{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XJDR5WX3LR6DY65OJBABTC5YZS","short_pith_number":"pith:XJDR5WX3","canonical_record":{"source":{"id":"2405.20624","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-31T05:22:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f225ba99b58014201725d1c10b5e9590d038741d0aae64a219aa527edd350ce9","abstract_canon_sha256":"4cdb821f96ae65d44968795d198b2e8b22e19c3d7c2cc0c255ba5208413f461e"},"schema_version":"1.0"},"canonical_sha256":"ba471edafb5c7c3c7bae4840198bb8ccb996db241554e7e2485ac2bf55a64c48","source":{"kind":"arxiv","id":"2405.20624","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.20624","created_at":"2026-07-05T08:25:39Z"},{"alias_kind":"arxiv_version","alias_value":"2405.20624v1","created_at":"2026-07-05T08:25:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20624","created_at":"2026-07-05T08:25:39Z"},{"alias_kind":"pith_short_12","alias_value":"XJDR5WX3LR6D","created_at":"2026-07-05T08:25:39Z"},{"alias_kind":"pith_short_16","alias_value":"XJDR5WX3LR6DY65O","created_at":"2026-07-05T08:25:39Z"},{"alias_kind":"pith_short_8","alias_value":"XJDR5WX3","created_at":"2026-07-05T08:25:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XJDR5WX3LR6DY65OJBABTC5YZS","target":"record","payload":{"canonical_record":{"source":{"id":"2405.20624","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-31T05:22:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f225ba99b58014201725d1c10b5e9590d038741d0aae64a219aa527edd350ce9","abstract_canon_sha256":"4cdb821f96ae65d44968795d198b2e8b22e19c3d7c2cc0c255ba5208413f461e"},"schema_version":"1.0"},"canonical_sha256":"ba471edafb5c7c3c7bae4840198bb8ccb996db241554e7e2485ac2bf55a64c48","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:39.920309Z","signature_b64":"SHNsxyL01NACBoBQm5mjVVussBZRIzma72lY2PqdBdKrl6jFwICai+HTzw4SbtkyI0nZx4jsIDK2fgMWgaHkBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba471edafb5c7c3c7bae4840198bb8ccb996db241554e7e2485ac2bf55a64c48","last_reissued_at":"2026-07-05T08:25:39.919867Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:39.919867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.20624","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":"2026-07-05T08:25:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vdPLD4O8APgKCc+/DyoTCeFPqeCyIeq4WSTuinJcRoZm4VIkDYQNn5RIrrz8ivZLoJCcfUExh7LjvXsi0ojsBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:22:10.588671Z"},"content_sha256":"dbf03107570d247c7164e27d97f0e41286d1dfb46e81da6f02d540f9536d0373","schema_version":"1.0","event_id":"sha256:dbf03107570d247c7164e27d97f0e41286d1dfb46e81da6f02d540f9536d0373"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XJDR5WX3LR6DY65OJBABTC5YZS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging Large Language Models for Entity Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Qianyu Huang, Tongfang Zhao","submitted_at":"2024-05-31T05:22:07Z","abstract_excerpt":"Entity matching (EM) is a critical task in data integration, aiming to identify records across different datasets that refer to the same real-world entities. Traditional methods often rely on manually engineered features and rule-based systems, which struggle with diverse and unstructured data. The emergence of Large Language Models (LLMs) such as GPT-4 offers transformative potential for EM, leveraging their advanced semantic understanding and contextual capabilities. This vision paper explores the application of LLMs to EM, discussing their advantages, challenges, and future research directi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20624","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/2405.20624/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":"2026-07-05T08:25:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DB6YDftb4VcFzDQDO0cqNbid0B6JI8PWB04eqZ8NL0cDvuEBCekg86AZQod2meY+d3k3Nz+xZZen0YR9vOoNBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:22:10.589220Z"},"content_sha256":"c76976c9479b09e8973d1d36598c338618ed7df1a0b8b3558349a6a1e7946eb3","schema_version":"1.0","event_id":"sha256:c76976c9479b09e8973d1d36598c338618ed7df1a0b8b3558349a6a1e7946eb3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XJDR5WX3LR6DY65OJBABTC5YZS/bundle.json","state_url":"https://pith.