{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RVEGLZANKI644B5S6KQWWJ4CS2","short_pith_number":"pith:RVEGLZAN","canonical_record":{"source":{"id":"2412.12591","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T06:48:24Z","cross_cats_sorted":[],"title_canon_sha256":"9d135089de9b195ce612160eaa12bd47e4c547c721a890467a47c7d5453b6537","abstract_canon_sha256":"f9fdcc6a65593a3cae9ab9d3bcb4b7f72b9a0409cdcca57b8d80a6ef6f033528"},"schema_version":"1.0"},"canonical_sha256":"8d4865e40d523dce07b2f2a16b278296831b63d83cd1db13309f32fdc1c25136","source":{"kind":"arxiv","id":"2412.12591","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.12591","created_at":"2026-07-05T11:43:08Z"},{"alias_kind":"arxiv_version","alias_value":"2412.12591v2","created_at":"2026-07-05T11:43:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12591","created_at":"2026-07-05T11:43:08Z"},{"alias_kind":"pith_short_12","alias_value":"RVEGLZANKI64","created_at":"2026-07-05T11:43:08Z"},{"alias_kind":"pith_short_16","alias_value":"RVEGLZANKI644B5S","created_at":"2026-07-05T11:43:08Z"},{"alias_kind":"pith_short_8","alias_value":"RVEGLZAN","created_at":"2026-07-05T11:43:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RVEGLZANKI644B5S6KQWWJ4CS2","target":"record","payload":{"canonical_record":{"source":{"id":"2412.12591","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T06:48:24Z","cross_cats_sorted":[],"title_canon_sha256":"9d135089de9b195ce612160eaa12bd47e4c547c721a890467a47c7d5453b6537","abstract_canon_sha256":"f9fdcc6a65593a3cae9ab9d3bcb4b7f72b9a0409cdcca57b8d80a6ef6f033528"},"schema_version":"1.0"},"canonical_sha256":"8d4865e40d523dce07b2f2a16b278296831b63d83cd1db13309f32fdc1c25136","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:08.667590Z","signature_b64":"R5Fzg8WRglOcaFMSarVZHE6YUcEpMGoVdrSI6Q7kIxi+44I7upvO+kidpC7hiH1sv68UtZOWiuQUrFPrRIq4BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d4865e40d523dce07b2f2a16b278296831b63d83cd1db13309f32fdc1c25136","last_reissued_at":"2026-07-05T11:43:08.667134Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:08.667134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.12591","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":"2026-07-05T11:43:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"scLnIfDEq95lDEtoI5cMg5a6BLG/sMBJZ6obG2dz2nfsu/aHVTzwmGNAE8fCjZu968ZiR5jf/J+LFc8KrhhiBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T16:10:38.706635Z"},"content_sha256":"2587ffbbc43c3751ba129b1328dcff9056326c952da7dfde34d6b5cf482b6111","schema_version":"1.0","event_id":"sha256:2587ffbbc43c3751ba129b1328dcff9056326c952da7dfde34d6b5cf482b6111"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RVEGLZANKI644B5S6KQWWJ4CS2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLMs are Also Effective Embedding Models: An In-depth Overview","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chongyang Tao, JunShuo Zhang, Kai Hua, Shen Gao, Shuai Ma, Tao Shen, Wenpeng Hu, Zhengwei Tao, Zhen Li","submitted_at":"2024-12-17T06:48:24Z","abstract_excerpt":"Large language models (LLMs) have revolutionized natural language processing by achieving state-of-the-art performance across various tasks. Recently, their effectiveness as embedding models has gained attention, marking a paradigm shift from traditional encoder-only models like ELMo and BERT to decoder-only, large-scale LLMs such as GPT, LLaMA, and Mistral. This survey provides an in-depth overview of this transition, beginning with foundational techniques before the LLM era, followed by LLM-based embedding models through two main strategies to derive embeddings from LLMs. 1) Direct prompting"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12591","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/2412.12591/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":"2026-07-05T11:43:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RId80b3RJlU9qLGo0hmrAnU79Jto8dRia/HFydV58x1F+l1bKJMfBp1pC6GFUqi9P7hg7eM/CGdnBTQSMN50DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T16:10:38.707655Z"},"content_sha256":"a4c2a63d5a193d2168c535de7e4bc6d0ff1dcd825f1390c5ca2ab836cc82fc0f","schema_version":"1.0","event_id":"sha256:a4c2a63d5a193d2168c535de7e4bc6d0ff1dcd825f1390c5ca2ab836cc82fc0f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RVEGLZANKI644B5S6KQWWJ4CS2/bundle.json","state_url":