{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:R47PKM4MSML5MGHAMKMCN3CWRN","short_pith_number":"pith:R47PKM4M","canonical_record":{"source":{"id":"2309.06541","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-12T19:32:45Z","cross_cats_sorted":[],"title_canon_sha256":"1fd188600963f2a6d5a4c215c4809acb9c27b7d04d6d6f1ed0fcb949729a6a95","abstract_canon_sha256":"25c6f959df7a62c6d0b7001b3f068cda1125dbf31b4bac99c2c3ddc649d08ada"},"schema_version":"1.0"},"canonical_sha256":"8f3ef5338c9317d618e0629826ec568b6d39e3e22859cab066d985f6c105cb83","source":{"kind":"arxiv","id":"2309.06541","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.06541","created_at":"2026-07-05T06:50:19Z"},{"alias_kind":"arxiv_version","alias_value":"2309.06541v1","created_at":"2026-07-05T06:50:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.06541","created_at":"2026-07-05T06:50:19Z"},{"alias_kind":"pith_short_12","alias_value":"R47PKM4MSML5","created_at":"2026-07-05T06:50:19Z"},{"alias_kind":"pith_short_16","alias_value":"R47PKM4MSML5MGHA","created_at":"2026-07-05T06:50:19Z"},{"alias_kind":"pith_short_8","alias_value":"R47PKM4M","created_at":"2026-07-05T06:50:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:R47PKM4MSML5MGHAMKMCN3CWRN","target":"record","payload":{"canonical_record":{"source":{"id":"2309.06541","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-12T19:32:45Z","cross_cats_sorted":[],"title_canon_sha256":"1fd188600963f2a6d5a4c215c4809acb9c27b7d04d6d6f1ed0fcb949729a6a95","abstract_canon_sha256":"25c6f959df7a62c6d0b7001b3f068cda1125dbf31b4bac99c2c3ddc649d08ada"},"schema_version":"1.0"},"canonical_sha256":"8f3ef5338c9317d618e0629826ec568b6d39e3e22859cab066d985f6c105cb83","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:50:19.239992Z","signature_b64":"x1nUOvBjPoRyeohhCJMCVvuydPkWQyNqP7kdS/UnSbJerlMYq0ABfQXweBds12A64GjWGKASBFCkh7QcIo9SCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f3ef5338c9317d618e0629826ec568b6d39e3e22859cab066d985f6c105cb83","last_reissued_at":"2026-07-05T06:50:19.239497Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:50:19.239497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.06541","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":"2026-07-05T06:50:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+zE0Z9I/9lP5lwHbOpOzwpOmSNuPfj6znNjjgiRmn862KZz1v0u14R8LEgGuivNxXWiWHs3YQnlFo7ClP0ZQAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T17:03:32.022658Z"},"content_sha256":"115c20aae4139c082c76cf5a09a839ef38ccdbecc581a13d841448f56aea259e","schema_version":"1.0","event_id":"sha256:115c20aae4139c082c76cf5a09a839ef38ccdbecc581a13d841448f56aea259e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:R47PKM4MSML5MGHAMKMCN3CWRN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Text Encoders Lack Knowledge: Leveraging Generative LLMs for Domain-Specific Semantic Textual Similarity","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Joseph Gatto, Omar Sharif, Parker Seegmiller, Philip Bohlman, Sarah Masud Preum","submitted_at":"2023-09-12T19:32:45Z","abstract_excerpt":"Amidst the sharp rise in the evaluation of large language models (LLMs) on various tasks, we find that semantic textual similarity (STS) has been under-explored. In this study, we show that STS can be cast as a text generation problem while maintaining strong performance on multiple STS benchmarks. Additionally, we show generative LLMs significantly outperform existing encoder-based STS models when characterizing the semantic similarity between two texts with complex semantic relationships dependent on world knowledge. We validate this claim by evaluating both generative LLMs and existing enco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.06541","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/2309.06541/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":"2026-07-05T06:50:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"viPjVjgmquD20ftdl9sUBiRI1CsalJLKCnAL1OFpsxgBWjNtY1Y/z34I3mbwTJllCr0ClufzcFHQJ7zhE5T1Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T17:03:32.023629Z"},"content_sha256":"87efc94588504c9952c17e70125b0cacec05e4a8df7000c9109be00c3d9efeaa","schema_version":"1.0","event_id":"sha256:87efc94588504c9952c17e70125b0cacec05e4a8df7000c9109be00c3d9efeaa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R47PKM4MSML5MGHAMKMCN3CWRN/bundle.json","state_url":"https://pith.science