{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:D2TLCFQLRPXM7VBJJHVHY6PU6W","short_pith_number":"pith:D2TLCFQL","schema_version":"1.0","canonical_sha256":"1ea6b1160b8beecfd42949ea7c79f4f599bb99a9a63559bd9725752a0b96aa0d","source":{"kind":"arxiv","id":"2511.21223","version":2},"attestation_state":"computed","paper":{"title":"Maxitive Donsker-Varadhan Formulation for Possibilistic Variational Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Badr-Eddine Ch\\'erief-Abdellatif, Jasraj Singh, Jeremie Houssineau, Shelvia Wongso","submitted_at":"2025-11-26T09:53:28Z","abstract_excerpt":"Variational inference (VI) is a cornerstone of modern Bayesian learning, enabling approximate inference in complex models. However, its formulation depends on expectations and divergences defined through high-dimensional integrals, often rendering analytical treatment impossible and necessitating heavy reliance on approximations. Possibility theory, an imprecise probability framework, allows us to directly model epistemic uncertainty instead of relying on a subjective interpretation of probabilities. While this framework provides robustness and interpretability under sparse or imprecise inform"},"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":"2511.21223","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-11-26T09:53:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"21f030bfac009e65667c1de3a6d631ac330dd88897de772ecf7daabad14585e8","abstract_canon_sha256":"6cdf3102635368f28d6f75bf6525c3c422798e105cad93fcb74279506b4f1b41"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:05:12.145039Z","signature_b64":"D2pi/rPMc1pCr3mSecfldw2d3NkVasmiwibeZ48ReYpybSMH6jIsMCt+5H4xCpwQNMaLuOcGDQQzObeXk33gBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ea6b1160b8beecfd42949ea7c79f4f599bb99a9a63559bd9725752a0b96aa0d","last_reissued_at":"2026-05-21T01:05:12.144058Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:05:12.144058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Maxitive Donsker-Varadhan Formulation for Possibilistic Variational Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Badr-Eddine Ch\\'erief-Abdellatif, Jasraj Singh, Jeremie Houssineau, Shelvia Wongso","submitted_at":"2025-11-26T09:53:28Z","abstract_excerpt":"Variational inference (VI) is a cornerstone of modern Bayesian learning, enabling approximate inference in complex models. However, its formulation depends on expectations and divergences defined through high-dimensional integrals, often rendering analytical treatment impossible and necessitating heavy reliance on approximations. Possibility theory, an imprecise probability framework, allows us to directly model epistemic uncertainty instead of relying on a subjective interpretation of probabilities. While this framework provides robustness and interpretability under sparse or imprecise inform"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.21223","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/2511.21223/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":"2511.21223","created_at":"2026-05-21T01:05:12.144207+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.21223v2","created_at":"2026-05-21T01:05:12.144207+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.21223","created_at":"2026-05-21T01:05:12.144207+00:00"},{"alias_kind":"pith_short_12","alias_value":"D2TLCFQLRPXM","created_at":"2026-05-21T01:05:12.144207+00:00"},{"alias_kind":"pith_short_16","alias_value":"D2TLCFQLRPXM7VBJ","created_at":"2026-05-21T01:05:12.144207+00:00"},{"alias_kind":"pith_short_8","alias_value":"D2TLCFQL","created_at":"2026-05-21T01:05:12.144207+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.00600","citing_title":"Possibilistic Predictive Uncertainty for Deep Learning","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D2TLCFQLRPXM7VBJJHVHY6PU6W","json":"https://pith.science/pith/D2TLCFQLRPXM7VBJJHVHY6PU6W.json","graph_json":"https://pith.science/api/pith-number/D2TLCFQLRPXM7VBJJHVHY6PU6W/graph.json","events_json":"https://pith.science/api/pith-number/D2TLCFQLRPXM7VBJJHVHY6PU6W/events.json","paper":"https://pith.science/paper/D2TLCFQL"},"agent_actions":{"view_html":"https://pith.science/pith/D2TLCFQLRPXM7VBJJHVHY6PU6W","download_json":"https://pith.science/pith/D2TLCFQLRPXM7VBJJHVHY6PU6W.json","view_paper":"https://pith.science/paper/D2TLCFQL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.21223&json=true","fetch_graph":"https://pith.science/api/pith-number/D2TLCFQLRPXM7VBJJHVHY6PU6W/graph.json","fetch_events":"https://pith.science/api/pith-number/D2TLCFQLRPXM7VBJJHVHY6PU6W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D2TLCFQLRPXM7VBJJHVHY6PU6W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D2TLCFQLRPXM7VBJJHVHY6PU6W/action/storage_attestation","attest_author":"https://pith.science/pith/D2TLCFQLRPXM7VBJJHVHY6PU6W/action/author_attestation","sign_citation":"https://pith.science/pith/D2TLCFQLRPXM7VBJJHVHY6PU6W/action/citation_signature","submit_replication":"https://pith.science/pith/D2TLCFQLRPXM7VBJJHVHY6PU6W/action/replication_record"}},"created_at":"2026-05-21T01:05:12.144207+00:00","updated_at":"2026-05-21T01:05:12.144207+00:00"}