{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:WEX7EEM5K3XNIZBRXUVREEGDBS","short_pith_number":"pith:WEX7EEM5","canonical_record":{"source":{"id":"2409.08185","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-12T16:20:57Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c2f9278dc837dd46a52fbc5b6b85a0ef550df6cb82ce8d0ba6bc71c8f7cdfe29","abstract_canon_sha256":"5fa1582632db40dfaa8c98d30d21cd0dbd948a1cbb2b6ce32a2cb6b372ce576e"},"schema_version":"1.0"},"canonical_sha256":"b12ff2119d56eed46431bd2b1210c30c99a237996216edea632537a3c2eb2de8","source":{"kind":"arxiv","id":"2409.08185","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.08185","created_at":"2026-07-05T11:06:23Z"},{"alias_kind":"arxiv_version","alias_value":"2409.08185v2","created_at":"2026-07-05T11:06:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08185","created_at":"2026-07-05T11:06:23Z"},{"alias_kind":"pith_short_12","alias_value":"WEX7EEM5K3XN","created_at":"2026-07-05T11:06:23Z"},{"alias_kind":"pith_short_16","alias_value":"WEX7EEM5K3XNIZBR","created_at":"2026-07-05T11:06:23Z"},{"alias_kind":"pith_short_8","alias_value":"WEX7EEM5","created_at":"2026-07-05T11:06:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:WEX7EEM5K3XNIZBRXUVREEGDBS","target":"record","payload":{"canonical_record":{"source":{"id":"2409.08185","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-12T16:20:57Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c2f9278dc837dd46a52fbc5b6b85a0ef550df6cb82ce8d0ba6bc71c8f7cdfe29","abstract_canon_sha256":"5fa1582632db40dfaa8c98d30d21cd0dbd948a1cbb2b6ce32a2cb6b372ce576e"},"schema_version":"1.0"},"canonical_sha256":"b12ff2119d56eed46431bd2b1210c30c99a237996216edea632537a3c2eb2de8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:23.360529Z","signature_b64":"3wqvH4CmjlEOO59j0Mj/0PhScxRw5DAxKvW3YeQKMQvBMIQbk5ERSXPl3WER0rzCrWtgsINoWy+nlu6Td7zFCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b12ff2119d56eed46431bd2b1210c30c99a237996216edea632537a3c2eb2de8","last_reissued_at":"2026-07-05T11:06:23.359888Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:23.359888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.08185","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":"2026-07-05T11:06:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6u0K7Sia6Ykj0dWcfZiY0h1W9kTTRZ0Wv3esVC4Gah6Rq5TbehcCaxUO3SYgM43CZ9Sv8ARF8PaPz3AsDXWlAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:53:05.472463Z"},"content_sha256":"75004f9de2ff680b891c04c50867e64374d0c3d8a86dec92772a4cf5dc61b048","schema_version":"1.0","event_id":"sha256:75004f9de2ff680b891c04c50867e64374d0c3d8a86dec92772a4cf5dc61b048"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:WEX7EEM5K3XNIZBRXUVREEGDBS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fine-tuning Large Language Models for Entity Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aaron Steiner, Christian Bizer, Ralph Peeters","submitted_at":"2024-09-12T16:20:57Z","abstract_excerpt":"Generative large language models (LLMs) are a promising alternative to pre-trained language models for entity matching due to their high zero-shot performance and ability to generalize to unseen entities. Existing research on using LLMs for entity matching has focused on prompt engineering and in-context learning. This paper explores the potential of fine-tuning LLMs for entity matching. We analyze fine-tuning along two dimensions: 1) the representation of training examples, where we experiment with adding different types of LLM-generated explanations to the training set, and 2) the selection "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08185","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/2409.08185/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":"2026-07-05T11:06:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iQXh8/ya4jktW3jVbuten9JzCziNVt3D2wlASdliPanfzrUdUsfwMoIQQKcvI8wqY4GStNJM/ZyJGLMQkCBoBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:53:05.473241Z"},"content_sha256":"9506e6d3dd80c37037c195906aa2daaf53eb81c61f6db6d05577f25351a10111","schema_version":"1.0","event_id":"sha256:9506e6d3dd80c37037c195906aa2daaf53eb81c61f6db6d05577f25351a10111"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WEX7EEM5K3XNIZBRXUVREEGDBS/bundle.json","state_url":"https://pith