{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SHNES4PJ5VYP57TCBGJ3ODMIKG","short_pith_number":"pith:SHNES4PJ","canonical_record":{"source":{"id":"2412.14533","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T05:11:16Z","cross_cats_sorted":[],"title_canon_sha256":"6f9867c3c70c2b17657e6b79b177334ece50435646c4521010a699d8658715da","abstract_canon_sha256":"60f27e8d1ee9303e3d43d701ede0b08c716b000440014aa07b65ce286e768c06"},"schema_version":"1.0"},"canonical_sha256":"91da4971e9ed70fefe620993b70d88519433281a6065df01e110492ec2a8f479","source":{"kind":"arxiv","id":"2412.14533","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.14533","created_at":"2026-07-05T11:22:35Z"},{"alias_kind":"arxiv_version","alias_value":"2412.14533v2","created_at":"2026-07-05T11:22:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14533","created_at":"2026-07-05T11:22:35Z"},{"alias_kind":"pith_short_12","alias_value":"SHNES4PJ5VYP","created_at":"2026-07-05T11:22:35Z"},{"alias_kind":"pith_short_16","alias_value":"SHNES4PJ5VYP57TC","created_at":"2026-07-05T11:22:35Z"},{"alias_kind":"pith_short_8","alias_value":"SHNES4PJ","created_at":"2026-07-05T11:22:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SHNES4PJ5VYP57TCBGJ3ODMIKG","target":"record","payload":{"canonical_record":{"source":{"id":"2412.14533","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T05:11:16Z","cross_cats_sorted":[],"title_canon_sha256":"6f9867c3c70c2b17657e6b79b177334ece50435646c4521010a699d8658715da","abstract_canon_sha256":"60f27e8d1ee9303e3d43d701ede0b08c716b000440014aa07b65ce286e768c06"},"schema_version":"1.0"},"canonical_sha256":"91da4971e9ed70fefe620993b70d88519433281a6065df01e110492ec2a8f479","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:35.043632Z","signature_b64":"DQMwl8FgEDC4fT9+iKKCxHeAWK5QyVwM5XioaVgmDaihRd8X8lJpqVQAVSEeCsrAXzrRJZGjURToSVO5dXgEBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91da4971e9ed70fefe620993b70d88519433281a6065df01e110492ec2a8f479","last_reissued_at":"2026-07-05T11:22:35.043132Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:35.043132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.14533","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":"2026-07-05T11:22:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FruCB0y8OVtBZRk/uiOihYpGhiTasXAPJLGqhkBqWbzG4PbmXp4UmexirQ0Z2bJRKHevUoaIjDDqwd+O+TbYAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T21:54:53.901252Z"},"content_sha256":"ecfa55ecc80240687dd3c6c51fbb1d2fdbe1e67177af47da2be20e7a0ec0e8bc","schema_version":"1.0","event_id":"sha256:ecfa55ecc80240687dd3c6c51fbb1d2fdbe1e67177af47da2be20e7a0ec0e8bc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SHNES4PJ5VYP57TCBGJ3ODMIKG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ClusterChat: Multi-Feature Search for Corpus Exploration","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ashish Chouhan, Michael Gertz, Saifeldin Mandour","submitted_at":"2024-12-19T05:11:16Z","abstract_excerpt":"Exploring large-scale text corpora presents a significant challenge in biomedical, finance, and legal domains, where vast amounts of documents are continuously published. Traditional search methods, such as keyword-based search, often retrieve documents in isolation, limiting the user's ability to easily inspect corpus-wide trends and relationships. We present ClusterChat (The demo video and source code are available at: https://github.com/achouhan93/ClusterChat), an open-source system for corpus exploration that integrates cluster-based organization of documents using textual embeddings with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14533","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/2412.14533/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":"2026-07-05T11:22:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"quZfLcUBOl1xqVpeCkY9eb/YmOYnRal83ayj1eaIw9vX4bq/9dWqNDC9mTmhlirjoJzGU8lAtUKej2pNhy0aAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T21:54:53.901749Z"},"content_sha256":"76778659a1227fc982e7c9b81e636b6fc8a953edd77ea7a40a0ee101c879cf73","schema_version":"1.0","event_id":"sha256:76778659a1227fc982e7c9b81e636b6fc8a953edd77ea7a40a0ee101c879cf73"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SHNES4PJ5VYP57TCBGJ3ODMIKG/bundle.json","state_url":"https://