{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DS4C3VBD6CDWWE62CORZIXNO62","short_pith_number":"pith:DS4C3VBD","canonical_record":{"source":{"id":"2402.15343","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-23T14:23:51Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f99d1d0b4c43c352b536da414bad223fc1fe03208b947836bb1a644b5365f6aa","abstract_canon_sha256":"c9de48a978b5d39735b550d6d4f9fae0710152f3b79f00d3ed49cf2b7eecfec1"},"schema_version":"1.0"},"canonical_sha256":"1cb82dd423f0876b13da13a3945daef699e65e4dd575968e2c2ba22a42dad1e9","source":{"kind":"arxiv","id":"2402.15343","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.15343","created_at":"2026-07-05T07:48:39Z"},{"alias_kind":"arxiv_version","alias_value":"2402.15343v1","created_at":"2026-07-05T07:48:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15343","created_at":"2026-07-05T07:48:39Z"},{"alias_kind":"pith_short_12","alias_value":"DS4C3VBD6CDW","created_at":"2026-07-05T07:48:39Z"},{"alias_kind":"pith_short_16","alias_value":"DS4C3VBD6CDWWE62","created_at":"2026-07-05T07:48:39Z"},{"alias_kind":"pith_short_8","alias_value":"DS4C3VBD","created_at":"2026-07-05T07:48:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DS4C3VBD6CDWWE62CORZIXNO62","target":"record","payload":{"canonical_record":{"source":{"id":"2402.15343","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-23T14:23:51Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f99d1d0b4c43c352b536da414bad223fc1fe03208b947836bb1a644b5365f6aa","abstract_canon_sha256":"c9de48a978b5d39735b550d6d4f9fae0710152f3b79f00d3ed49cf2b7eecfec1"},"schema_version":"1.0"},"canonical_sha256":"1cb82dd423f0876b13da13a3945daef699e65e4dd575968e2c2ba22a42dad1e9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:39.394430Z","signature_b64":"anN/TEOTVMnEcAzU+iwwZINzBZIzUmiUWhjc5QrJDCqkoXO4pIpCU5WMXLnpk9r2vj/Rdo+3tLnXRo+SxBWIDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1cb82dd423f0876b13da13a3945daef699e65e4dd575968e2c2ba22a42dad1e9","last_reissued_at":"2026-07-05T07:48:39.393999Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:39.393999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.15343","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":"2026-07-05T07:48:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/P07NVZjubeeIKs4oFv77SNo7qoQOf04mx+sR5uF1WA/VGM6xjUjfZWAIr9Fh/BDWkzoBMaCBrEnBGLpsxsFAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T23:41:38.749184Z"},"content_sha256":"9b3a4fbca3c5914b9b197b2ba7df762d4b1d3e5b07832126e02a6155dba7896e","schema_version":"1.0","event_id":"sha256:9b3a4fbca3c5914b9b197b2ba7df762d4b1d3e5b07832126e02a6155dba7896e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DS4C3VBD6CDWWE62CORZIXNO62","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"NuNER: Entity Recognition Encoder Pre-training via LLM-Annotated Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alexandre Constantin, Benoit Crabb\\'e, Etienne Bernard, Sergei Bogdanov, Timoth\\'ee Bernard","submitted_at":"2024-02-23T14:23:51Z","abstract_excerpt":"Large Language Models (LLMs) have shown impressive abilities in data annotation, opening the way for new approaches to solve classic NLP problems. In this paper, we show how to use LLMs to create NuNER, a compact language representation model specialized in the Named Entity Recognition (NER) task. NuNER can be fine-tuned to solve downstream NER problems in a data-efficient way, outperforming similar-sized foundation models in the few-shot regime and competing with much larger LLMs. We find that the size and entity-type diversity of the pre-training dataset are key to achieving good performance"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15343","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/2402.15343/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":"2026-07-05T07:48:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FLY/iSFnvHhymBkMqV4CkU3GA52e6pTzcM3P4O/GR4x3b1C3CGBwtCwDplqm+Pa2+eioXdPMs6xVr/lg4HCeCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T23:41:38.750139Z"},"content_sha256":"416bcfee8894380e0514bdcd1651d8afae8a688bdfc1d2002dc9f22431055cae","schema_version":"1.0","event_id":"sha256:416bcfee8894380e0514bdcd1651d8afae8a688bdfc1d2002dc9f22431055cae"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DS4C3VBD6CDWWE62CORZIXNO62/bundle.json","state_url