{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JIIDIA44OE6POISE37SXHM45B3","short_pith_number":"pith:JIIDIA44","schema_version":"1.0","canonical_sha256":"4a1034039c713cf72244dfe573b39d0ecc903d4c71a76457b883e7950e19a729","source":{"kind":"arxiv","id":"2505.09007","version":2},"attestation_state":"computed","paper":{"title":"Vendi Information Gain: An Alternative To Mutual Information For Science And Machine Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.IT"],"primary_cat":"cs.IT","authors_text":"Adji Bousso Dieng, Quan Nguyen","submitted_at":"2025-05-13T22:49:15Z","abstract_excerpt":"In his 1948 seminal paper A Mathematical Theory of Communication that birthed information theory, Claude Shannon introduced mutual information (MI), which he called \"rate of transmission\", as a way to quantify information gain (IG) and defined it as the difference between the marginal and conditional entropy of a random variable. While MI has become a standard tool in science and engineering, it has several shortcomings. First, MI is often intractable - it requires a density over samples with tractable Shannon entropy - and existing techniques for approximating it often fail, especially in hig"},"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":"2505.09007","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IT","submitted_at":"2025-05-13T22:49:15Z","cross_cats_sorted":["math.IT"],"title_canon_sha256":"dfebd853bb48b260761a2b94e6090d3c5daa4c4cdb92edc90baef21b7e1d4639","abstract_canon_sha256":"15a0087195c21c8a1fd42976ac805c5d6fb0a2ee839da28f69a78bd04d7c90bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:22.441232Z","signature_b64":"XNary/R23RW5xxw+UJeJsg+dapN3lSdo9C6q7tS+igp7Z+qTrmAmUktGPZtxvGpvquLAMG0EUn7kf56qSC3yCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a1034039c713cf72244dfe573b39d0ecc903d4c71a76457b883e7950e19a729","last_reissued_at":"2026-07-05T11:04:22.440703Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:22.440703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vendi Information Gain: An Alternative To Mutual Information For Science And Machine Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.IT"],"primary_cat":"cs.IT","authors_text":"Adji Bousso Dieng, Quan Nguyen","submitted_at":"2025-05-13T22:49:15Z","abstract_excerpt":"In his 1948 seminal paper A Mathematical Theory of Communication that birthed information theory, Claude Shannon introduced mutual information (MI), which he called \"rate of transmission\", as a way to quantify information gain (IG) and defined it as the difference between the marginal and conditional entropy of a random variable. While MI has become a standard tool in science and engineering, it has several shortcomings. First, MI is often intractable - it requires a density over samples with tractable Shannon entropy - and existing techniques for approximating it often fail, especially in hig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.09007","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/2505.09007/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":"2505.09007","created_at":"2026-07-05T11:04:22.440764+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.09007v2","created_at":"2026-07-05T11:04:22.440764+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.09007","created_at":"2026-07-05T11:04:22.440764+00:00"},{"alias_kind":"pith_short_12","alias_value":"JIIDIA44OE6P","created_at":"2026-07-05T11:04:22.440764+00:00"},{"alias_kind":"pith_short_16","alias_value":"JIIDIA44OE6POISE","created_at":"2026-07-05T11:04:22.440764+00:00"},{"alias_kind":"pith_short_8","alias_value":"JIIDIA44","created_at":"2026-07-05T11:04:22.440764+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29448","citing_title":"How Much Is a Dataset Worth? Scaling Laws, the Vendi Score, and Matrix Spectral Functions","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JIIDIA44OE6POISE37SXHM45B3","json":"https://pith.science/pith/JIIDIA44OE6POISE37SXHM45B3.json","graph_json":"https://pith.science/api/pith-number/JIIDIA44OE6POISE37SXHM45B3/graph.json","events_json":"https://pith.science/api/pith-number/JIIDIA44OE6POISE37SXHM45B3/events.json","paper":"https://pith.science/paper/JIIDIA44"},"agent_actions":{"view_html":"https://pith.science/pith/JIIDIA44OE6POISE37SXHM45B3","download_json":"https://pith.science/pith/JIIDIA44OE6POISE37SXHM45B3.json","view_paper":"https://pith.science/paper/JIIDIA44","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.09007&json=true","fetch_graph":"https://pith.science/api/pith-number/JIIDIA44OE6POISE37SXHM45B3/graph.json","fetch_events":"https://pith.science/api/pith-number/JIIDIA44OE6POISE37SXHM45B3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JIIDIA44OE6POISE37SXHM45B3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JIIDIA44OE6POISE37SXHM45B3/action/storage_attestation","attest_author":"https://pith.science/pith/JIIDIA44OE6POISE37SXHM45B3/action/author_attestation","sign_citation":"https://pith.science/pith/JIIDIA44OE6POISE37SXHM45B3/action/citation_signature","submit_replication":"https://pith.science/pith/JIIDIA44OE6POISE37SXHM45B3/action/replication_record"}},"created_at":"2026-07-05T11:04:22.440764+00:00","updated_at":"2026-07-05T11:04:22.440764+00:00"}