{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ZLJIVJZIQT5UDBUUIXMMCETSWV","short_pith_number":"pith:ZLJIVJZI","canonical_record":{"source":{"id":"2608.12875","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-13T06:39:45Z","cross_cats_sorted":[],"title_canon_sha256":"a3f8dfc634e354eed7cf42ad44d8c7f95266d87ddeae97351e6322d048f40881","abstract_canon_sha256":"fdc1ef5aabb8c6a9f58958eea4f5ef398d97b2a9c88c607756c5e67e2bbfea76"},"schema_version":"1.0"},"canonical_sha256":"cad28aa72884fb41869445d8c11272b57c1522383e33193fbbd6e5efe650db3c","source":{"kind":"arxiv","id":"2608.12875","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.12875","created_at":"2026-08-14T00:49:31Z"},{"alias_kind":"arxiv_version","alias_value":"2608.12875v1","created_at":"2026-08-14T00:49:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.12875","created_at":"2026-08-14T00:49:31Z"},{"alias_kind":"pith_short_12","alias_value":"ZLJIVJZIQT5U","created_at":"2026-08-14T00:49:31Z"},{"alias_kind":"pith_short_16","alias_value":"ZLJIVJZIQT5UDBUU","created_at":"2026-08-14T00:49:31Z"},{"alias_kind":"pith_short_8","alias_value":"ZLJIVJZI","created_at":"2026-08-14T00:49:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ZLJIVJZIQT5UDBUUIXMMCETSWV","target":"record","payload":{"canonical_record":{"source":{"id":"2608.12875","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-13T06:39:45Z","cross_cats_sorted":[],"title_canon_sha256":"a3f8dfc634e354eed7cf42ad44d8c7f95266d87ddeae97351e6322d048f40881","abstract_canon_sha256":"fdc1ef5aabb8c6a9f58958eea4f5ef398d97b2a9c88c607756c5e67e2bbfea76"},"schema_version":"1.0"},"canonical_sha256":"cad28aa72884fb41869445d8c11272b57c1522383e33193fbbd6e5efe650db3c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-14T00:49:31.065677Z","signature_b64":"GNjxplM3Uj+wAjYFEzZ0pRwd4qoH/pD2YoaJZ4A+3Lc7oHkha0pXhNUlamZxCxKX/1Arf9qN4Iegj9ojsS8HDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cad28aa72884fb41869445d8c11272b57c1522383e33193fbbd6e5efe650db3c","last_reissued_at":"2026-08-14T00:49:31.053348Z","signature_status":"signed_v1","first_computed_at":"2026-08-14T00:49:31.053348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.12875","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":"2026-08-14T00:49:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MIcd64PbZL8++LYEN1KDoiiGDqld0k1BmPvXDRN9LOK3Ag6UcPEvBUn5rppDzbeQOPw76rM+/xJVLtnaD1uuDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T18:30:34.983382Z"},"content_sha256":"e1ff59a7ba485d28aa5436f3608ffe9ed7b141bb967ac1eca114b875cb386617","schema_version":"1.0","event_id":"sha256:e1ff59a7ba485d28aa5436f3608ffe9ed7b141bb967ac1eca114b875cb386617"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ZLJIVJZIQT5UDBUUIXMMCETSWV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Embedder's Dilemma: LLMs Are Better, but at What Cost?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adnan El Assadi, Jinhyuk Lee, Niklas Muennighoff","submitted_at":"2026-08-13T06:39:45Z","abstract_excerpt":"Should you replace your text-embedding pipeline with a large language model? We answer this with a controlled, cost-aware comparison of ten LLMs across six families and 26 embedding models (118M to 14B parameters) on 37 tasks spanning classification, semantic textual similarity (STS), clustering, pair classification, and retrieval. In aggregate the two paradigms are effectively tied: the best LLM (Gemini 3.1 Pro, 77.6) and the best embedding model (77.2) differ by 0.4 points. Their strengths differ by task: LLMs lead on reasoning-heavy retrieval, embedding models lead on classification, and th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12875","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/2608.12875/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":"2026-08-14T00:49:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AdS59VMP4n8OtOG2Byz4xuQ1JgGo/dUwS4qxg11CEaowjptxndSBvepr7mPM6oFD06pzkraNCEGwdcaKjFuMAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T18:30:34.984283Z"},"content_sha256":"3b6e773ccb7e0e95b33c25ca423e3670a51251d98f25b8a47ca1299f4c80801b","schema_version":"1.0","event_id":"sha256:3b6e773ccb7e0e95b33c25ca423e3670a51251d98f25b8a47ca1299f4c80801b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZLJIVJZIQT5UDBUUIXMMCETSWV/bundle.json","state_url":"https://pith