{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SS54RG6ZL2UIZNKUDPRLZXXDFY","short_pith_number":"pith:SS54RG6Z","canonical_record":{"source":{"id":"2404.04281","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-03T03:17:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ccd48c339f5bad241b852492491dd9fabe61b5350c1cff979302cd907bc2d03f","abstract_canon_sha256":"cb26b0c4bb3dcf5302ebb435fc00f6533de86fe674ce141390088dceda533a1e"},"schema_version":"1.0"},"canonical_sha256":"94bbc89bd95ea88cb5541be2bcdee32e34354dfbbca4dc41cb7889afeae95aa2","source":{"kind":"arxiv","id":"2404.04281","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.04281","created_at":"2026-07-05T09:13:00Z"},{"alias_kind":"arxiv_version","alias_value":"2404.04281v2","created_at":"2026-07-05T09:13:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.04281","created_at":"2026-07-05T09:13:00Z"},{"alias_kind":"pith_short_12","alias_value":"SS54RG6ZL2UI","created_at":"2026-07-05T09:13:00Z"},{"alias_kind":"pith_short_16","alias_value":"SS54RG6ZL2UIZNKU","created_at":"2026-07-05T09:13:00Z"},{"alias_kind":"pith_short_8","alias_value":"SS54RG6Z","created_at":"2026-07-05T09:13:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SS54RG6ZL2UIZNKUDPRLZXXDFY","target":"record","payload":{"canonical_record":{"source":{"id":"2404.04281","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-03T03:17:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ccd48c339f5bad241b852492491dd9fabe61b5350c1cff979302cd907bc2d03f","abstract_canon_sha256":"cb26b0c4bb3dcf5302ebb435fc00f6533de86fe674ce141390088dceda533a1e"},"schema_version":"1.0"},"canonical_sha256":"94bbc89bd95ea88cb5541be2bcdee32e34354dfbbca4dc41cb7889afeae95aa2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:00.976405Z","signature_b64":"KMKe9nHxwgSUs2XmQYlhCP4lG4t1su4VfeU7ryYQR9ZU7g0VfiBiFDbacujtm+U7bdA+R91raTaCuneqvA8KDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94bbc89bd95ea88cb5541be2bcdee32e34354dfbbca4dc41cb7889afeae95aa2","last_reissued_at":"2026-07-05T09:13:00.975909Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:00.975909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.04281","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":"2026-07-05T09:13:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UTIz9rv9EsvXZA/RdamOcNr/RT4QoUtIGNx0+UFyAh9KoFCM4kX9a6MmbKLjtxf5LR0NWFV7tvQtWAvRAXoiCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:43:30.404010Z"},"content_sha256":"f83867921f9f37b503e7f85917397b1be89ab071c2541d347c347961e4852174","schema_version":"1.0","event_id":"sha256:f83867921f9f37b503e7f85917397b1be89ab071c2541d347c347961e4852174"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SS54RG6ZL2UIZNKUDPRLZXXDFY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Similar Data Points Identification with LLM: A Human-in-the-loop Strategy Using Summarization and Hidden State Insights","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ang Liu, Fanghao Song, Xianlong Zeng, Yijing Gao","submitted_at":"2024-04-03T03:17:28Z","abstract_excerpt":"This study introduces a simple yet effective method for identifying similar data points across non-free text domains, such as tabular and image data, using Large Language Models (LLMs). Our two-step approach involves data point summarization and hidden state extraction. Initially, data is condensed via summarization using an LLM, reducing complexity and highlighting essential information in sentences. Subsequently, the summarization sentences are fed through another LLM to extract hidden states, serving as compact, feature-rich representations. This approach leverages the advanced comprehensio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.04281","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/2404.04281/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":"2026-07-05T09:13:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zrMZcJN0UqlmogJ85xH+j6xIidt5R5YKn21Yv1FABZ8AdysUkGr2GviGB3+mA82E49KwBnNEpBsL+4r1WFi+Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:43:30.404563Z"},"content_sha256":"e9b789ccebdfcf14160bfe3980268eb024716a42c99128f5ca2b403c3ff470b3","schema_version":"1.0","event_id":"sha256:e9b789ccebdfcf14160bfe3980268eb024716a42c99128f5ca2b403c3ff470b3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SS54RG6ZL2UIZNKUDPRLZXXDFY/bundle.json","state_url":"https://pith