science/pith/XJDR5WX3LR6DY65OJBABTC5YZS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XJDR5WX3LR6DY65OJBABTC5YZS/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":"2026-08-08T16:22:10Z","links":{"resolver":"https://pith.science/pith/XJDR5WX3LR6DY65OJBABTC5YZS","bundle":"https://pith.science/pith/XJDR5WX3LR6DY65OJBABTC5YZS/bundle.json","state":"https://pith.science/pith/XJDR5WX3LR6DY65OJBABTC5YZS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XJDR5WX3LR6DY65OJBABTC5YZS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XJDR5WX3LR6DY65OJBABTC5YZS","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":"4cdb821f96ae65d44968795d198b2e8b22e19c3d7c2cc0c255ba5208413f461e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-31T05:22:07Z","title_canon_sha256":"f225ba99b58014201725d1c10b5e9590d038741d0aae64a219aa527edd350ce9"},"schema_version":"1.0","source":{"id":"2405.20624","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.20624","created_at":"2026-07-05T08:25:39Z"},{"alias_kind":"arxiv_version","alias_value":"2405.20624v1","created_at":"2026-07-05T08:25:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20624","created_at":"2026-07-05T08:25:39Z"},{"alias_kind":"pith_short_12","alias_value":"XJDR5WX3LR6D","created_at":"2026-07-05T08:25:39Z"},{"alias_kind":"pith_short_16","alias_value":"XJDR5WX3LR6DY65O","created_at":"2026-07-05T08:25:39Z"},{"alias_kind":"pith_short_8","alias_value":"XJDR5WX3","created_at":"2026-07-05T08:25:39Z"}],"graph_snapshots":[{"event_id":"sha256:c76976c9479b09e8973d1d36598c338618ed7df1a0b8b3558349a6a1e7946eb3","target":"graph","created_at":"2026-07-05T08:25:39Z","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/2405.20624/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Entity matching (EM) is a critical task in data integration, aiming to identify records across different datasets that refer to the same real-world entities. Traditional methods often rely on manually engineered features and rule-based systems, which struggle with diverse and unstructured data. The emergence of Large Language Models (LLMs) such as GPT-4 offers transformative potential for EM, leveraging their advanced semantic understanding and contextual capabilities. This vision paper explores the application of LLMs to EM, discussing their advantages, challenges, and future research directi","authors_text":"Qianyu Huang, Tongfang Zhao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-31T05:22:07Z","title":"Leveraging Large Language Models for Entity Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20624","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:dbf03107570d247c7164e27d97f0e41286d1dfb46e81da6f02d540f9536d0373","target":"record","created_at":"2026-07-05T08:25:39Z","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":"4cdb821f96ae65d44968795d198b2e8b22e19c3d7c2cc0c255ba5208413f461e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-31T05:22:07Z","title_canon_sha256":"f225ba99b58014201725d1c10b5e9590d038741d0aae64a219aa527edd350ce9"},"schema_version":"1.0","source":{"id":"2405.20624","kind":"arxiv","version":1}},"canonical_sha256":"ba471edafb5c7c3c7bae4840198bb8ccb996db241554e7e2485ac2bf55a64c48","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba471edafb5c7c3c7bae4840198bb8ccb996db241554e7e2485ac2bf55a64c48","first_computed_at":"2026-07-05T08:25:39.919867Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:25:39.919867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SHNsxyL01NACBoBQm5mjVVussBZRIzma72lY2PqdBdKrl6jFwICai+HTzw4SbtkyI0nZx4jsIDK2fgMWgaHkBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:25:39.920309Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.20624","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dbf03107570d247c7164e27d97f0e41286d1dfb46e81da6f02d540f9536d0373","sha256:c76976c9479b09e8973d1d36598c338618ed7df1a0b8b3558349a6a1e7946eb3"],"state_sha256":"6aa14773cc8821e2d1d052381c651b0da26f65f0f09d4915bd63ccac9ac9b54f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N/RuUPXyWx65Hj1bEUZdmoukGh0BEHGlM247d9mMAVYiNopsBYxzWI0jCjpU2mCxcKdfS+XpWURWxFxPAKgpBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T16:22:10.594419Z","bundle_sha256":"0ae05046cf1df20fe93f42f51a2d7d5f74833da712c89487a5e7799c10134258"}}