{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CU6IK7HPZ54BGGJFFIYYPV3ZE2","short_pith_number":"pith:CU6IK7HP","schema_version":"1.0","canonical_sha256":"153c857cefcf781319252a3187d7792695850c7fd153a0c8500b2fca92164482","source":{"kind":"arxiv","id":"2506.19992","version":2},"attestation_state":"computed","paper":{"title":"HERCULES: Hierarchical Embedding-based Recursive Clustering Using LLMs for Efficient Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bernadett Aradi, Gabor Petnehazi","submitted_at":"2025-06-24T20:22:00Z","abstract_excerpt":"The explosive growth of complex datasets across various modalities necessitates advanced analytical tools that not only group data effectively but also provide human-understandable insights into the discovered structures. We introduce HERCULES (Hierarchical Embedding-based Recursive Clustering Using LLMs for Efficient Summarization), a novel algorithm and Python package designed for hierarchical k-means clustering of diverse data types, including text, images, and numeric data (processed one modality per run). HERCULES constructs a cluster hierarchy by recursively applying k-means clustering, "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.19992","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-24T20:22:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f90ba0313a30eb351dd6dfd7290e73c2b8f3a483f82e7185ee66a43abe86361d","abstract_canon_sha256":"56d6e7ac92228af18f636f4f23fb1cb98296759bbe4b535eed8050f23efa1930"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:03:49.327596Z","signature_b64":"LneDZnlc+gCXzie/c6S+k8wub0Z3EZwgLeVEViJqRmPQLSYcwjhUQHRnm1SGTjoi5htbDCZIc8f12b2s+ddgAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"153c857cefcf781319252a3187d7792695850c7fd153a0c8500b2fca92164482","last_reissued_at":"2026-07-05T12:03:49.327065Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:03:49.327065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HERCULES: Hierarchical Embedding-based Recursive Clustering Using LLMs for Efficient Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bernadett Aradi, Gabor Petnehazi","submitted_at":"2025-06-24T20:22:00Z","abstract_excerpt":"The explosive growth of complex datasets across various modalities necessitates advanced analytical tools that not only group data effectively but also provide human-understandable insights into the discovered structures. We introduce HERCULES (Hierarchical Embedding-based Recursive Clustering Using LLMs for Efficient Summarization), a novel algorithm and Python package designed for hierarchical k-means clustering of diverse data types, including text, images, and numeric data (processed one modality per run). HERCULES constructs a cluster hierarchy by recursively applying k-means clustering, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19992","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/2506.19992/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.19992","created_at":"2026-07-05T12:03:49.327128+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.19992v2","created_at":"2026-07-05T12:03:49.327128+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19992","created_at":"2026-07-05T12:03:49.327128+00:00"},{"alias_kind":"pith_short_12","alias_value":"CU6IK7HPZ54B","created_at":"2026-07-05T12:03:49.327128+00:00"},{"alias_kind":"pith_short_16","alias_value":"CU6IK7HPZ54BGGJF","created_at":"2026-07-05T12:03:49.327128+00:00"},{"alias_kind":"pith_short_8","alias_value":"CU6IK7HP","created_at":"2026-07-05T12:03:49.327128+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.15424","citing_title":"LLM-MemCluster: Empowering Large Language Models with Dynamic Memory for Text Clustering","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CU6IK7HPZ54BGGJFFIYYPV3ZE2","json":"https://pith.science/pith/CU6IK7HPZ54BGGJFFIYYPV3ZE2.json","graph_json":"https://pith.science/api/pith-number/CU6IK7HPZ54BGGJFFIYYPV3ZE2/graph.json","events_json":"https://pith.science/api/pith-number/CU6IK7HPZ54BGGJFFIYYPV3ZE2/events.json","paper":"https://pith.science/paper/CU6IK7HP"},"agent_actions":{"view_html":"https://pith.science/pith/CU6IK7HPZ54BGGJFFIYYPV3ZE2","download_json":"https://pith.science/pith/CU6IK7HPZ54BGGJFFIYYPV3ZE2.json","view_paper":"https://pith.science/paper/CU6IK7HP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.19992&json=true","fetch_graph":"https://pith.science/api/pith-number/CU6IK7HPZ54BGGJFFIYYPV3ZE2/graph.json","fetch_events":"https://pith.science/api/pith-number/CU6IK7HPZ54BGGJFFIYYPV3ZE2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CU6IK7HPZ54BGGJFFIYYPV3ZE2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CU6IK7HPZ54BGGJFFIYYPV3ZE2/action/storage_attestation","attest_author":"https://pith.science/pith/CU6IK7HPZ54BGGJFFIYYPV3ZE2/action/author_attestation","sign_citation":"https://pith.science/pith/CU6IK7HPZ54BGGJFFIYYPV3ZE2/action/citation_signature","submit_replication":"https://pith.science/pith/CU6IK7HPZ54BGGJFFIYYPV3ZE2/action/replication_record"}},"created_at":"2026-07-05T12:03:49.327128+00:00","updated_at":"2026-07-05T12:03:49.327128+00:00"}