{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4OUMTPJA7Z5B4FJUP365MB3FV4","short_pith_number":"pith:4OUMTPJA","canonical_record":{"source":{"id":"2402.06738","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-09T19:16:27Z","cross_cats_sorted":[],"title_canon_sha256":"dc46d0ea158d7556e32fd9060e71f1159a114799d9fc26aa9744bd461f8c60ca","abstract_canon_sha256":"83e62900ffad2d97d7c8814971ff1d343f12900d569beddee2f0607c2bd410eb"},"schema_version":"1.0"},"canonical_sha256":"e3a8c9bd20fe7a1e15347efdd60765af153d5c8dccd6f2bf1185cee4406ca365","source":{"kind":"arxiv","id":"2402.06738","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.06738","created_at":"2026-07-05T11:07:01Z"},{"alias_kind":"arxiv_version","alias_value":"2402.06738v3","created_at":"2026-07-05T11:07:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.06738","created_at":"2026-07-05T11:07:01Z"},{"alias_kind":"pith_short_12","alias_value":"4OUMTPJA7Z5B","created_at":"2026-07-05T11:07:01Z"},{"alias_kind":"pith_short_16","alias_value":"4OUMTPJA7Z5B4FJU","created_at":"2026-07-05T11:07:01Z"},{"alias_kind":"pith_short_8","alias_value":"4OUMTPJA","created_at":"2026-07-05T11:07:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4OUMTPJA7Z5B4FJUP365MB3FV4","target":"record","payload":{"canonical_record":{"source":{"id":"2402.06738","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-09T19:16:27Z","cross_cats_sorted":[],"title_canon_sha256":"dc46d0ea158d7556e32fd9060e71f1159a114799d9fc26aa9744bd461f8c60ca","abstract_canon_sha256":"83e62900ffad2d97d7c8814971ff1d343f12900d569beddee2f0607c2bd410eb"},"schema_version":"1.0"},"canonical_sha256":"e3a8c9bd20fe7a1e15347efdd60765af153d5c8dccd6f2bf1185cee4406ca365","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:01.567171Z","signature_b64":"8eCQcEIuMrpO0arzHDJVeUeSsLY16+jwcEjizd4sqyNxb7g1OZFbV9Ng+7SxLP5qTxwfA+3UxzdpJJNbQO2QAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3a8c9bd20fe7a1e15347efdd60765af153d5c8dccd6f2bf1185cee4406ca365","last_reissued_at":"2026-07-05T11:07:01.566759Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:01.566759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.06738","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:07:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+3qLB+HOLIysRKpyFXB/a14uJutdkSERXatzm0bJtL+E/A0eMEOKXGH2oy8BpR41pXMXtDsseWpKf6509ZmTCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:36:37.815640Z"},"content_sha256":"6800a354e1dafe0970c7252a66b1fb4de933217c77e296e5d476248c3c169fda","schema_version":"1.0","event_id":"sha256:6800a354e1dafe0970c7252a66b1fb4de933217c77e296e5d476248c3c169fda"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4OUMTPJA7Z5B4FJUP365MB3FV4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EntGPT: Entity Linking with Generative Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amrit Poudel, Balaji Veeramani, Qingkai Zeng, Sanmitra Bhattacharya, Tim Weninger, Yifan Ding","submitted_at":"2024-02-09T19:16:27Z","abstract_excerpt":"Entity Linking in natural language processing seeks to match text entities to their corresponding entries in a dictionary or knowledge base. Traditional approaches rely on contextual models, which can be complex, hard to train, and have limited transferability across different domains. Generative large language models like GPT offer a promising alternative but often underperform with naive prompts. In this study, we introduce EntGPT, employing advanced prompt engineering to enhance EL tasks. Our three-step hard-prompting method (EntGPT-P) significantly boosts the micro-F_1 score by up to 36% o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.06738","kind":"arxiv","version":3},"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/2402.06738/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":"2026-07-05T11:07:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9j2DFf9+R2xBFUPiu0yd0FMK3BnK5gcO9lp8IgkjAOQBMW1kfZBPCO1Qj8QoTxlA+N1vPspNzRxFiATe8DiiCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:36:37.816028Z"},"content_sha256":"12e66114f6dfcaf73c0775c5406bb743c44b19639baa668ce895765912d52551","schema_version":"1.0","event_id":"sha256:12e66114f6dfcaf73c0775c5406bb743c44b19639baa668ce895765912d52551"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4OUMTPJA7Z5B4FJUP365MB3FV4/bundle.json","state_url":"https://pith.science/pith/4OUMTPJA7Z5B4FJUP365MB3FV4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4OUMTPJA7Z5B4FJUP365MB3FV4/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":"2026-07-07T08:36:37Z","links":{"resolver":"https://pith.science/pith/4OUMTPJA7Z5B4FJUP365MB3FV4","bundle":"https://pith.science/pith/4OUMTPJA7Z5B4FJUP365MB3FV4/bundle.json","state":"https://pith.science/pith/4OUMTPJA7Z5B4FJUP365MB3FV4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4OUMTPJA7Z5B4FJUP365MB3FV4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4OUMTPJA7Z5B4FJUP365MB3FV4","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":"83e62900ffad2d97d7c8814971ff1d343f12900d569beddee2f0607c2bd410eb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-09T19:16:27Z","title_canon_sha256":"dc46d0ea158d7556e32fd9060e71f1159a114799d9fc26aa9744bd461f8c60ca"},"schema_version":"1.0","source":{"id":"2402.06738","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.06738","created_at":"2026-07-05T11:07:01Z"},{"alias_kind":"arxiv_version","alias_value":"2402.06738v3","created_at":"2026-07-05T11:07:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.06738","created_at":"2026-07-05T11:07:01Z"},{"alias_kind":"pith_short_12","alias_value":"4OUMTPJA7Z5B","created_at":"2026-07-05T11:07:01Z"},{"alias_kind":"pith_short_16","alias_value":"4OUMTPJA7Z5B4FJU","created_at":"2026-07-05T11:07:01Z"},{"alias_kind":"pith_short_8","alias_value":"4OUMTPJA","created_at":"2026-07-05T11:07:01Z"}],"graph_snapshots":[{"event_id":"sha256:12e66114f6dfcaf73c0775c5406bb743c44b19639baa668ce895765912d52551","target":"graph","created_at":"2026-07-05T11:07:01Z","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/2402.06738/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Entity Linking in natural language processing seeks to match text entities to their corresponding entries in a dictionary or knowledge base. Traditional approaches rely on contextual models, which can be complex, hard to train, and have limited transferability across different domains. Generative large language models like GPT offer a promising alternative but often underperform with naive prompts. In this study, we introduce EntGPT, employing advanced prompt engineering to enhance EL tasks. Our three-step hard-prompting method (EntGPT-P) significantly boosts the micro-F_1 score by up to 36% o","authors_text":"Amrit Poudel, Balaji Veeramani, Qingkai Zeng, Sanmitra Bhattacharya, Tim Weninger, Yifan Ding","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-09T19:16:27Z","title":"EntGPT: Entity Linking with Generative Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.06738","kind":"arxiv","version":3},"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":"sha256:6800a354e1dafe0970c7252a66b1fb4de933217c77e296e5d476248c3c169fda","target":"record","created_at":"2026-07-05T11:07:01Z","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":"83e62900ffad2d97d7c8814971ff1d343f12900d569beddee2f0607c2bd410eb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-09T19:16:27Z","title_canon_sha256":"dc46d0ea158d7556e32fd9060e71f1159a114799d9fc26aa9744bd461f8c60ca"},"schema_version":"1.0","source":{"id":"2402.06738","kind":"arxiv","version":3}},"canonical_sha256":"e3a8c9bd20fe7a1e15347efdd60765af153d5c8dccd6f2bf1185cee4406ca365","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e3a8c9bd20fe7a1e15347efdd60765af153d5c8dccd6f2bf1185cee4406ca365","first_computed_at":"2026-07-05T11:07:01.566759Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:01.566759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8eCQcEIuMrpO0arzHDJVeUeSsLY16+jwcEjizd4sqyNxb7g1OZFbV9Ng+7SxLP5qTxwfA+3UxzdpJJNbQO2QAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:01.567171Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.06738","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6800a354e1dafe0970c7252a66b1fb4de933217c77e296e5d476248c3c169fda","sha256:12e66114f6dfcaf73c0775c5406bb743c44b19639baa668ce895765912d52551"],"state_sha256":"d4168c3dc8960bc2fca649cab6c08dee39ebb7676440eb2f84514f8e976a9a6a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TASwFnT3fIAaVU+YIJiQvaxB80Kxe55Ynwnu7Gx5yRtZrKVgJdBSOOawT2yfDMmbnIXlkc4AeI1/avtJbeGSBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:36:37.817935Z","bundle_sha256":"b80682799469221921e8cf050ccba86ea33e741d4c154fce66ac0e2041deca1f"}}