{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CU6IK7HPZ54BGGJFFIYYPV3ZE2","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":"56d6e7ac92228af18f636f4f23fb1cb98296759bbe4b535eed8050f23efa1930","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-24T20:22:00Z","title_canon_sha256":"f90ba0313a30eb351dd6dfd7290e73c2b8f3a483f82e7185ee66a43abe86361d"},"schema_version":"1.0","source":{"id":"2506.19992","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.19992","created_at":"2026-07-05T12:03:49Z"},{"alias_kind":"arxiv_version","alias_value":"2506.19992v2","created_at":"2026-07-05T12:03:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19992","created_at":"2026-07-05T12:03:49Z"},{"alias_kind":"pith_short_12","alias_value":"CU6IK7HPZ54B","created_at":"2026-07-05T12:03:49Z"},{"alias_kind":"pith_short_16","alias_value":"CU6IK7HPZ54BGGJF","created_at":"2026-07-05T12:03:49Z"},{"alias_kind":"pith_short_8","alias_value":"CU6IK7HP","created_at":"2026-07-05T12:03:49Z"}],"graph_snapshots":[{"event_id":"sha256:2434cd1ef1a36960980d3236a5cfda2ad186f5b61c167c38dcd1f8d8c8006c6f","target":"graph","created_at":"2026-07-05T12:03:49Z","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/2506.19992/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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, ","authors_text":"Bernadett Aradi, Gabor Petnehazi","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-24T20:22:00Z","title":"HERCULES: Hierarchical Embedding-based Recursive Clustering Using LLMs for Efficient Summarization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19992","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:b633a5ddfdc974186c3185dd19886a80f0632b2d4f0dc79ee5854b3b625bbcfe","target":"record","created_at":"2026-07-05T12:03:49Z","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":"56d6e7ac92228af18f636f4f23fb1cb98296759bbe4b535eed8050f23efa1930","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-24T20:22:00Z","title_canon_sha256":"f90ba0313a30eb351dd6dfd7290e73c2b8f3a483f82e7185ee66a43abe86361d"},"schema_version":"1.0","source":{"id":"2506.19992","kind":"arxiv","version":2}},"canonical_sha256":"153c857cefcf781319252a3187d7792695850c7fd153a0c8500b2fca92164482","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"153c857cefcf781319252a3187d7792695850c7fd153a0c8500b2fca92164482","first_computed_at":"2026-07-05T12:03:49.327065Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:03:49.327065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LneDZnlc+gCXzie/c6S+k8wub0Z3EZwgLeVEViJqRmPQLSYcwjhUQHRnm1SGTjoi5htbDCZIc8f12b2s+ddgAw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:03:49.327596Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.19992","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b633a5ddfdc974186c3185dd19886a80f0632b2d4f0dc79ee5854b3b625bbcfe","sha256:2434cd1ef1a36960980d3236a5cfda2ad186f5b61c167c38dcd1f8d8c8006c6f"],"state_sha256":"a405442132f8c68bd9bfe895fa9fad85afba0e81608a290146d281fb61e17654"}