{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FG5XZYZRD7LCTDHF2USAFRLQCZ","short_pith_number":"pith:FG5XZYZR","canonical_record":{"source":{"id":"2404.16442","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-25T09:20:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4decf1930afb215bffe30df148fbdc4d502374b7d4766f57cf8785ceaec1f0b3","abstract_canon_sha256":"a59690c9fc7f5172822b798fd84b5fa8aaf738dfc53701b6e7a661cb1e052a7f"},"schema_version":"1.0"},"canonical_sha256":"29bb7ce3311fd6298ce5d52402c570166f79ab3293a2bbd1bb531156aa9d599b","source":{"kind":"arxiv","id":"2404.16442","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.16442","created_at":"2026-07-05T08:12:07Z"},{"alias_kind":"arxiv_version","alias_value":"2404.16442v1","created_at":"2026-07-05T08:12:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.16442","created_at":"2026-07-05T08:12:07Z"},{"alias_kind":"pith_short_12","alias_value":"FG5XZYZRD7LC","created_at":"2026-07-05T08:12:07Z"},{"alias_kind":"pith_short_16","alias_value":"FG5XZYZRD7LCTDHF","created_at":"2026-07-05T08:12:07Z"},{"alias_kind":"pith_short_8","alias_value":"FG5XZYZR","created_at":"2026-07-05T08:12:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FG5XZYZRD7LCTDHF2USAFRLQCZ","target":"record","payload":{"canonical_record":{"source":{"id":"2404.16442","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-25T09:20:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4decf1930afb215bffe30df148fbdc4d502374b7d4766f57cf8785ceaec1f0b3","abstract_canon_sha256":"a59690c9fc7f5172822b798fd84b5fa8aaf738dfc53701b6e7a661cb1e052a7f"},"schema_version":"1.0"},"canonical_sha256":"29bb7ce3311fd6298ce5d52402c570166f79ab3293a2bbd1bb531156aa9d599b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:12:07.057105Z","signature_b64":"zUK5c/+l9wGtEIr4jW4oB77J0wnYAgpeJOUF3JNeG0ilL6sR1kOR6XP61RykuGZiAu8xNVMGd6Ogmoo3NFReAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29bb7ce3311fd6298ce5d52402c570166f79ab3293a2bbd1bb531156aa9d599b","last_reissued_at":"2026-07-05T08:12:07.056616Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:12:07.056616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.16442","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":"2026-07-05T08:12:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o7RigZ+tKxuNh2lxG2Fu7smlmaEHX9C8EJyWbrC6o//tjiXukaRTyGggQCjKqcUIwoFMJCC92ru7sB6Oc0g2Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T08:49:40.142174Z"},"content_sha256":"364401bbf7f454362f5d64ca2079fd1bc8b7faa07f5a3ea898aa5b5fb85a266c","schema_version":"1.0","event_id":"sha256:364401bbf7f454362f5d64ca2079fd1bc8b7faa07f5a3ea898aa5b5fb85a266c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FG5XZYZRD7LCTDHF2USAFRLQCZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Contextual Categorization Enhancement through LLMs Latent-Space","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anas Safi, Andreas Fischer, Zineddine Bettouche","submitted_at":"2024-04-25T09:20:51Z","abstract_excerpt":"Managing the semantic quality of the categorization in large textual datasets, such as Wikipedia, presents significant challenges in terms of complexity and cost. In this paper, we propose leveraging transformer models to distill semantic information from texts in the Wikipedia dataset and its associated categories into a latent space. We then explore different approaches based on these encodings to assess and enhance the semantic identity of the categories. Our graphical approach is powered by Convex Hull, while we utilize Hierarchical Navigable Small Worlds (HNSWs) for the hierarchical appro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.16442","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/2404.16442/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":"2026-07-05T08:12:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8+7GqsLZU3ix5nxzG6e6VpJfcMN0mA9dz9aZR9jX/4OjIyNf+WhdVxq+YAGisE/ZIdI2WvNzedpzPKfS8ERlCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T08:49:40.143055Z"},"content_sha256":"027fca8e23ad3287586e071d6faec5252b9a8be61c9c0415106b319d633cf44a","schema_version":"1.0","event_id":"sha256:027fca8e23ad3287586e071d6faec5252b9a8be61c9c0415106b319d633cf44a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FG5XZYZRD7LCTDHF2USAFRLQCZ/bundle.json","state_url":"https://pith