{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:TZAAYRG27OMJ4LSVR3RBFPFIAO","short_pith_number":"pith:TZAAYRG2","canonical_record":{"source":{"id":"2310.11244","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-17T13:12:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"eded7ed7ba25e5cc37d583de53932a0419d9bd35305c1356315b6bfe3af745d6","abstract_canon_sha256":"a2a2d79565b6c27f607b2dcb98cc40d45704b9035194f31994fa79f8471abf43"},"schema_version":"1.0"},"canonical_sha256":"9e400c44dafb989e2e558ee212bca803bc41845379c66ab0560239757488f060","source":{"kind":"arxiv","id":"2310.11244","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.11244","created_at":"2026-07-05T09:22:14Z"},{"alias_kind":"arxiv_version","alias_value":"2310.11244v4","created_at":"2026-07-05T09:22:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.11244","created_at":"2026-07-05T09:22:14Z"},{"alias_kind":"pith_short_12","alias_value":"TZAAYRG27OMJ","created_at":"2026-07-05T09:22:14Z"},{"alias_kind":"pith_short_16","alias_value":"TZAAYRG27OMJ4LSV","created_at":"2026-07-05T09:22:14Z"},{"alias_kind":"pith_short_8","alias_value":"TZAAYRG2","created_at":"2026-07-05T09:22:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:TZAAYRG27OMJ4LSVR3RBFPFIAO","target":"record","payload":{"canonical_record":{"source":{"id":"2310.11244","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-17T13:12:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"eded7ed7ba25e5cc37d583de53932a0419d9bd35305c1356315b6bfe3af745d6","abstract_canon_sha256":"a2a2d79565b6c27f607b2dcb98cc40d45704b9035194f31994fa79f8471abf43"},"schema_version":"1.0"},"canonical_sha256":"9e400c44dafb989e2e558ee212bca803bc41845379c66ab0560239757488f060","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:22:14.483773Z","signature_b64":"Gtg9pWLx5eJnFsgPwc20MPFrNsSYnYpf90jMfwl6D9DtKJiJraPwCDMzI+/Sa5j9XRYgXN62gYMi5d4suvYnCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e400c44dafb989e2e558ee212bca803bc41845379c66ab0560239757488f060","last_reissued_at":"2026-07-05T09:22:14.483338Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:22:14.483338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.11244","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:22:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GBhTDnX+cfviELtyqT1yVKHtVmhYoKnsYnbAIVmlgGaPQKVfY04qdJzDsbwMrf+szPMDAVbNCrZp6/OYwt9LDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T00:16:58.809171Z"},"content_sha256":"0a3400f30887c0c73bce363ce2d6c76c773fd8e8aefd7a726273f1a452c55f8e","schema_version":"1.0","event_id":"sha256:0a3400f30887c0c73bce363ce2d6c76c773fd8e8aefd7a726273f1a452c55f8e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:TZAAYRG27OMJ4LSVR3RBFPFIAO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Entity Matching using Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Aaron Steiner, Christian Bizer, Ralph Peeters","submitted_at":"2023-10-17T13:12:32Z","abstract_excerpt":"Entity matching is the task of deciding whether two entity descriptions refer to the same real-world entity. Entity matching is a central step in most data integration pipelines. Many state-of-the-art entity matching methods rely on pre-trained language models (PLMs) such as BERT or RoBERTa. Two major drawbacks of these models for entity matching are that (i) the models require significant amounts of task-specific training data and (ii) the fine-tuned models are not robust concerning out-of-distribution entities. This paper investigates using generative large language models (LLMs) as a less t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.11244","kind":"arxiv","version":4},"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/2310.11244/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":"2026-07-05T09:22:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aLbFPl9qAnmauShrbRxe6NSGUR3X2Gct6pAU1nw27JIcj6KNapz1VgKZVzCkhsHauS6LEViECju+fTIru0iZDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T00:16:58.809694Z"},"content_sha256":"56f8f0abd62fb7b3e6bf1b7e7a10cdf7d48321bcef3a65d0a34a43850487782a","schema_version":"1.0","event_id":"sha256:56f8f0abd62fb7b3e6bf1b7e7a10cdf7d48321bcef3a65d0a34a43850487782a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TZAAYRG27OMJ4LSVR3RBFPFIAO/bundle.json","state_url":"https://pith.science