"https://pith.science/pith/RVEGLZANKI644B5S6KQWWJ4CS2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RVEGLZANKI644B5S6KQWWJ4CS2/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":"2026-08-05T16:10:38Z","links":{"resolver":"https://pith.science/pith/RVEGLZANKI644B5S6KQWWJ4CS2","bundle":"https://pith.science/pith/RVEGLZANKI644B5S6KQWWJ4CS2/bundle.json","state":"https://pith.science/pith/RVEGLZANKI644B5S6KQWWJ4CS2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RVEGLZANKI644B5S6KQWWJ4CS2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RVEGLZANKI644B5S6KQWWJ4CS2","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":"f9fdcc6a65593a3cae9ab9d3bcb4b7f72b9a0409cdcca57b8d80a6ef6f033528","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T06:48:24Z","title_canon_sha256":"9d135089de9b195ce612160eaa12bd47e4c547c721a890467a47c7d5453b6537"},"schema_version":"1.0","source":{"id":"2412.12591","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.12591","created_at":"2026-07-05T11:43:08Z"},{"alias_kind":"arxiv_version","alias_value":"2412.12591v2","created_at":"2026-07-05T11:43:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12591","created_at":"2026-07-05T11:43:08Z"},{"alias_kind":"pith_short_12","alias_value":"RVEGLZANKI64","created_at":"2026-07-05T11:43:08Z"},{"alias_kind":"pith_short_16","alias_value":"RVEGLZANKI644B5S","created_at":"2026-07-05T11:43:08Z"},{"alias_kind":"pith_short_8","alias_value":"RVEGLZAN","created_at":"2026-07-05T11:43:08Z"}],"graph_snapshots":[{"event_id":"sha256:a4c2a63d5a193d2168c535de7e4bc6d0ff1dcd825f1390c5ca2ab836cc82fc0f","target":"graph","created_at":"2026-07-05T11:43:08Z","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/2412.12591/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have revolutionized natural language processing by achieving state-of-the-art performance across various tasks. Recently, their effectiveness as embedding models has gained attention, marking a paradigm shift from traditional encoder-only models like ELMo and BERT to decoder-only, large-scale LLMs such as GPT, LLaMA, and Mistral. This survey provides an in-depth overview of this transition, beginning with foundational techniques before the LLM era, followed by LLM-based embedding models through two main strategies to derive embeddings from LLMs. 1) Direct prompting","authors_text":"Chongyang Tao, JunShuo Zhang, Kai Hua, Shen Gao, Shuai Ma, Tao Shen, Wenpeng Hu, Zhengwei Tao, Zhen Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T06:48:24Z","title":"LLMs are Also Effective Embedding Models: An In-depth Overview"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12591","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":"sha256:2587ffbbc43c3751ba129b1328dcff9056326c952da7dfde34d6b5cf482b6111","target":"record","created_at":"2026-07-05T11:43:08Z","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":"f9fdcc6a65593a3cae9ab9d3bcb4b7f72b9a0409cdcca57b8d80a6ef6f033528","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T06:48:24Z","title_canon_sha256":"9d135089de9b195ce612160eaa12bd47e4c547c721a890467a47c7d5453b6537"},"schema_version":"1.0","source":{"id":"2412.12591","kind":"arxiv","version":2}},"canonical_sha256":"8d4865e40d523dce07b2f2a16b278296831b63d83cd1db13309f32fdc1c25136","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d4865e40d523dce07b2f2a16b278296831b63d83cd1db13309f32fdc1c25136","first_computed_at":"2026-07-05T11:43:08.667134Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:43:08.667134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R5Fzg8WRglOcaFMSarVZHE6YUcEpMGoVdrSI6Q7kIxi+44I7upvO+kidpC7hiH1sv68UtZOWiuQUrFPrRIq4BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:43:08.667590Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.12591","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2587ffbbc43c3751ba129b1328dcff9056326c952da7dfde34d6b5cf482b6111","sha256:a4c2a63d5a193d2168c535de7e4bc6d0ff1dcd825f1390c5ca2ab836cc82fc0f"],"state_sha256":"bcf2b955264d9d6684d4a6b36d4f4a22bf9f9eb811bc123098672c35792d7799"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s1OWO+BG/d3E/iB5P3765taZA1bJq+nNYwUpgAVj/Br+3n7wuXtopHTm4tbCsTQpV/yHQXF1HP9GJmIm6BXDDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T16:10:38.739988Z","bundle_sha256":"95dbd8254b60dacbcd7d5e6b641883454bd6b091c77894e32d0c0b6c2617ab33"}}