{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:I6EXTQOL46IWEGDIU3I5U6YLFV","short_pith_number":"pith:I6EXTQOL","canonical_record":{"source":{"id":"2506.02509","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-06-03T06:39:18Z","cross_cats_sorted":[],"title_canon_sha256":"656ed891e1eb48b9bcd219238ef019ac52919b0d754056f2a90b3ec76445fb64","abstract_canon_sha256":"5ba9000c65b9563dac4e7fd385965ff5edd0ce2d90859ea5a3ee9ca22d3f1e79"},"schema_version":"1.0"},"canonical_sha256":"478979c1cbe791621868a6d1da7b0b2d4830016c48feebcb0fc0c59e4b4affd6","source":{"kind":"arxiv","id":"2506.02509","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02509","created_at":"2026-07-05T11:15:03Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02509v1","created_at":"2026-07-05T11:15:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02509","created_at":"2026-07-05T11:15:03Z"},{"alias_kind":"pith_short_12","alias_value":"I6EXTQOL46IW","created_at":"2026-07-05T11:15:03Z"},{"alias_kind":"pith_short_16","alias_value":"I6EXTQOL46IWEGDI","created_at":"2026-07-05T11:15:03Z"},{"alias_kind":"pith_short_8","alias_value":"I6EXTQOL","created_at":"2026-07-05T11:15:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:I6EXTQOL46IWEGDIU3I5U6YLFV","target":"record","payload":{"canonical_record":{"source":{"id":"2506.02509","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-06-03T06:39:18Z","cross_cats_sorted":[],"title_canon_sha256":"656ed891e1eb48b9bcd219238ef019ac52919b0d754056f2a90b3ec76445fb64","abstract_canon_sha256":"5ba9000c65b9563dac4e7fd385965ff5edd0ce2d90859ea5a3ee9ca22d3f1e79"},"schema_version":"1.0"},"canonical_sha256":"478979c1cbe791621868a6d1da7b0b2d4830016c48feebcb0fc0c59e4b4affd6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:03.392856Z","signature_b64":"aOAWyZPfZt0QrZj2HzMWz8p87mm8os6gF2eWjtXSLqSXPD+pXb6L41UA0EpnOgJL6Ljee+zzoZl3bY/6Rq9zBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"478979c1cbe791621868a6d1da7b0b2d4830016c48feebcb0fc0c59e4b4affd6","last_reissued_at":"2026-07-05T11:15:03.392376Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:03.392376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.02509","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":"2026-07-05T11:15:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rKOYP8capkAPOIXUt8f6Yo+S8ujIbRI3STsHiO2Ki+7KbKRPB7ZhNuX/JJMX+kp95YITVUDE3q7SJGmO0qIiCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:23:49.959069Z"},"content_sha256":"7fdcff619f841144349395474760e9747789a0c051e8515af7478c626a308dda","schema_version":"1.0","event_id":"sha256:7fdcff619f841144349395474760e9747789a0c051e8515af7478c626a308dda"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:I6EXTQOL46IWEGDIU3I5U6YLFV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"In-context Clustering-based Entity Resolution with Large Language Models: A Design Space Exploration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Arijit Khan, Haitong Tang, Jiajie Fu, Sharad Mehrotra, Xiangyu Ke, Yunjun Gao","submitted_at":"2025-06-03T06:39:18Z","abstract_excerpt":"Entity Resolution (ER) is a fundamental data quality improvement task that identifies and links records referring to the same real-world entity. Traditional ER approaches often rely on pairwise comparisons, which can be costly in terms of time and monetary resources, especially with large datasets. Recently, Large Language Models (LLMs) have shown promising results in ER tasks. However, existing methods typically focus on pairwise matching, missing the potential of LLMs to perform clustering directly in a more cost-effective and scalable manner. In this paper, we propose a novel in-context clu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02509","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/2506.02509/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":"2026-07-05T11:15:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IvAWhAivVGesAsiyGgEPnDkADM622oofw0ovD/s/IehFiNrtjzWANTfDtVMWcbU2rcLRzJlxYGy88i+5UY+pDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:23:49.959609Z"},"content_sha256":"b3727e6bab4e61b7d6c644e4b08700b018fda05b3dfa6495dfa2f7549ecbbbb8","schema_version":"1.0","event_id":"sha256:b3727e6bab4e61b7d6c644e4b08700b018fda05b3dfa6495dfa2f7549ecbbbb8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I6EXTQOL46IWEGDIU3I5U6YLFV/bundle.json","state_url":"https://pith