":"https://pith.science/pith/DS4C3VBD6CDWWE62CORZIXNO62/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DS4C3VBD6CDWWE62CORZIXNO62/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":"2026-08-09T23:41:38Z","links":{"resolver":"https://pith.science/pith/DS4C3VBD6CDWWE62CORZIXNO62","bundle":"https://pith.science/pith/DS4C3VBD6CDWWE62CORZIXNO62/bundle.json","state":"https://pith.science/pith/DS4C3VBD6CDWWE62CORZIXNO62/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DS4C3VBD6CDWWE62CORZIXNO62/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DS4C3VBD6CDWWE62CORZIXNO62","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":"c9de48a978b5d39735b550d6d4f9fae0710152f3b79f00d3ed49cf2b7eecfec1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-23T14:23:51Z","title_canon_sha256":"f99d1d0b4c43c352b536da414bad223fc1fe03208b947836bb1a644b5365f6aa"},"schema_version":"1.0","source":{"id":"2402.15343","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.15343","created_at":"2026-07-05T07:48:39Z"},{"alias_kind":"arxiv_version","alias_value":"2402.15343v1","created_at":"2026-07-05T07:48:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15343","created_at":"2026-07-05T07:48:39Z"},{"alias_kind":"pith_short_12","alias_value":"DS4C3VBD6CDW","created_at":"2026-07-05T07:48:39Z"},{"alias_kind":"pith_short_16","alias_value":"DS4C3VBD6CDWWE62","created_at":"2026-07-05T07:48:39Z"},{"alias_kind":"pith_short_8","alias_value":"DS4C3VBD","created_at":"2026-07-05T07:48:39Z"}],"graph_snapshots":[{"event_id":"sha256:416bcfee8894380e0514bdcd1651d8afae8a688bdfc1d2002dc9f22431055cae","target":"graph","created_at":"2026-07-05T07:48:39Z","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/2402.15343/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have shown impressive abilities in data annotation, opening the way for new approaches to solve classic NLP problems. In this paper, we show how to use LLMs to create NuNER, a compact language representation model specialized in the Named Entity Recognition (NER) task. NuNER can be fine-tuned to solve downstream NER problems in a data-efficient way, outperforming similar-sized foundation models in the few-shot regime and competing with much larger LLMs. We find that the size and entity-type diversity of the pre-training dataset are key to achieving good performance","authors_text":"Alexandre Constantin, Benoit Crabb\\'e, Etienne Bernard, Sergei Bogdanov, Timoth\\'ee Bernard","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-23T14:23:51Z","title":"NuNER: Entity Recognition Encoder Pre-training via LLM-Annotated Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15343","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":"sha256:9b3a4fbca3c5914b9b197b2ba7df762d4b1d3e5b07832126e02a6155dba7896e","target":"record","created_at":"2026-07-05T07:48:39Z","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":"c9de48a978b5d39735b550d6d4f9fae0710152f3b79f00d3ed49cf2b7eecfec1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-23T14:23:51Z","title_canon_sha256":"f99d1d0b4c43c352b536da414bad223fc1fe03208b947836bb1a644b5365f6aa"},"schema_version":"1.0","source":{"id":"2402.15343","kind":"arxiv","version":1}},"canonical_sha256":"1cb82dd423f0876b13da13a3945daef699e65e4dd575968e2c2ba22a42dad1e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1cb82dd423f0876b13da13a3945daef699e65e4dd575968e2c2ba22a42dad1e9","first_computed_at":"2026-07-05T07:48:39.393999Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:48:39.393999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"anN/TEOTVMnEcAzU+iwwZINzBZIzUmiUWhjc5QrJDCqkoXO4pIpCU5WMXLnpk9r2vj/Rdo+3tLnXRo+SxBWIDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:48:39.394430Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.15343","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9b3a4fbca3c5914b9b197b2ba7df762d4b1d3e5b07832126e02a6155dba7896e","sha256:416bcfee8894380e0514bdcd1651d8afae8a688bdfc1d2002dc9f22431055cae"],"state_sha256":"731f0affbc25411c2773d48f9e22501e307d5b639a609952803631b340d1cd0b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HCQuYcDd5p5yyIwTm0LkmIIvR4yUC8Pr9lKuX85IUQIa7rQmhYvGzW2GRBiscKcD3hxef4lsRbrA6LofZRnBCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T23:41:38.756727Z","bundle_sha256":"b658a591cd1335eb9cafc3e87750356f07e2f7ce043c46259caccd00d22c9a0a"}}