.science/pith/SS54RG6ZL2UIZNKUDPRLZXXDFY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SS54RG6ZL2UIZNKUDPRLZXXDFY/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":"2026-08-09T05:43:30Z","links":{"resolver":"https://pith.science/pith/SS54RG6ZL2UIZNKUDPRLZXXDFY","bundle":"https://pith.science/pith/SS54RG6ZL2UIZNKUDPRLZXXDFY/bundle.json","state":"https://pith.science/pith/SS54RG6ZL2UIZNKUDPRLZXXDFY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SS54RG6ZL2UIZNKUDPRLZXXDFY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SS54RG6ZL2UIZNKUDPRLZXXDFY","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":"cb26b0c4bb3dcf5302ebb435fc00f6533de86fe674ce141390088dceda533a1e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-03T03:17:28Z","title_canon_sha256":"ccd48c339f5bad241b852492491dd9fabe61b5350c1cff979302cd907bc2d03f"},"schema_version":"1.0","source":{"id":"2404.04281","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.04281","created_at":"2026-07-05T09:13:00Z"},{"alias_kind":"arxiv_version","alias_value":"2404.04281v2","created_at":"2026-07-05T09:13:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.04281","created_at":"2026-07-05T09:13:00Z"},{"alias_kind":"pith_short_12","alias_value":"SS54RG6ZL2UI","created_at":"2026-07-05T09:13:00Z"},{"alias_kind":"pith_short_16","alias_value":"SS54RG6ZL2UIZNKU","created_at":"2026-07-05T09:13:00Z"},{"alias_kind":"pith_short_8","alias_value":"SS54RG6Z","created_at":"2026-07-05T09:13:00Z"}],"graph_snapshots":[{"event_id":"sha256:e9b789ccebdfcf14160bfe3980268eb024716a42c99128f5ca2b403c3ff470b3","target":"graph","created_at":"2026-07-05T09:13:00Z","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/2404.04281/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This study introduces a simple yet effective method for identifying similar data points across non-free text domains, such as tabular and image data, using Large Language Models (LLMs). Our two-step approach involves data point summarization and hidden state extraction. Initially, data is condensed via summarization using an LLM, reducing complexity and highlighting essential information in sentences. Subsequently, the summarization sentences are fed through another LLM to extract hidden states, serving as compact, feature-rich representations. This approach leverages the advanced comprehensio","authors_text":"Ang Liu, Fanghao Song, Xianlong Zeng, Yijing Gao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-03T03:17:28Z","title":"Similar Data Points Identification with LLM: A Human-in-the-loop Strategy Using Summarization and Hidden State Insights"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.04281","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:f83867921f9f37b503e7f85917397b1be89ab071c2541d347c347961e4852174","target":"record","created_at":"2026-07-05T09:13:00Z","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":"cb26b0c4bb3dcf5302ebb435fc00f6533de86fe674ce141390088dceda533a1e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-03T03:17:28Z","title_canon_sha256":"ccd48c339f5bad241b852492491dd9fabe61b5350c1cff979302cd907bc2d03f"},"schema_version":"1.0","source":{"id":"2404.04281","kind":"arxiv","version":2}},"canonical_sha256":"94bbc89bd95ea88cb5541be2bcdee32e34354dfbbca4dc41cb7889afeae95aa2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"94bbc89bd95ea88cb5541be2bcdee32e34354dfbbca4dc41cb7889afeae95aa2","first_computed_at":"2026-07-05T09:13:00.975909Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:13:00.975909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KMKe9nHxwgSUs2XmQYlhCP4lG4t1su4VfeU7ryYQR9ZU7g0VfiBiFDbacujtm+U7bdA+R91raTaCuneqvA8KDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:13:00.976405Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.04281","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f83867921f9f37b503e7f85917397b1be89ab071c2541d347c347961e4852174","sha256:e9b789ccebdfcf14160bfe3980268eb024716a42c99128f5ca2b403c3ff470b3"],"state_sha256":"e0cb9305242347fb2acb232579c9e95bc913b795ef77a3b6fc96b8b28548ee8b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rQPya9MOFQE+A7qzzlRrRF1WwiwVrGeTXd8+172sn6Gj3OO7f7C2bxwPrRkDardn3MWgnnpHsl5fUsoN3wzFCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T05:43:30.407869Z","bundle_sha256":"958a301c0d2ce0baef986550deb8a13ff8ace185ed56e5757ea476545cf69822"}}