.science/pith/I6EXTQOL46IWEGDIU3I5U6YLFV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I6EXTQOL46IWEGDIU3I5U6YLFV/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":"2026-08-08T18:23:49Z","links":{"resolver":"https://pith.science/pith/I6EXTQOL46IWEGDIU3I5U6YLFV","bundle":"https://pith.science/pith/I6EXTQOL46IWEGDIU3I5U6YLFV/bundle.json","state":"https://pith.science/pith/I6EXTQOL46IWEGDIU3I5U6YLFV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I6EXTQOL46IWEGDIU3I5U6YLFV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:I6EXTQOL46IWEGDIU3I5U6YLFV","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":"5ba9000c65b9563dac4e7fd385965ff5edd0ce2d90859ea5a3ee9ca22d3f1e79","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-06-03T06:39:18Z","title_canon_sha256":"656ed891e1eb48b9bcd219238ef019ac52919b0d754056f2a90b3ec76445fb64"},"schema_version":"1.0","source":{"id":"2506.02509","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02509","created_at":"2026-07-05T11:15:03Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02509v1","created_at":"2026-07-05T11:15:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02509","created_at":"2026-07-05T11:15:03Z"},{"alias_kind":"pith_short_12","alias_value":"I6EXTQOL46IW","created_at":"2026-07-05T11:15:03Z"},{"alias_kind":"pith_short_16","alias_value":"I6EXTQOL46IWEGDI","created_at":"2026-07-05T11:15:03Z"},{"alias_kind":"pith_short_8","alias_value":"I6EXTQOL","created_at":"2026-07-05T11:15:03Z"}],"graph_snapshots":[{"event_id":"sha256:b3727e6bab4e61b7d6c644e4b08700b018fda05b3dfa6495dfa2f7549ecbbbb8","target":"graph","created_at":"2026-07-05T11:15:03Z","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/2506.02509/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Entity Resolution (ER) is a fundamental data quality improvement task that identifies and links records referring to the same real-world entity. Traditional ER approaches often rely on pairwise comparisons, which can be costly in terms of time and monetary resources, especially with large datasets. Recently, Large Language Models (LLMs) have shown promising results in ER tasks. However, existing methods typically focus on pairwise matching, missing the potential of LLMs to perform clustering directly in a more cost-effective and scalable manner. In this paper, we propose a novel in-context clu","authors_text":"Arijit Khan, Haitong Tang, Jiajie Fu, Sharad Mehrotra, Xiangyu Ke, Yunjun Gao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-06-03T06:39:18Z","title":"In-context Clustering-based Entity Resolution with Large Language Models: A Design Space Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02509","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":"sha256:7fdcff619f841144349395474760e9747789a0c051e8515af7478c626a308dda","target":"record","created_at":"2026-07-05T11:15:03Z","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":"5ba9000c65b9563dac4e7fd385965ff5edd0ce2d90859ea5a3ee9ca22d3f1e79","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-06-03T06:39:18Z","title_canon_sha256":"656ed891e1eb48b9bcd219238ef019ac52919b0d754056f2a90b3ec76445fb64"},"schema_version":"1.0","source":{"id":"2506.02509","kind":"arxiv","version":1}},"canonical_sha256":"478979c1cbe791621868a6d1da7b0b2d4830016c48feebcb0fc0c59e4b4affd6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"478979c1cbe791621868a6d1da7b0b2d4830016c48feebcb0fc0c59e4b4affd6","first_computed_at":"2026-07-05T11:15:03.392376Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:03.392376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aOAWyZPfZt0QrZj2HzMWz8p87mm8os6gF2eWjtXSLqSXPD+pXb6L41UA0EpnOgJL6Ljee+zzoZl3bY/6Rq9zBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:03.392856Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.02509","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7fdcff619f841144349395474760e9747789a0c051e8515af7478c626a308dda","sha256:b3727e6bab4e61b7d6c644e4b08700b018fda05b3dfa6495dfa2f7549ecbbbb8"],"state_sha256":"1d9db250b6744f6cbb241effdcf97726542c7837124a2a0ea0a30da2d1c62b41"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"voi7b7T1SSNuN5StOjrD4LjnfTqQZZG3xCLD0wodHCIZGKByDer1lE23oEPrb4dg3JkuffUDDzA08cVQgNrVBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T18:23:49.966180Z","bundle_sha256":"bc2e9dd36042b435bc4bb859c5a1e8514f08112f34f5382a81d72df597a542d2"}}