.science/pith/WEX7EEM5K3XNIZBRXUVREEGDBS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WEX7EEM5K3XNIZBRXUVREEGDBS/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":"2026-08-06T03:53:05Z","links":{"resolver":"https://pith.science/pith/WEX7EEM5K3XNIZBRXUVREEGDBS","bundle":"https://pith.science/pith/WEX7EEM5K3XNIZBRXUVREEGDBS/bundle.json","state":"https://pith.science/pith/WEX7EEM5K3XNIZBRXUVREEGDBS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WEX7EEM5K3XNIZBRXUVREEGDBS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WEX7EEM5K3XNIZBRXUVREEGDBS","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":"5fa1582632db40dfaa8c98d30d21cd0dbd948a1cbb2b6ce32a2cb6b372ce576e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-12T16:20:57Z","title_canon_sha256":"c2f9278dc837dd46a52fbc5b6b85a0ef550df6cb82ce8d0ba6bc71c8f7cdfe29"},"schema_version":"1.0","source":{"id":"2409.08185","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.08185","created_at":"2026-07-05T11:06:23Z"},{"alias_kind":"arxiv_version","alias_value":"2409.08185v2","created_at":"2026-07-05T11:06:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08185","created_at":"2026-07-05T11:06:23Z"},{"alias_kind":"pith_short_12","alias_value":"WEX7EEM5K3XN","created_at":"2026-07-05T11:06:23Z"},{"alias_kind":"pith_short_16","alias_value":"WEX7EEM5K3XNIZBR","created_at":"2026-07-05T11:06:23Z"},{"alias_kind":"pith_short_8","alias_value":"WEX7EEM5","created_at":"2026-07-05T11:06:23Z"}],"graph_snapshots":[{"event_id":"sha256:9506e6d3dd80c37037c195906aa2daaf53eb81c61f6db6d05577f25351a10111","target":"graph","created_at":"2026-07-05T11:06:23Z","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/2409.08185/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generative large language models (LLMs) are a promising alternative to pre-trained language models for entity matching due to their high zero-shot performance and ability to generalize to unseen entities. Existing research on using LLMs for entity matching has focused on prompt engineering and in-context learning. This paper explores the potential of fine-tuning LLMs for entity matching. We analyze fine-tuning along two dimensions: 1) the representation of training examples, where we experiment with adding different types of LLM-generated explanations to the training set, and 2) the selection ","authors_text":"Aaron Steiner, Christian Bizer, Ralph Peeters","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-12T16:20:57Z","title":"Fine-tuning Large Language Models for Entity Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08185","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":"sha256:75004f9de2ff680b891c04c50867e64374d0c3d8a86dec92772a4cf5dc61b048","target":"record","created_at":"2026-07-05T11:06:23Z","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":"5fa1582632db40dfaa8c98d30d21cd0dbd948a1cbb2b6ce32a2cb6b372ce576e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-12T16:20:57Z","title_canon_sha256":"c2f9278dc837dd46a52fbc5b6b85a0ef550df6cb82ce8d0ba6bc71c8f7cdfe29"},"schema_version":"1.0","source":{"id":"2409.08185","kind":"arxiv","version":2}},"canonical_sha256":"b12ff2119d56eed46431bd2b1210c30c99a237996216edea632537a3c2eb2de8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b12ff2119d56eed46431bd2b1210c30c99a237996216edea632537a3c2eb2de8","first_computed_at":"2026-07-05T11:06:23.359888Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:23.359888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3wqvH4CmjlEOO59j0Mj/0PhScxRw5DAxKvW3YeQKMQvBMIQbk5ERSXPl3WER0rzCrWtgsINoWy+nlu6Td7zFCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:23.360529Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.08185","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:75004f9de2ff680b891c04c50867e64374d0c3d8a86dec92772a4cf5dc61b048","sha256:9506e6d3dd80c37037c195906aa2daaf53eb81c61f6db6d05577f25351a10111"],"state_sha256":"42ef48887b0bf9ba45d9ca34821d18ede3dd6866953b24e6bb02641e7df48e80"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RGvkCF8oe4tIldUKy6QQALYgZdv35O1hr7UbhcQo8dIjE0NEaBd55B0Gph1xJGEZL7qBnnfbU+P/p7Hf/2ccBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T03:53:05.478548Z","bundle_sha256":"bfa76cabcfa78013f15768aa28192fbd8a8319001e0b039df77e7ce3ec4c3e85"}}