{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7WRAHT5R7PQCGCSLZ4VZKPD6QL","short_pith_number":"pith:7WRAHT5R","canonical_record":{"source":{"id":"2409.18511","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-27T07:46:06Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"74c88a557606b7db643f4b17da0f264607933aff11556bc008eb2436793dd354","abstract_canon_sha256":"cd27cd0b3c4e657af0a20b1403fa7e8e111c80cf70a5ebe2cff10f64b4839045"},"schema_version":"1.0"},"canonical_sha256":"fda203cfb1fbe0230a4bcf2b953c7e82dfa8f34be7c24f1f581f35a8a7bea790","source":{"kind":"arxiv","id":"2409.18511","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.18511","created_at":"2026-07-05T10:15:45Z"},{"alias_kind":"arxiv_version","alias_value":"2409.18511v4","created_at":"2026-07-05T10:15:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.18511","created_at":"2026-07-05T10:15:45Z"},{"alias_kind":"pith_short_12","alias_value":"7WRAHT5R7PQC","created_at":"2026-07-05T10:15:45Z"},{"alias_kind":"pith_short_16","alias_value":"7WRAHT5R7PQCGCSL","created_at":"2026-07-05T10:15:45Z"},{"alias_kind":"pith_short_8","alias_value":"7WRAHT5R","created_at":"2026-07-05T10:15:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7WRAHT5R7PQCGCSLZ4VZKPD6QL","target":"record","payload":{"canonical_record":{"source":{"id":"2409.18511","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-27T07:46:06Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"74c88a557606b7db643f4b17da0f264607933aff11556bc008eb2436793dd354","abstract_canon_sha256":"cd27cd0b3c4e657af0a20b1403fa7e8e111c80cf70a5ebe2cff10f64b4839045"},"schema_version":"1.0"},"canonical_sha256":"fda203cfb1fbe0230a4bcf2b953c7e82dfa8f34be7c24f1f581f35a8a7bea790","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:45.635825Z","signature_b64":"nTf6dRQX4xXCZ4T9zXJlSDbTz8SdOL8JWMXeQDK7SQqlNpDvSLqT8J7z9hX/TgIKfw9ehq6PlXVUf28ZciAPCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fda203cfb1fbe0230a4bcf2b953c7e82dfa8f34be7c24f1f581f35a8a7bea790","last_reissued_at":"2026-07-05T10:15:45.635338Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:45.635338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.18511","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":"2026-07-05T10:15:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Iu0X6TDWTARrNXeJaVotIclpQZKBzLXVLqz4wPvwWY2CS2ukJaf9z/9cmWs43NGyqC7nwLQ2Wl4OlLgZ9j+sCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T06:09:54.442854Z"},"content_sha256":"1c25411d8b2184b03f62a2e96c210746c6aba06820cc144e5f318800c5d859b7","schema_version":"1.0","event_id":"sha256:1c25411d8b2184b03f62a2e96c210746c6aba06820cc144e5f318800c5d859b7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7WRAHT5R7PQCGCSLZ4VZKPD6QL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Do We Need Domain-Specific Embedding Models? An Empirical Investigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Yixuan Tang, Yi Yang","submitted_at":"2024-09-27T07:46:06Z","abstract_excerpt":"Embedding models play a crucial role in representing and retrieving information across various NLP applications. Recent advancements in Large Language Models (LLMs) have further enhanced the performance of embedding models, which are trained on massive amounts of text covering almost every domain. These models are often benchmarked on general-purpose datasets like Massive Text Embedding Benchmark (MTEB), where they demonstrate superior performance. However, a critical question arises: Is the development of domain-specific embedding models necessary when general-purpose models are trained on va"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.18511","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/2409.18511/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":"2026-07-05T10:15:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LfJ3iH0R2dgyOJbk9qP2NaQAbAhe/DSim72nN4LxUrq/CGADGHT248ROAsNVsxDEhSlB0javQ2HYlKlffw0pDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T06:09:54.443442Z"},"content_sha256":"7d7f5b6961a537cd30730997f447479d502054144b83a662b90ee5a641c96364","schema_version":"1.0","event_id":"sha256:7d7f5b6961a537cd30730997f447479d502054144b83a662b90ee5a641c96364"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7WRAHT5R7PQCGCSLZ4VZKPD6QL/bundle.json","state_url":"https://pith.science