{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VENMGDT5Q7D4N2LFPYJAPEREN2","short_pith_number":"pith:VENMGDT5","canonical_record":{"source":{"id":"2408.07003","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-13T16:07:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"35ba581836cbf09a83df15085fb80bb7e7fcd1cd4f9988dbf85f5b5f56bd1299","abstract_canon_sha256":"c1d63acd60be88fef01673c37b431e7a99c599ca1e524b2b302dd3101fc9e97a"},"schema_version":"1.0"},"canonical_sha256":"a91ac30e7d87c7c6e9657e120792246ea0e59227b9413335a01c2ed1a0fd7bd3","source":{"kind":"arxiv","id":"2408.07003","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.07003","created_at":"2026-06-24T01:14:55Z"},{"alias_kind":"arxiv_version","alias_value":"2408.07003v1","created_at":"2026-06-24T01:14:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.07003","created_at":"2026-06-24T01:14:55Z"},{"alias_kind":"pith_short_12","alias_value":"VENMGDT5Q7D4","created_at":"2026-06-24T01:14:55Z"},{"alias_kind":"pith_short_16","alias_value":"VENMGDT5Q7D4N2LF","created_at":"2026-06-24T01:14:55Z"},{"alias_kind":"pith_short_8","alias_value":"VENMGDT5","created_at":"2026-06-24T01:14:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VENMGDT5Q7D4N2LFPYJAPEREN2","target":"record","payload":{"canonical_record":{"source":{"id":"2408.07003","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-13T16:07:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"35ba581836cbf09a83df15085fb80bb7e7fcd1cd4f9988dbf85f5b5f56bd1299","abstract_canon_sha256":"c1d63acd60be88fef01673c37b431e7a99c599ca1e524b2b302dd3101fc9e97a"},"schema_version":"1.0"},"canonical_sha256":"a91ac30e7d87c7c6e9657e120792246ea0e59227b9413335a01c2ed1a0fd7bd3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:14:55.691335Z","signature_b64":"uS4VkmmGtjJIQ+AfAAK5vlg7L1AenZJrT+qlghgJMKiv9FV7WoAcDBWIGXB4ydZPBSx1Tdbi0GKQ3WbVDWvLBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a91ac30e7d87c7c6e9657e120792246ea0e59227b9413335a01c2ed1a0fd7bd3","last_reissued_at":"2026-06-24T01:14:55.690771Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:14:55.690771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.07003","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":"2026-06-24T01:14:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4Z3eOSlZCwhJ0TqXZ0FFXE7qXH0LovEUyyzeSnpc6rkZzKsH9EOOp9OKoHXku4WBDbu29wu6NmTTlGNTg1xrBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T08:11:50.229263Z"},"content_sha256":"b5eed763ffe9fe867988d9545481f86acdb88660f73e977f54cef0d292e7c870","schema_version":"1.0","event_id":"sha256:b5eed763ffe9fe867988d9545481f86acdb88660f73e977f54cef0d292e7c870"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VENMGDT5Q7D4N2LFPYJAPEREN2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generative AI for automatic topic labelling","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Carolina Pradier, Diego Kozlowski, Pierre Benz","submitted_at":"2024-08-13T16:07:16Z","abstract_excerpt":"Topic Modeling has become a prominent tool for the study of scientific fields, as they allow for a large scale interpretation of research trends. Nevertheless, the output of these models is structured as a list of keywords which requires a manual interpretation for the labelling. This paper proposes to assess the reliability of three LLMs, namely flan, GPT-4o, and GPT-4 mini for topic labelling. Drawing on previous research leveraging BERTopic, we generate topics from a dataset of all the scientific articles (n=34,797) authored by all biology professors in Switzerland (n=465) between 2008 and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.07003","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/2408.07003/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":"2026-06-24T01:14:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2hPAiTd/31e0cgNFX2ULmoJ/UC6xhek+B2syJzyasCFgdpBPwmMiIhzZg1J0pZdTY1n2DKv9yUen/1tdO/2CDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T08:11:50.229665Z"},"content_sha256":"fcbbbcaa4d71c1561db4021c5b94b098f13192c12c6f3e3fa1f3eac70664a9d9","schema_version":"1.0","event_id":"sha256:fcbbbcaa4d71c1561db4021c5b94b098f13192c12c6f3e3fa1f3eac70664a9d9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VENMGDT5Q7D4N2LFPYJAPEREN2/bundle.json","state_url":"https://pith.science/pith/VENMGDT5Q7D4N2LFPYJAPEREN2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VENMGDT5Q7D4N2LFPYJAPEREN2/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":"2026-06-27T08:11:50Z","links":{"resolver":"https://pith.science/pith/VENMGDT5Q7D4N2LFPYJAPEREN2","bundle":"https://pith.science/pith/VENMGDT5Q7D4N2LFPYJAPEREN2/bundle.json","state":"https://pith.science/pith/VENMGDT5Q7D4N2LFPYJAPEREN2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VENMGDT5Q7D4N2LFPYJAPEREN2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VENMGDT5Q7D4N2LFPYJAPEREN2","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":"c1d63acd60be88fef01673c37b431e7a99c599ca1e524b2b302dd3101fc9e97a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-13T16:07:16Z","title_canon_sha256":"35ba581836cbf09a83df15085fb80bb7e7fcd1cd4f9988dbf85f5b5f56bd1299"},"schema_version":"1.0","source":{"id":"2408.07003","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.07003","created_at":"2026-06-24T01:14:55Z"},{"alias_kind":"arxiv_version","alias_value":"2408.07003v1","created_at":"2026-06-24T01:14:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.07003","created_at":"2026-06-24T01:14:55Z"},{"alias_kind":"pith_short_12","alias_value":"VENMGDT5Q7D4","created_at":"2026-06-24T01:14:55Z"},{"alias_kind":"pith_short_16","alias_value":"VENMGDT5Q7D4N2LF","created_at":"2026-06-24T01:14:55Z"},{"alias_kind":"pith_short_8","alias_value":"VENMGDT5","created_at":"2026-06-24T01:14:55Z"}],"graph_snapshots":[{"event_id":"sha256:fcbbbcaa4d71c1561db4021c5b94b098f13192c12c6f3e3fa1f3eac70664a9d9","target":"graph","created_at":"2026-06-24T01:14:55Z","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/2408.07003/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Topic Modeling has become a prominent tool for the study of scientific fields, as they allow for a large scale interpretation of research trends. Nevertheless, the output of these models is structured as a list of keywords which requires a manual interpretation for the labelling. This paper proposes to assess the reliability of three LLMs, namely flan, GPT-4o, and GPT-4 mini for topic labelling. Drawing on previous research leveraging BERTopic, we generate topics from a dataset of all the scientific articles (n=34,797) authored by all biology professors in Switzerland (n=465) between 2008 and ","authors_text":"Carolina Pradier, Diego Kozlowski, Pierre Benz","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-13T16:07:16Z","title":"Generative AI for automatic topic labelling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.07003","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:b5eed763ffe9fe867988d9545481f86acdb88660f73e977f54cef0d292e7c870","target":"record","created_at":"2026-06-24T01:14:55Z","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":"c1d63acd60be88fef01673c37b431e7a99c599ca1e524b2b302dd3101fc9e97a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-13T16:07:16Z","title_canon_sha256":"35ba581836cbf09a83df15085fb80bb7e7fcd1cd4f9988dbf85f5b5f56bd1299"},"schema_version":"1.0","source":{"id":"2408.07003","kind":"arxiv","version":1}},"canonical_sha256":"a91ac30e7d87c7c6e9657e120792246ea0e59227b9413335a01c2ed1a0fd7bd3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a91ac30e7d87c7c6e9657e120792246ea0e59227b9413335a01c2ed1a0fd7bd3","first_computed_at":"2026-06-24T01:14:55.690771Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T01:14:55.690771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uS4VkmmGtjJIQ+AfAAK5vlg7L1AenZJrT+qlghgJMKiv9FV7WoAcDBWIGXB4ydZPBSx1Tdbi0GKQ3WbVDWvLBw==","signature_status":"signed_v1","signed_at":"2026-06-24T01:14:55.691335Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.07003","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5eed763ffe9fe867988d9545481f86acdb88660f73e977f54cef0d292e7c870","sha256:fcbbbcaa4d71c1561db4021c5b94b098f13192c12c6f3e3fa1f3eac70664a9d9"],"state_sha256":"f927cbe2e43b662638b7b4bceb77902cecb61dc7a2404f6b82cfb27affdecbee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q8VxJzxs4GRF+HuNPVPx6E/FVFOfvqdj5lE4KU1KFkGJUzfGUANjn+pP0HnlO2KiC+3BadWdrPg2isURlh1zDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T08:11:50.231623Z","bundle_sha256":"18005adb8705ecb5cc1ca3290acb69228802495a1800070f182bef7cd7d98b9f"}}