/pith/R47PKM4MSML5MGHAMKMCN3CWRN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R47PKM4MSML5MGHAMKMCN3CWRN/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":"2026-08-15T17:03:32Z","links":{"resolver":"https://pith.science/pith/R47PKM4MSML5MGHAMKMCN3CWRN","bundle":"https://pith.science/pith/R47PKM4MSML5MGHAMKMCN3CWRN/bundle.json","state":"https://pith.science/pith/R47PKM4MSML5MGHAMKMCN3CWRN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R47PKM4MSML5MGHAMKMCN3CWRN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:R47PKM4MSML5MGHAMKMCN3CWRN","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":"25c6f959df7a62c6d0b7001b3f068cda1125dbf31b4bac99c2c3ddc649d08ada","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-12T19:32:45Z","title_canon_sha256":"1fd188600963f2a6d5a4c215c4809acb9c27b7d04d6d6f1ed0fcb949729a6a95"},"schema_version":"1.0","source":{"id":"2309.06541","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.06541","created_at":"2026-07-05T06:50:19Z"},{"alias_kind":"arxiv_version","alias_value":"2309.06541v1","created_at":"2026-07-05T06:50:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.06541","created_at":"2026-07-05T06:50:19Z"},{"alias_kind":"pith_short_12","alias_value":"R47PKM4MSML5","created_at":"2026-07-05T06:50:19Z"},{"alias_kind":"pith_short_16","alias_value":"R47PKM4MSML5MGHA","created_at":"2026-07-05T06:50:19Z"},{"alias_kind":"pith_short_8","alias_value":"R47PKM4M","created_at":"2026-07-05T06:50:19Z"}],"graph_snapshots":[{"event_id":"sha256:87efc94588504c9952c17e70125b0cacec05e4a8df7000c9109be00c3d9efeaa","target":"graph","created_at":"2026-07-05T06:50:19Z","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/2309.06541/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Amidst the sharp rise in the evaluation of large language models (LLMs) on various tasks, we find that semantic textual similarity (STS) has been under-explored. In this study, we show that STS can be cast as a text generation problem while maintaining strong performance on multiple STS benchmarks. Additionally, we show generative LLMs significantly outperform existing encoder-based STS models when characterizing the semantic similarity between two texts with complex semantic relationships dependent on world knowledge. We validate this claim by evaluating both generative LLMs and existing enco","authors_text":"Joseph Gatto, Omar Sharif, Parker Seegmiller, Philip Bohlman, Sarah Masud Preum","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-12T19:32:45Z","title":"Text Encoders Lack Knowledge: Leveraging Generative LLMs for Domain-Specific Semantic Textual Similarity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.06541","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":"sha256:115c20aae4139c082c76cf5a09a839ef38ccdbecc581a13d841448f56aea259e","target":"record","created_at":"2026-07-05T06:50:19Z","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":"25c6f959df7a62c6d0b7001b3f068cda1125dbf31b4bac99c2c3ddc649d08ada","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-12T19:32:45Z","title_canon_sha256":"1fd188600963f2a6d5a4c215c4809acb9c27b7d04d6d6f1ed0fcb949729a6a95"},"schema_version":"1.0","source":{"id":"2309.06541","kind":"arxiv","version":1}},"canonical_sha256":"8f3ef5338c9317d618e0629826ec568b6d39e3e22859cab066d985f6c105cb83","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f3ef5338c9317d618e0629826ec568b6d39e3e22859cab066d985f6c105cb83","first_computed_at":"2026-07-05T06:50:19.239497Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:50:19.239497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x1nUOvBjPoRyeohhCJMCVvuydPkWQyNqP7kdS/UnSbJerlMYq0ABfQXweBds12A64GjWGKASBFCkh7QcIo9SCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:50:19.239992Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.06541","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:115c20aae4139c082c76cf5a09a839ef38ccdbecc581a13d841448f56aea259e","sha256:87efc94588504c9952c17e70125b0cacec05e4a8df7000c9109be00c3d9efeaa"],"state_sha256":"04d9a18c54062acb5895ddef348383ec8a643bd9de612c8df2ee28a408f29433"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JDVpe4fGbmIxaX6hlgc0nynMIwlF7oPzWYptzH7grKjoFNk26J2rodfU4q4U4ImzbZKql0uy8nxZOKhQPYBWCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T17:03:32.049961Z","bundle_sha256":"8ad6ad6ec6a9698fc736083ae0302390067167806bc71998f55110090a016b94"}}