/pith/7WRAHT5R7PQCGCSLZ4VZKPD6QL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7WRAHT5R7PQCGCSLZ4VZKPD6QL/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":"2026-08-08T06:09:54Z","links":{"resolver":"https://pith.science/pith/7WRAHT5R7PQCGCSLZ4VZKPD6QL","bundle":"https://pith.science/pith/7WRAHT5R7PQCGCSLZ4VZKPD6QL/bundle.json","state":"https://pith.science/pith/7WRAHT5R7PQCGCSLZ4VZKPD6QL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7WRAHT5R7PQCGCSLZ4VZKPD6QL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7WRAHT5R7PQCGCSLZ4VZKPD6QL","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":"cd27cd0b3c4e657af0a20b1403fa7e8e111c80cf70a5ebe2cff10f64b4839045","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-27T07:46:06Z","title_canon_sha256":"74c88a557606b7db643f4b17da0f264607933aff11556bc008eb2436793dd354"},"schema_version":"1.0","source":{"id":"2409.18511","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.18511","created_at":"2026-07-05T10:15:45Z"},{"alias_kind":"arxiv_version","alias_value":"2409.18511v4","created_at":"2026-07-05T10:15:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.18511","created_at":"2026-07-05T10:15:45Z"},{"alias_kind":"pith_short_12","alias_value":"7WRAHT5R7PQC","created_at":"2026-07-05T10:15:45Z"},{"alias_kind":"pith_short_16","alias_value":"7WRAHT5R7PQCGCSL","created_at":"2026-07-05T10:15:45Z"},{"alias_kind":"pith_short_8","alias_value":"7WRAHT5R","created_at":"2026-07-05T10:15:45Z"}],"graph_snapshots":[{"event_id":"sha256:7d7f5b6961a537cd30730997f447479d502054144b83a662b90ee5a641c96364","target":"graph","created_at":"2026-07-05T10:15:45Z","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/2409.18511/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Embedding models play a crucial role in representing and retrieving information across various NLP applications. Recent advancements in Large Language Models (LLMs) have further enhanced the performance of embedding models, which are trained on massive amounts of text covering almost every domain. These models are often benchmarked on general-purpose datasets like Massive Text Embedding Benchmark (MTEB), where they demonstrate superior performance. However, a critical question arises: Is the development of domain-specific embedding models necessary when general-purpose models are trained on va","authors_text":"Yixuan Tang, Yi Yang","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-27T07:46:06Z","title":"Do We Need Domain-Specific Embedding Models? An Empirical Investigation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.18511","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":"sha256:1c25411d8b2184b03f62a2e96c210746c6aba06820cc144e5f318800c5d859b7","target":"record","created_at":"2026-07-05T10:15:45Z","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":"cd27cd0b3c4e657af0a20b1403fa7e8e111c80cf70a5ebe2cff10f64b4839045","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-27T07:46:06Z","title_canon_sha256":"74c88a557606b7db643f4b17da0f264607933aff11556bc008eb2436793dd354"},"schema_version":"1.0","source":{"id":"2409.18511","kind":"arxiv","version":4}},"canonical_sha256":"fda203cfb1fbe0230a4bcf2b953c7e82dfa8f34be7c24f1f581f35a8a7bea790","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fda203cfb1fbe0230a4bcf2b953c7e82dfa8f34be7c24f1f581f35a8a7bea790","first_computed_at":"2026-07-05T10:15:45.635338Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:15:45.635338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nTf6dRQX4xXCZ4T9zXJlSDbTz8SdOL8JWMXeQDK7SQqlNpDvSLqT8J7z9hX/TgIKfw9ehq6PlXVUf28ZciAPCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:15:45.635825Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.18511","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c25411d8b2184b03f62a2e96c210746c6aba06820cc144e5f318800c5d859b7","sha256:7d7f5b6961a537cd30730997f447479d502054144b83a662b90ee5a641c96364"],"state_sha256":"473e89a6ed05e73c21e99a6882f8cb79c5a3a2169b84e7b6a3012777a7c59b82"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RImMPVX7cQByVQJPiq1hNgRb75XfMitlo5SAfUKlPM7/ehvTG1V5CC1HbV3u2RkAJURb8lxry8YHCMx+hp0qCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T06:09:54.448116Z","bundle_sha256":"0b62afb65602f01a27d8afe59b0fe3886e3593943d6e6b50d1716a54f80b45a2"}}