIR","target":"record","payload":{"canonical_record":{"source":{"id":"2509.06184","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-07T19:28:52Z","cross_cats_sorted":[],"title_canon_sha256":"542711450bf6625dd653cbb2e55eaa569dcced6467da704b4e921898023cecc1","abstract_canon_sha256":"983e3a81c6ceeb83ecfd71bd3dee2550b6e7df580468355a5484bf31a7e7df9b"},"schema_version":"1.0"},"canonical_sha256":"0cbdab2303e6edaa76824f6e5adeb5444ff2ef58ab1ef80e9e59e947bfe8f434","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:31.248165Z","signature_b64":"Fd0tb3IqJiWeaFwh0FuUHDh2X1v+VYyZBApz79WkRGEjlwZ8LqbvqZVoFeNk3G07SzftIAo+pyYBI7ogRwoYDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0cbdab2303e6edaa76824f6e5adeb5444ff2ef58ab1ef80e9e59e947bfe8f434","last_reissued_at":"2026-07-05T12:06:31.247633Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:31.247633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.06184","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":"2026-07-05T12:06:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9uW5RueXd3GcG4Xct7/JVHrtny3G6d5drqS5Vw4UK3+zmTNYVeQAo1VlaO56wKxRoBSGT21PiN3xLg73rhWQAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:25:37.437165Z"},"content_sha256":"88ec4bee25583e996199e4b8fbd8d6e911c6ff4a9521ede0a54f9e41e1715d02","schema_version":"1.0","event_id":"sha256:88ec4bee25583e996199e4b8fbd8d6e911c6ff4a9521ede0a54f9e41e1715d02"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BS62WIYD43W2U5UCJ5XFVXVVIR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Understanding the Influence of Synthetic Data for Text Embedders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aditi Raghunathan, Jacob Mitchell Springer, Marius Mosbach, Siva Reddy, Vaibhav Adlakha","submitted_at":"2025-09-07T19:28:52Z","abstract_excerpt":"Recent progress in developing general purpose text embedders has been driven by training on ever-growing corpora of synthetic LLM-generated data. Nonetheless, no publicly available synthetic dataset exists, posing a barrier to studying its role for generalization. To address this issue, we first reproduce and publicly release the synthetic data proposed by Wang et al. (Mistral-E5). Our synthetic data is high quality and leads to consistent improvements in performance. Next, we critically examine where exactly synthetic data improves model generalization. Our analysis reveals that benefits from"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06184","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/2509.06184/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":"2026-07-05T12:06:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ts5tT8N1l4XQBVI5rNq9JDHnDCbenzDzORFJBD3zw7a4c4MY9ss5/Ra65PxxD0l4p43mR2KrBwVQfyCWcy/oBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:25:37.437705Z"},"content_sha256":"679e4d936e5970d8c1d9feb5541a1dd3eafcb9985a32b396f9c74c6a798e3529","schema_version":"1.0","event_id":"sha256:679e4d936e5970d8c1d9feb5541a1dd3eafcb9985a32b396f9c74c6a798e3529"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BS62WIYD43W2U5UCJ5XFVXVVIR/bundle.json","state_url":"https://pith.science/pith/BS62WIYD43W2U5UCJ5XFVXVVIR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BS62WIYD43W2U5UCJ5XFVXVVIR/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":"2026-08-06T01:25:37Z","links":{"resolver":"https://pith.science/pith/BS62WIYD43W2U5UCJ5XFVXVVIR","bundle":"https://pith.science/pith/BS62WIYD43W2U5UCJ5XFVXVVIR/bundle.json","state":"https://pith.science/pith/BS62WIYD43W2U5UCJ5XFVXVVIR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BS62WIYD43W2U5UCJ5XFVXVVIR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BS62WIYD43W2U5UCJ5XFVXVVIR","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":"983e3a81c6ceeb83ecfd71bd3dee2550b6e7df580468355a5484bf31a7e7df9b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-07T19:28:52Z","title_canon_sha256":"542711450bf6625dd653cbb2e55eaa569dcced6467da704b4e921898023cecc1"},"schema_version":"1.0","source":{"id":"2509.06184","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.06184","created_at":"2026-07-05T12:06:31Z"},{"alias_kind":"arxiv_version","alias_value":"2509.06184v1","created_at":"2026-07-05T12:06:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06184","created_at":"2026-07-05T12:06:31Z"},{"alias_kind":"pith_short_12","alias_value":"BS62WIYD43W2","created_at":"2026-07-05T12:06:31Z"},{"alias_kind":"pith_short_16","alias_value":"BS62WIYD43W2U5UC","created_at":"2026-07-05T12:06:31Z"},{"alias_kind":"pith_short_8","alias_value":"BS62WIYD","created_at":"2026-07-05T12:06:31Z"}],"graph_snapshots":[{"event_id":"sha256:679e4d936e5970d8c1d9feb5541a1dd3eafcb9985a32b396f9c74c6a798e3529","target":"graph","created_at":"2026-07-05T12:06:31Z","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/2509.06184/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent progress in developing general purpose text embedders has been driven by training on ever-growing corpora of synthetic LLM-generated data. Nonetheless, no publicly available synthetic dataset exists, posing a barrier to studying its role for generalization. To address this issue, we first reproduce and publicly release the synthetic data proposed by Wang et al. (Mistral-E5). Our synthetic data is high quality and leads to consistent improvements in performance. Next, we critically examine where exactly synthetic data improves model generalization. Our analysis reveals that benefits from","authors_text":"Aditi Raghunathan, Jacob Mitchell Springer, Marius Mosbach, Siva Reddy, Vaibhav Adlakha","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-07T19:28:52Z","title":"Understanding the Influence of Synthetic Data for Text Embedders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06184","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":"sha256:88ec4bee25583e996199e4b8fbd8d6e911c6ff4a9521ede0a54f9e41e1715d02","target":"record","created_at":"2026-07-05T12:06:31Z","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":"983e3a81c6ceeb83ecfd71bd3dee2550b6e7df580468355a5484bf31a7e7df9b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-07T19:28:52Z","title_canon_sha256":"542711450bf6625dd653cbb2e55eaa569dcced6467da704b4e921898023cecc1"},"schema_version":"1.0","source":{"id":"2509.06184","kind":"arxiv","version":1}},"canonical_sha256":"0cbdab2303e6edaa76824f6e5adeb5444ff2ef58ab1ef80e9e59e947bfe8f434","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0cbdab2303e6edaa76824f6e5adeb5444ff2ef58ab1ef80e9e59e947bfe8f434","first_computed_at":"2026-07-05T12:06:31.247633Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:06:31.247633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Fd0tb3IqJiWeaFwh0FuUHDh2X1v+VYyZBApz79WkRGEjlwZ8LqbvqZVoFeNk3G07SzftIAo+pyYBI7ogRwoYDA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:06:31.248165Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.06184","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:88ec4bee25583e996199e4b8fbd8d6e911c6ff4a9521ede0a54f9e41e1715d02","sha256:679e4d936e5970d8c1d9feb5541a1dd3eafcb9985a32b396f9c74c6a798e3529"],"state_sha256":"646186dc2af2f11d89adb8d79bbae40fdb54d99b6aabd1996ce73210711f9f21"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7nAHIEfaNNSdAY0o0rHLSWcy7n497Nkm/QusUwjeqdSm6Y+zXg++7HsDyeErFIElkZH7yvdD3wZNP8j2dCAFCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T01:25:37.442974Z","bundle_sha256":"a771c8bc8a6efbfd8463014d9b1d9c459f4a05915e8d6ca74f6d34d96e64c7c0"}}