pith.science/pith/SHNES4PJ5VYP57TCBGJ3ODMIKG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SHNES4PJ5VYP57TCBGJ3ODMIKG/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":"2026-08-15T21:54:53Z","links":{"resolver":"https://pith.science/pith/SHNES4PJ5VYP57TCBGJ3ODMIKG","bundle":"https://pith.science/pith/SHNES4PJ5VYP57TCBGJ3ODMIKG/bundle.json","state":"https://pith.science/pith/SHNES4PJ5VYP57TCBGJ3ODMIKG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SHNES4PJ5VYP57TCBGJ3ODMIKG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SHNES4PJ5VYP57TCBGJ3ODMIKG","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":"60f27e8d1ee9303e3d43d701ede0b08c716b000440014aa07b65ce286e768c06","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T05:11:16Z","title_canon_sha256":"6f9867c3c70c2b17657e6b79b177334ece50435646c4521010a699d8658715da"},"schema_version":"1.0","source":{"id":"2412.14533","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.14533","created_at":"2026-07-05T11:22:35Z"},{"alias_kind":"arxiv_version","alias_value":"2412.14533v2","created_at":"2026-07-05T11:22:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14533","created_at":"2026-07-05T11:22:35Z"},{"alias_kind":"pith_short_12","alias_value":"SHNES4PJ5VYP","created_at":"2026-07-05T11:22:35Z"},{"alias_kind":"pith_short_16","alias_value":"SHNES4PJ5VYP57TC","created_at":"2026-07-05T11:22:35Z"},{"alias_kind":"pith_short_8","alias_value":"SHNES4PJ","created_at":"2026-07-05T11:22:35Z"}],"graph_snapshots":[{"event_id":"sha256:76778659a1227fc982e7c9b81e636b6fc8a953edd77ea7a40a0ee101c879cf73","target":"graph","created_at":"2026-07-05T11:22:35Z","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/2412.14533/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Exploring large-scale text corpora presents a significant challenge in biomedical, finance, and legal domains, where vast amounts of documents are continuously published. Traditional search methods, such as keyword-based search, often retrieve documents in isolation, limiting the user's ability to easily inspect corpus-wide trends and relationships. We present ClusterChat (The demo video and source code are available at: https://github.com/achouhan93/ClusterChat), an open-source system for corpus exploration that integrates cluster-based organization of documents using textual embeddings with ","authors_text":"Ashish Chouhan, Michael Gertz, Saifeldin Mandour","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T05:11:16Z","title":"ClusterChat: Multi-Feature Search for Corpus Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14533","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:ecfa55ecc80240687dd3c6c51fbb1d2fdbe1e67177af47da2be20e7a0ec0e8bc","target":"record","created_at":"2026-07-05T11:22:35Z","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":"60f27e8d1ee9303e3d43d701ede0b08c716b000440014aa07b65ce286e768c06","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T05:11:16Z","title_canon_sha256":"6f9867c3c70c2b17657e6b79b177334ece50435646c4521010a699d8658715da"},"schema_version":"1.0","source":{"id":"2412.14533","kind":"arxiv","version":2}},"canonical_sha256":"91da4971e9ed70fefe620993b70d88519433281a6065df01e110492ec2a8f479","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"91da4971e9ed70fefe620993b70d88519433281a6065df01e110492ec2a8f479","first_computed_at":"2026-07-05T11:22:35.043132Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:22:35.043132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DQMwl8FgEDC4fT9+iKKCxHeAWK5QyVwM5XioaVgmDaihRd8X8lJpqVQAVSEeCsrAXzrRJZGjURToSVO5dXgEBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:22:35.043632Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.14533","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ecfa55ecc80240687dd3c6c51fbb1d2fdbe1e67177af47da2be20e7a0ec0e8bc","sha256:76778659a1227fc982e7c9b81e636b6fc8a953edd77ea7a40a0ee101c879cf73"],"state_sha256":"89160fd3e2ed08f4f7466747e93fb3bd2b309211eb53861eac330a994408259f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"exwTi/jQFMN+ImuDA//xANhfqEhUsQioKiKStYqNjWkDnrpoGtCdkG1qbp2yVKrUKLCShSwWR4qG8o5zE6mDAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T21:54:53.905343Z","bundle_sha256":"cfb3e9ccfda7173812ff1b115274cf27281e1f4d7b6010e1e3506886756bb3e6"}}