{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JTLOVPWAYZQSGAUDX5JIDUVXAW","short_pith_number":"pith:JTLOVPWA","canonical_record":{"source":{"id":"2406.01607","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-05-27T09:52:54Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"729ba752e09e4c3a1f8278f63bb7d8344244568e5e53112787284b9184ba780f","abstract_canon_sha256":"155c0fb0b3ed7aff7285ab6f7170d627b9e8a976e644db8f738ff88e44096a93"},"schema_version":"1.0"},"canonical_sha256":"4cd6eabec0c661230283bf5281d2b705b64376be83106f8fc7e223f3aca205b1","source":{"kind":"arxiv","id":"2406.01607","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.01607","created_at":"2026-07-05T08:34:20Z"},{"alias_kind":"arxiv_version","alias_value":"2406.01607v2","created_at":"2026-07-05T08:34:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01607","created_at":"2026-07-05T08:34:20Z"},{"alias_kind":"pith_short_12","alias_value":"JTLOVPWAYZQS","created_at":"2026-07-05T08:34:20Z"},{"alias_kind":"pith_short_16","alias_value":"JTLOVPWAYZQSGAUD","created_at":"2026-07-05T08:34:20Z"},{"alias_kind":"pith_short_8","alias_value":"JTLOVPWA","created_at":"2026-07-05T08:34:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JTLOVPWAYZQSGAUDX5JIDUVXAW","target":"record","payload":{"canonical_record":{"source":{"id":"2406.01607","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-05-27T09:52:54Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"729ba752e09e4c3a1f8278f63bb7d8344244568e5e53112787284b9184ba780f","abstract_canon_sha256":"155c0fb0b3ed7aff7285ab6f7170d627b9e8a976e644db8f738ff88e44096a93"},"schema_version":"1.0"},"canonical_sha256":"4cd6eabec0c661230283bf5281d2b705b64376be83106f8fc7e223f3aca205b1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:20.059004Z","signature_b64":"r22Wz0vsJuOXtB6RSqW2uQnpSJO3hh+VERB7PI4m0UqNOLtAIOUyRApJEMfDLVofmT1d5UBfMTuZSn5/Wj7NCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4cd6eabec0c661230283bf5281d2b705b64376be83106f8fc7e223f3aca205b1","last_reissued_at":"2026-07-05T08:34:20.058556Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:20.058556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.01607","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":"2026-07-05T08:34:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xd/KYIvXEP/v8EYzUhrIw9La3Bs2KotQlfyfUBz7vui6Ib+fhCfUIY/oqTNeq7Lii5bDq+ykRZuWzDjqpYkrCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:16:04.821954Z"},"content_sha256":"3ae9c5ce6822ac7c7d3626e97e07da7aa5d1643a9cf1ad683f3106ed6cb86de2","schema_version":"1.0","event_id":"sha256:3ae9c5ce6822ac7c7d3626e97e07da7aa5d1643a9cf1ad683f3106ed6cb86de2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JTLOVPWAYZQSGAUDX5JIDUVXAW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Recent advances in text embedding: A Comprehensive Review of Top-Performing Methods on the MTEB Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Hongliu Cao","submitted_at":"2024-05-27T09:52:54Z","abstract_excerpt":"Text embedding methods have become increasingly popular in both industrial and academic fields due to their critical role in a variety of natural language processing tasks. The significance of universal text embeddings has been further highlighted with the rise of Large Language Models (LLMs) applications such as Retrieval-Augmented Systems (RAGs). While previous models have attempted to be general-purpose, they often struggle to generalize across tasks and domains. However, recent advancements in training data quantity, quality and diversity; synthetic data generation from LLMs as well as usi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01607","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/2406.01607/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":"2026-07-05T08:34:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/PqKz0QjVSB3sd6gNSZ8rmMsq2C7y65tQp9xPCIF/N3l7373KWqTP1KqpC1x7BKW9nzdDyW/XE3IF2wxpmPjDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:16:04.822814Z"},"content_sha256":"99c7df5b8a307dc5ec1407a361feb71ebfab03bac96c89755c6a8caa854e039d","schema_version":"1.0","event_id":"sha256:99c7df5b8a307dc5ec1407a361feb71ebfab03bac96c89755c6a8caa854e039d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JTLOVPWAYZQSGAUDX5JIDUVXAW/bundle.json","state_url":"https://pith.science