{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NZXYC7PV2L4ORM4I6QHERNODLW","short_pith_number":"pith:NZXYC7PV","canonical_record":{"source":{"id":"2404.05961","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-09T02:51:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"58ac51054147aa345d4982f892f462ed01824e8c352582229ff821306db96557","abstract_canon_sha256":"d8c323ffe0231c2b496675ad8e1b867d34fae9e11d7f616517b07f609bffb9c8"},"schema_version":"1.0"},"canonical_sha256":"6e6f817df5d2f8e8b388f40e48b5c35d910142b7b4367fd427d736d2536b51ea","source":{"kind":"arxiv","id":"2404.05961","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.05961","created_at":"2026-07-05T08:57:55Z"},{"alias_kind":"arxiv_version","alias_value":"2404.05961v2","created_at":"2026-07-05T08:57:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05961","created_at":"2026-07-05T08:57:55Z"},{"alias_kind":"pith_short_12","alias_value":"NZXYC7PV2L4O","created_at":"2026-07-05T08:57:55Z"},{"alias_kind":"pith_short_16","alias_value":"NZXYC7PV2L4ORM4I","created_at":"2026-07-05T08:57:55Z"},{"alias_kind":"pith_short_8","alias_value":"NZXYC7PV","created_at":"2026-07-05T08:57:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NZXYC7PV2L4ORM4I6QHERNODLW","target":"record","payload":{"canonical_record":{"source":{"id":"2404.05961","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-09T02:51:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"58ac51054147aa345d4982f892f462ed01824e8c352582229ff821306db96557","abstract_canon_sha256":"d8c323ffe0231c2b496675ad8e1b867d34fae9e11d7f616517b07f609bffb9c8"},"schema_version":"1.0"},"canonical_sha256":"6e6f817df5d2f8e8b388f40e48b5c35d910142b7b4367fd427d736d2536b51ea","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:55.952939Z","signature_b64":"BaZHOmSnDrxActK3Zg7NUf3aGadFnr68Y97j1dXCsciEnc87j4X8xmoDR77tkJ6Yjw45ewcALNnexr6vssg8Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e6f817df5d2f8e8b388f40e48b5c35d910142b7b4367fd427d736d2536b51ea","last_reissued_at":"2026-07-05T08:57:55.951932Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:55.951932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.05961","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":"2026-07-05T08:57:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P07hcfHkLJmptGVOK/ppbc2g4TEOPDj50s0VcwPdLDdOMq/yoSPwirWeMCmUWXS0LVhlnCORR2nG9GVa7Y8wBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T18:18:07.125822Z"},"content_sha256":"c2cc48c742033bbd607da8c14f879e703fb7008460ca2edc0e651a7915ac2f52","schema_version":"1.0","event_id":"sha256:c2cc48c742033bbd607da8c14f879e703fb7008460ca2edc0e651a7915ac2f52"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NZXYC7PV2L4ORM4I6QHERNODLW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dzmitry Bahdanau, Marius Mosbach, Nicolas Chapados, Parishad BehnamGhader, Siva Reddy, Vaibhav Adlakha","submitted_at":"2024-04-09T02:51:05Z","abstract_excerpt":"Large decoder-only language models (LLMs) are the state-of-the-art models on most of today's NLP tasks and benchmarks. Yet, the community is only slowly adopting these models for text embedding tasks, which require rich contextualized representations. In this work, we introduce LLM2Vec, a simple unsupervised approach that can transform any decoder-only LLM into a strong text encoder. LLM2Vec consists of three simple steps: 1) enabling bidirectional attention, 2) masked next token prediction, and 3) unsupervised contrastive learning. We demonstrate the effectiveness of LLM2Vec by applying it to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05961","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/2404.05961/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":"2026-07-05T08:57:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sCkXfCfT5+CuaLnCe6lE6nTVZYrJcs83ueedrslGqYyJ9B3TGeTsjGAv0q9AH+a1GDCgYvf20kZ93lFvks2tBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T18:18:07.126340Z"},"content_sha256":"bfb260021fd1a66fda8d8f72d626688e39070d48eab64fe9750e97729cab76ff","schema_version":"1.0","event_id":"sha256:bfb260021fd1a66fda8d8f72d626688e39070d48eab64fe9750e97729cab76ff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NZXYC7PV2L4ORM4I6QHERNODLW/bundle.json","state_url":"https://pith.science/pith/NZXYC7PV