.science/pith/FG5XZYZRD7LCTDHF2USAFRLQCZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FG5XZYZRD7LCTDHF2USAFRLQCZ/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":"2026-08-11T08:49:40Z","links":{"resolver":"https://pith.science/pith/FG5XZYZRD7LCTDHF2USAFRLQCZ","bundle":"https://pith.science/pith/FG5XZYZRD7LCTDHF2USAFRLQCZ/bundle.json","state":"https://pith.science/pith/FG5XZYZRD7LCTDHF2USAFRLQCZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FG5XZYZRD7LCTDHF2USAFRLQCZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FG5XZYZRD7LCTDHF2USAFRLQCZ","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":"a59690c9fc7f5172822b798fd84b5fa8aaf738dfc53701b6e7a661cb1e052a7f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-25T09:20:51Z","title_canon_sha256":"4decf1930afb215bffe30df148fbdc4d502374b7d4766f57cf8785ceaec1f0b3"},"schema_version":"1.0","source":{"id":"2404.16442","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.16442","created_at":"2026-07-05T08:12:07Z"},{"alias_kind":"arxiv_version","alias_value":"2404.16442v1","created_at":"2026-07-05T08:12:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.16442","created_at":"2026-07-05T08:12:07Z"},{"alias_kind":"pith_short_12","alias_value":"FG5XZYZRD7LC","created_at":"2026-07-05T08:12:07Z"},{"alias_kind":"pith_short_16","alias_value":"FG5XZYZRD7LCTDHF","created_at":"2026-07-05T08:12:07Z"},{"alias_kind":"pith_short_8","alias_value":"FG5XZYZR","created_at":"2026-07-05T08:12:07Z"}],"graph_snapshots":[{"event_id":"sha256:027fca8e23ad3287586e071d6faec5252b9a8be61c9c0415106b319d633cf44a","target":"graph","created_at":"2026-07-05T08:12:07Z","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/2404.16442/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Managing the semantic quality of the categorization in large textual datasets, such as Wikipedia, presents significant challenges in terms of complexity and cost. In this paper, we propose leveraging transformer models to distill semantic information from texts in the Wikipedia dataset and its associated categories into a latent space. We then explore different approaches based on these encodings to assess and enhance the semantic identity of the categories. Our graphical approach is powered by Convex Hull, while we utilize Hierarchical Navigable Small Worlds (HNSWs) for the hierarchical appro","authors_text":"Anas Safi, Andreas Fischer, Zineddine Bettouche","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-25T09:20:51Z","title":"Contextual Categorization Enhancement through LLMs Latent-Space"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.16442","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":"sha256:364401bbf7f454362f5d64ca2079fd1bc8b7faa07f5a3ea898aa5b5fb85a266c","target":"record","created_at":"2026-07-05T08:12:07Z","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":"a59690c9fc7f5172822b798fd84b5fa8aaf738dfc53701b6e7a661cb1e052a7f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-25T09:20:51Z","title_canon_sha256":"4decf1930afb215bffe30df148fbdc4d502374b7d4766f57cf8785ceaec1f0b3"},"schema_version":"1.0","source":{"id":"2404.16442","kind":"arxiv","version":1}},"canonical_sha256":"29bb7ce3311fd6298ce5d52402c570166f79ab3293a2bbd1bb531156aa9d599b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"29bb7ce3311fd6298ce5d52402c570166f79ab3293a2bbd1bb531156aa9d599b","first_computed_at":"2026-07-05T08:12:07.056616Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:12:07.056616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zUK5c/+l9wGtEIr4jW4oB77J0wnYAgpeJOUF3JNeG0ilL6sR1kOR6XP61RykuGZiAu8xNVMGd6Ogmoo3NFReAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:12:07.057105Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.16442","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:364401bbf7f454362f5d64ca2079fd1bc8b7faa07f5a3ea898aa5b5fb85a266c","sha256:027fca8e23ad3287586e071d6faec5252b9a8be61c9c0415106b319d633cf44a"],"state_sha256":"5de11883559679c9c984ca65073f1f2c606eb1c25e18d2a763d68b421d4eedc9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qH9GgceK/wU5PT5iaHaU3tV/aat490S5ruvQJd2+M747wdCmTITHJ8yMqymaUK9ij3BS1SQ/kgnM6tPnRZLPAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T08:49:40.148327Z","bundle_sha256":"3f3b8331916541f885a1002016914ce60310b0f1ebfbb1483511f1fb482bb89a"}}