/pith/JTLOVPWAYZQSGAUDX5JIDUVXAW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JTLOVPWAYZQSGAUDX5JIDUVXAW/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":"2026-08-08T12:16:04Z","links":{"resolver":"https://pith.science/pith/JTLOVPWAYZQSGAUDX5JIDUVXAW","bundle":"https://pith.science/pith/JTLOVPWAYZQSGAUDX5JIDUVXAW/bundle.json","state":"https://pith.science/pith/JTLOVPWAYZQSGAUDX5JIDUVXAW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JTLOVPWAYZQSGAUDX5JIDUVXAW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JTLOVPWAYZQSGAUDX5JIDUVXAW","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":"155c0fb0b3ed7aff7285ab6f7170d627b9e8a976e644db8f738ff88e44096a93","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-05-27T09:52:54Z","title_canon_sha256":"729ba752e09e4c3a1f8278f63bb7d8344244568e5e53112787284b9184ba780f"},"schema_version":"1.0","source":{"id":"2406.01607","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.01607","created_at":"2026-07-05T08:34:20Z"},{"alias_kind":"arxiv_version","alias_value":"2406.01607v2","created_at":"2026-07-05T08:34:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01607","created_at":"2026-07-05T08:34:20Z"},{"alias_kind":"pith_short_12","alias_value":"JTLOVPWAYZQS","created_at":"2026-07-05T08:34:20Z"},{"alias_kind":"pith_short_16","alias_value":"JTLOVPWAYZQSGAUD","created_at":"2026-07-05T08:34:20Z"},{"alias_kind":"pith_short_8","alias_value":"JTLOVPWA","created_at":"2026-07-05T08:34:20Z"}],"graph_snapshots":[{"event_id":"sha256:99c7df5b8a307dc5ec1407a361feb71ebfab03bac96c89755c6a8caa854e039d","target":"graph","created_at":"2026-07-05T08:34:20Z","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/2406.01607/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text embedding methods have become increasingly popular in both industrial and academic fields due to their critical role in a variety of natural language processing tasks. The significance of universal text embeddings has been further highlighted with the rise of Large Language Models (LLMs) applications such as Retrieval-Augmented Systems (RAGs). While previous models have attempted to be general-purpose, they often struggle to generalize across tasks and domains. However, recent advancements in training data quantity, quality and diversity; synthetic data generation from LLMs as well as usi","authors_text":"Hongliu Cao","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-05-27T09:52:54Z","title":"Recent advances in text embedding: A Comprehensive Review of Top-Performing Methods on the MTEB Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01607","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":"sha256:3ae9c5ce6822ac7c7d3626e97e07da7aa5d1643a9cf1ad683f3106ed6cb86de2","target":"record","created_at":"2026-07-05T08:34:20Z","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":"155c0fb0b3ed7aff7285ab6f7170d627b9e8a976e644db8f738ff88e44096a93","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-05-27T09:52:54Z","title_canon_sha256":"729ba752e09e4c3a1f8278f63bb7d8344244568e5e53112787284b9184ba780f"},"schema_version":"1.0","source":{"id":"2406.01607","kind":"arxiv","version":2}},"canonical_sha256":"4cd6eabec0c661230283bf5281d2b705b64376be83106f8fc7e223f3aca205b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4cd6eabec0c661230283bf5281d2b705b64376be83106f8fc7e223f3aca205b1","first_computed_at":"2026-07-05T08:34:20.058556Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:34:20.058556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r22Wz0vsJuOXtB6RSqW2uQnpSJO3hh+VERB7PI4m0UqNOLtAIOUyRApJEMfDLVofmT1d5UBfMTuZSn5/Wj7NCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:34:20.059004Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.01607","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ae9c5ce6822ac7c7d3626e97e07da7aa5d1643a9cf1ad683f3106ed6cb86de2","sha256:99c7df5b8a307dc5ec1407a361feb71ebfab03bac96c89755c6a8caa854e039d"],"state_sha256":"12c6a731f1cb6eff33ddb14d334afcaa67c6c90e6725d5a9e122ea1b8ff93632"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QF8WZa7qFfjTA5aknuKADmn7F+w3UKvFXSiJds+c5CtKam0VJYH9oU/JTz6hwJGhqpZDEkOqAmLN+6kXoIQ9Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:16:04.829074Z","bundle_sha256":"2a5641a0b6da80cc58372faca562a26becc8ca1493b06a4edfa9f9c0c1160098"}}