.science/pith/ZLJIVJZIQT5UDBUUIXMMCETSWV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZLJIVJZIQT5UDBUUIXMMCETSWV/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":"2026-08-17T18:30:34Z","links":{"resolver":"https://pith.science/pith/ZLJIVJZIQT5UDBUUIXMMCETSWV","bundle":"https://pith.science/pith/ZLJIVJZIQT5UDBUUIXMMCETSWV/bundle.json","state":"https://pith.science/pith/ZLJIVJZIQT5UDBUUIXMMCETSWV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZLJIVJZIQT5UDBUUIXMMCETSWV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZLJIVJZIQT5UDBUUIXMMCETSWV","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":"fdc1ef5aabb8c6a9f58958eea4f5ef398d97b2a9c88c607756c5e67e2bbfea76","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-13T06:39:45Z","title_canon_sha256":"a3f8dfc634e354eed7cf42ad44d8c7f95266d87ddeae97351e6322d048f40881"},"schema_version":"1.0","source":{"id":"2608.12875","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.12875","created_at":"2026-08-14T00:49:31Z"},{"alias_kind":"arxiv_version","alias_value":"2608.12875v1","created_at":"2026-08-14T00:49:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.12875","created_at":"2026-08-14T00:49:31Z"},{"alias_kind":"pith_short_12","alias_value":"ZLJIVJZIQT5U","created_at":"2026-08-14T00:49:31Z"},{"alias_kind":"pith_short_16","alias_value":"ZLJIVJZIQT5UDBUU","created_at":"2026-08-14T00:49:31Z"},{"alias_kind":"pith_short_8","alias_value":"ZLJIVJZI","created_at":"2026-08-14T00:49:31Z"}],"graph_snapshots":[{"event_id":"sha256:3b6e773ccb7e0e95b33c25ca423e3670a51251d98f25b8a47ca1299f4c80801b","target":"graph","created_at":"2026-08-14T00:49:31Z","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/2608.12875/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Should you replace your text-embedding pipeline with a large language model? We answer this with a controlled, cost-aware comparison of ten LLMs across six families and 26 embedding models (118M to 14B parameters) on 37 tasks spanning classification, semantic textual similarity (STS), clustering, pair classification, and retrieval. In aggregate the two paradigms are effectively tied: the best LLM (Gemini 3.1 Pro, 77.6) and the best embedding model (77.2) differ by 0.4 points. Their strengths differ by task: LLMs lead on reasoning-heavy retrieval, embedding models lead on classification, and th","authors_text":"Adnan El Assadi, Jinhyuk Lee, Niklas Muennighoff","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-13T06:39:45Z","title":"The Embedder's Dilemma: LLMs Are Better, but at What Cost?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12875","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:e1ff59a7ba485d28aa5436f3608ffe9ed7b141bb967ac1eca114b875cb386617","target":"record","created_at":"2026-08-14T00:49:31Z","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":"fdc1ef5aabb8c6a9f58958eea4f5ef398d97b2a9c88c607756c5e67e2bbfea76","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-13T06:39:45Z","title_canon_sha256":"a3f8dfc634e354eed7cf42ad44d8c7f95266d87ddeae97351e6322d048f40881"},"schema_version":"1.0","source":{"id":"2608.12875","kind":"arxiv","version":1}},"canonical_sha256":"cad28aa72884fb41869445d8c11272b57c1522383e33193fbbd6e5efe650db3c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cad28aa72884fb41869445d8c11272b57c1522383e33193fbbd6e5efe650db3c","first_computed_at":"2026-08-14T00:49:31.053348Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-14T00:49:31.053348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GNjxplM3Uj+wAjYFEzZ0pRwd4qoH/pD2YoaJZ4A+3Lc7oHkha0pXhNUlamZxCxKX/1Arf9qN4Iegj9ojsS8HDQ==","signature_status":"signed_v1","signed_at":"2026-08-14T00:49:31.065677Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.12875","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e1ff59a7ba485d28aa5436f3608ffe9ed7b141bb967ac1eca114b875cb386617","sha256:3b6e773ccb7e0e95b33c25ca423e3670a51251d98f25b8a47ca1299f4c80801b"],"state_sha256":"75ab5128c0b8460bfa2b1db1029ef2ba3c303d56b48f5cd410fe273f094bfe0c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4Pg2gXPwWg3lbw2rSiQfsPxACu6WpenyI21fpqOQwwYBzxrJa8Q6V8/qyAIGcVkrsq15nDYu7A/sDgNzKJLmBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T18:30:34.990368Z","bundle_sha256":"ff69f59f5d4e71189ccc85143c1363aa44b8249ef874744b63016dd46524af9a"}}