2L4ORM4I6QHERNODLW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NZXYC7PV2L4ORM4I6QHERNODLW/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":"2026-08-01T18:18:07Z","links":{"resolver":"https://pith.science/pith/NZXYC7PV2L4ORM4I6QHERNODLW","bundle":"https://pith.science/pith/NZXYC7PV2L4ORM4I6QHERNODLW/bundle.json","state":"https://pith.science/pith/NZXYC7PV2L4ORM4I6QHERNODLW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NZXYC7PV2L4ORM4I6QHERNODLW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NZXYC7PV2L4ORM4I6QHERNODLW","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":"d8c323ffe0231c2b496675ad8e1b867d34fae9e11d7f616517b07f609bffb9c8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-09T02:51:05Z","title_canon_sha256":"58ac51054147aa345d4982f892f462ed01824e8c352582229ff821306db96557"},"schema_version":"1.0","source":{"id":"2404.05961","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.05961","created_at":"2026-07-05T08:57:55Z"},{"alias_kind":"arxiv_version","alias_value":"2404.05961v2","created_at":"2026-07-05T08:57:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05961","created_at":"2026-07-05T08:57:55Z"},{"alias_kind":"pith_short_12","alias_value":"NZXYC7PV2L4O","created_at":"2026-07-05T08:57:55Z"},{"alias_kind":"pith_short_16","alias_value":"NZXYC7PV2L4ORM4I","created_at":"2026-07-05T08:57:55Z"},{"alias_kind":"pith_short_8","alias_value":"NZXYC7PV","created_at":"2026-07-05T08:57:55Z"}],"graph_snapshots":[{"event_id":"sha256:bfb260021fd1a66fda8d8f72d626688e39070d48eab64fe9750e97729cab76ff","target":"graph","created_at":"2026-07-05T08:57:55Z","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/2404.05961/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large decoder-only language models (LLMs) are the state-of-the-art models on most of today's NLP tasks and benchmarks. Yet, the community is only slowly adopting these models for text embedding tasks, which require rich contextualized representations. In this work, we introduce LLM2Vec, a simple unsupervised approach that can transform any decoder-only LLM into a strong text encoder. LLM2Vec consists of three simple steps: 1) enabling bidirectional attention, 2) masked next token prediction, and 3) unsupervised contrastive learning. We demonstrate the effectiveness of LLM2Vec by applying it to","authors_text":"Dzmitry Bahdanau, Marius Mosbach, Nicolas Chapados, Parishad BehnamGhader, Siva Reddy, Vaibhav Adlakha","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-09T02:51:05Z","title":"LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05961","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:c2cc48c742033bbd607da8c14f879e703fb7008460ca2edc0e651a7915ac2f52","target":"record","created_at":"2026-07-05T08:57:55Z","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":"d8c323ffe0231c2b496675ad8e1b867d34fae9e11d7f616517b07f609bffb9c8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-09T02:51:05Z","title_canon_sha256":"58ac51054147aa345d4982f892f462ed01824e8c352582229ff821306db96557"},"schema_version":"1.0","source":{"id":"2404.05961","kind":"arxiv","version":2}},"canonical_sha256":"6e6f817df5d2f8e8b388f40e48b5c35d910142b7b4367fd427d736d2536b51ea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6e6f817df5d2f8e8b388f40e48b5c35d910142b7b4367fd427d736d2536b51ea","first_computed_at":"2026-07-05T08:57:55.951932Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:57:55.951932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BaZHOmSnDrxActK3Zg7NUf3aGadFnr68Y97j1dXCsciEnc87j4X8xmoDR77tkJ6Yjw45ewcALNnexr6vssg8Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:57:55.952939Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.05961","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c2cc48c742033bbd607da8c14f879e703fb7008460ca2edc0e651a7915ac2f52","sha256:bfb260021fd1a66fda8d8f72d626688e39070d48eab64fe9750e97729cab76ff"],"state_sha256":"bfa528c97b7f5263da696436c1775c8906f38407f88c5d3033610c88a7d45594"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"126xQ8piuST99sB7Nr08UVzeo+eTMd/oootbvibwyycOapbR5e9QqF5rle/rfYqFoAjUHd1dv9evujYTeMJPDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T18:18:07.131088Z","bundle_sha256":"d896c2e534ea421d4c2133336fceca59f1799b40952149e359762adac8bafdaf"}}