{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3ZFI6LZMFKD644TSB6VIL2SDPD","short_pith_number":"pith:3ZFI6LZM","schema_version":"1.0","canonical_sha256":"de4a8f2f2c2a87ee72720faa85ea4378fb36f8d6dc46b92053cb6bb7b5129f40","source":{"kind":"arxiv","id":"2506.00514","version":1},"attestation_state":"computed","paper":{"title":"Evaluating the Evaluation of Diversity in Commonsense Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bei Peng, Danushka Bollegala, Tianhui Zhang","submitted_at":"2025-05-31T11:18:26Z","abstract_excerpt":"In commonsense generation, given a set of input concepts, a model must generate a response that is not only commonsense bearing, but also capturing multiple diverse viewpoints. Numerous evaluation metrics based on form- and content-level overlap have been proposed in prior work for evaluating the diversity of a commonsense generation model. However, it remains unclear as to which metrics are best suited for evaluating the diversity in commonsense generation. To address this gap, we conduct a systematic meta-evaluation of diversity metrics for commonsense generation. We find that form-based div"},"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":"2506.00514","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-31T11:18:26Z","cross_cats_sorted":[],"title_canon_sha256":"40be912bdf3da55378fd621bdd131779e79d33308d0eaafd32ec06dc557f191c","abstract_canon_sha256":"d70c6d0b7870f89fa092c51838972bb7627ec2d204458599529d29688b5c31e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:36.212851Z","signature_b64":"Yt6/K4F5vUwXmX3S4JO7p8GT0hjFhirnzEItQWT2hSGfC/mYyXCe1l3r//adcRMhs4fIYTdrm9jCKqvSODB7CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de4a8f2f2c2a87ee72720faa85ea4378fb36f8d6dc46b92053cb6bb7b5129f40","last_reissued_at":"2026-07-05T11:13:36.212360Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:36.212360Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating the Evaluation of Diversity in Commonsense Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bei Peng, Danushka Bollegala, Tianhui Zhang","submitted_at":"2025-05-31T11:18:26Z","abstract_excerpt":"In commonsense generation, given a set of input concepts, a model must generate a response that is not only commonsense bearing, but also capturing multiple diverse viewpoints. Numerous evaluation metrics based on form- and content-level overlap have been proposed in prior work for evaluating the diversity of a commonsense generation model. However, it remains unclear as to which metrics are best suited for evaluating the diversity in commonsense generation. To address this gap, we conduct a systematic meta-evaluation of diversity metrics for commonsense generation. We find that form-based div"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00514","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/2506.00514/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":"2506.00514","created_at":"2026-07-05T11:13:36.212417+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.00514v1","created_at":"2026-07-05T11:13:36.212417+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00514","created_at":"2026-07-05T11:13:36.212417+00:00"},{"alias_kind":"pith_short_12","alias_value":"3ZFI6LZMFKD6","created_at":"2026-07-05T11:13:36.212417+00:00"},{"alias_kind":"pith_short_16","alias_value":"3ZFI6LZMFKD644TS","created_at":"2026-07-05T11:13:36.212417+00:00"},{"alias_kind":"pith_short_8","alias_value":"3ZFI6LZM","created_at":"2026-07-05T11:13:36.212417+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01811","citing_title":"\"I've Seen How This Goes\": Characterizing Diversity via Progressive Conditional Surprise","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3ZFI6LZMFKD644TSB6VIL2SDPD","json":"https://pith.science/pith/3ZFI6LZMFKD644TSB6VIL2SDPD.json","graph_json":"https://pith.science/api/pith-number/3ZFI6LZMFKD644TSB6VIL2SDPD/graph.json","events_json":"https://pith.science/api/pith-number/3ZFI6LZMFKD644TSB6VIL2SDPD/events.json","paper":"https://pith.science/paper/3ZFI6LZM"},"agent_actions":{"view_html":"https://pith.science/pith/3ZFI6LZMFKD644TSB6VIL2SDPD","download_json":"https://pith.science/pith/3ZFI6LZMFKD644TSB6VIL2SDPD.json","view_paper":"https://pith.science/paper/3ZFI6LZM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.00514&json=true","fetch_graph":"https://pith.science/api/pith-number/3ZFI6LZMFKD644TSB6VIL2SDPD/graph.json","fetch_events":"https://pith.science/api/pith-number/3ZFI6LZMFKD644TSB6VIL2SDPD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3ZFI6LZMFKD644TSB6VIL2SDPD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3ZFI6LZMFKD644TSB6VIL2SDPD/action/storage_attestation","attest_author":"https://pith.science/pith/3ZFI6LZMFKD644TSB6VIL2SDPD/action/author_attestation","sign_citation":"https://pith.science/pith/3ZFI6LZMFKD644TSB6VIL2SDPD/action/citation_signature","submit_replication":"https://pith.science/pith/3ZFI6LZMFKD644TSB6VIL2SDPD/action/replication_record"}},"created_at":"2026-07-05T11:13:36.212417+00:00","updated_at":"2026-07-05T11:13:36.212417+00:00"}