/pith/TZAAYRG27OMJ4LSVR3RBFPFIAO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TZAAYRG27OMJ4LSVR3RBFPFIAO/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":"2026-08-08T00:16:58Z","links":{"resolver":"https://pith.science/pith/TZAAYRG27OMJ4LSVR3RBFPFIAO","bundle":"https://pith.science/pith/TZAAYRG27OMJ4LSVR3RBFPFIAO/bundle.json","state":"https://pith.science/pith/TZAAYRG27OMJ4LSVR3RBFPFIAO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TZAAYRG27OMJ4LSVR3RBFPFIAO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TZAAYRG27OMJ4LSVR3RBFPFIAO","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":"a2a2d79565b6c27f607b2dcb98cc40d45704b9035194f31994fa79f8471abf43","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-17T13:12:32Z","title_canon_sha256":"eded7ed7ba25e5cc37d583de53932a0419d9bd35305c1356315b6bfe3af745d6"},"schema_version":"1.0","source":{"id":"2310.11244","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.11244","created_at":"2026-07-05T09:22:14Z"},{"alias_kind":"arxiv_version","alias_value":"2310.11244v4","created_at":"2026-07-05T09:22:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.11244","created_at":"2026-07-05T09:22:14Z"},{"alias_kind":"pith_short_12","alias_value":"TZAAYRG27OMJ","created_at":"2026-07-05T09:22:14Z"},{"alias_kind":"pith_short_16","alias_value":"TZAAYRG27OMJ4LSV","created_at":"2026-07-05T09:22:14Z"},{"alias_kind":"pith_short_8","alias_value":"TZAAYRG2","created_at":"2026-07-05T09:22:14Z"}],"graph_snapshots":[{"event_id":"sha256:56f8f0abd62fb7b3e6bf1b7e7a10cdf7d48321bcef3a65d0a34a43850487782a","target":"graph","created_at":"2026-07-05T09:22:14Z","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/2310.11244/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Entity matching is the task of deciding whether two entity descriptions refer to the same real-world entity. Entity matching is a central step in most data integration pipelines. Many state-of-the-art entity matching methods rely on pre-trained language models (PLMs) such as BERT or RoBERTa. Two major drawbacks of these models for entity matching are that (i) the models require significant amounts of task-specific training data and (ii) the fine-tuned models are not robust concerning out-of-distribution entities. This paper investigates using generative large language models (LLMs) as a less t","authors_text":"Aaron Steiner, Christian Bizer, Ralph Peeters","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-17T13:12:32Z","title":"Entity Matching using Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.11244","kind":"arxiv","version":4},"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":"sha256:0a3400f30887c0c73bce363ce2d6c76c773fd8e8aefd7a726273f1a452c55f8e","target":"record","created_at":"2026-07-05T09:22:14Z","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":"a2a2d79565b6c27f607b2dcb98cc40d45704b9035194f31994fa79f8471abf43","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-17T13:12:32Z","title_canon_sha256":"eded7ed7ba25e5cc37d583de53932a0419d9bd35305c1356315b6bfe3af745d6"},"schema_version":"1.0","source":{"id":"2310.11244","kind":"arxiv","version":4}},"canonical_sha256":"9e400c44dafb989e2e558ee212bca803bc41845379c66ab0560239757488f060","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e400c44dafb989e2e558ee212bca803bc41845379c66ab0560239757488f060","first_computed_at":"2026-07-05T09:22:14.483338Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:22:14.483338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Gtg9pWLx5eJnFsgPwc20MPFrNsSYnYpf90jMfwl6D9DtKJiJraPwCDMzI+/Sa5j9XRYgXN62gYMi5d4suvYnCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:22:14.483773Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.11244","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a3400f30887c0c73bce363ce2d6c76c773fd8e8aefd7a726273f1a452c55f8e","sha256:56f8f0abd62fb7b3e6bf1b7e7a10cdf7d48321bcef3a65d0a34a43850487782a"],"state_sha256":"4b70c80e42d4ed03fd48f813f8f7338a67b5c7aa08c51b131b3b00b7661062b4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ONIb9W4vXCWhUtJrCPvhnjX8NU2uWXIpjKcK5gmVkI0gKS9Odac+gIw6oyALiA3tJtQ1wrjpfGSNTH8OOBm0Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T00:16:58.816676Z","bundle_sha256":"6dc64f3180baddecf2b0f1086bfe40b6af69b69a845777eced42d81d21f73372"}}