{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:T6XEL2WTSBDY67RYNVU4G5N2DO","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":"d4976aefeb262f5e472946b53607a1234cf48d2e6cb2caedd6c05be1b7c61fc9","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-01T12:14:01Z","title_canon_sha256":"b190207710f69394955f9d4c4d4a1f46d9456e1342bdbb7aebfd4a522dfc787d"},"schema_version":"1.0","source":{"id":"2605.00600","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.00600","created_at":"2026-06-02T02:04:53Z"},{"alias_kind":"arxiv_version","alias_value":"2605.00600v2","created_at":"2026-06-02T02:04:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.00600","created_at":"2026-06-02T02:04:53Z"},{"alias_kind":"pith_short_12","alias_value":"T6XEL2WTSBDY","created_at":"2026-06-02T02:04:53Z"},{"alias_kind":"pith_short_16","alias_value":"T6XEL2WTSBDY67RY","created_at":"2026-06-02T02:04:53Z"},{"alias_kind":"pith_short_8","alias_value":"T6XEL2WT","created_at":"2026-06-02T02:04:53Z"}],"graph_snapshots":[{"event_id":"sha256:bd5a2c9e3fa9e107eb195654d89dbbd5b67affa608b86f75ac6125c65d6a1d6a","target":"graph","created_at":"2026-06-02T02:04:53Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"we introduce Dirichlet-approximated possibilistic posterior predictions (DAPPr), a principled framework leveraging possibility theory. We define a possibilistic posterior over parameters, projects this posterior to the prediction space via supremum operators, and approximates the projected posterior using learnable Dirichlet possibility functions. This projection-and-approximation strategy yields a simple training objective with closed-form solutions."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the supremum-based projection of the possibilistic posterior onto prediction space, followed by Dirichlet approximation, rigorously quantifies epistemic uncertainty rather than merely producing a convenient training objective."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"DAPPr introduces a possibilistic framework that projects parameter posteriors to predictions via supremum and approximates them with Dirichlet possibility functions to yield efficient, closed-form epistemic uncertainty estimates."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Deep neural networks can quantify epistemic uncertainty by projecting possibilistic posteriors over parameters onto predictions via supremum operators and approximating them with learnable Dirichlet possibility functions."}],"snapshot_sha256":"05d3d0c38df8ee8df7155688f2dee2e62f8c5b6adb693d3da8b1aa922e1a4045"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T19:39:11.131120Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T18:01:54.904392Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.00600/integrity.json","findings":[],"snapshot_sha256":"c3e53a54b63b685833fd8c482361f5ef01d205a6acbb9027fe18dc197e978c1e","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep neural networks achieve impressive results across diverse applications, yet their overconfidence on unseen inputs necessitates reliable epistemic uncertainty modeling. Existing methods for uncertainty modeling face a fundamental dilemma: Bayesian approaches provide principled estimates but remain computationally prohibitive, while efficient second-order predictors lack rigorous connections between their specific objectives and epistemic uncertainty quantification. To resolve this dilemma, we introduce Dirichlet-approximated possibilistic posterior predictions (DAPPr), a principled framewo","authors_text":"Jeremie Houssineau, Piotr Koniusz, Yao Ni, Yew Soon Ong","cross_cats":["cs.AI","cs.CV"],"headline":"Deep neural networks can quantify epistemic uncertainty by projecting possibilistic posteriors over parameters onto predictions via supremum operators and approximating them with learnable Dirichlet possibility functions.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-01T12:14:01Z","title":"Possibilistic Predictive Uncertainty for Deep Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.00600","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-09T19:11:00.236027Z","id":"c3f23cc6-b8a0-4724-bb31-31573d6cab5a","model_set":{"reader":"grok-4.3"},"one_line_summary":"DAPPr introduces a possibilistic framework that projects parameter posteriors to predictions via supremum and approximates them with Dirichlet possibility functions to yield efficient, closed-form epistemic uncertainty estimates.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Deep neural networks can quantify epistemic uncertainty by projecting possibilistic posteriors over parameters onto predictions via supremum operators and approximating them with learnable Dirichlet possibility functions.","strongest_claim":"we introduce Dirichlet-approximated possibilistic posterior predictions (DAPPr), a principled framework leveraging possibility theory. We define a possibilistic posterior over parameters, projects this posterior to the prediction space via supremum operators, and approximates the projected posterior using learnable Dirichlet possibility functions. This projection-and-approximation strategy yields a simple training objective with closed-form solutions.","weakest_assumption":"That the supremum-based projection of the possibilistic posterior onto prediction space, followed by Dirichlet approximation, rigorously quantifies epistemic uncertainty rather than merely producing a convenient training objective."}},"verdict_id":"c3f23cc6-b8a0-4724-bb31-31573d6cab5a"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:231ea24247037c2fd9386e73e90db6c8e1bdcb4322b91f799bc46db50479474a","target":"record","created_at":"2026-06-02T02:04:53Z","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":"d4976aefeb262f5e472946b53607a1234cf48d2e6cb2caedd6c05be1b7c61fc9","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-01T12:14:01Z","title_canon_sha256":"b190207710f69394955f9d4c4d4a1f46d9456e1342bdbb7aebfd4a522dfc787d"},"schema_version":"1.0","source":{"id":"2605.00600","kind":"arxiv","version":2}},"canonical_sha256":"9fae45ead390478f7e386d69c375ba1ba314bf093372b0045a94700113f2344b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9fae45ead390478f7e386d69c375ba1ba314bf093372b0045a94700113f2344b","first_computed_at":"2026-06-02T02:04:53.543821Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:53.543821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5lVPMTqI4k4g0xxqKvwl2ZMZ5/1fG0EJXMXY1638FdxaPcv8ZWPKiDTnNMfIELwzz71ID7zqZUJ4RvPL5zUvBw==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:53.544197Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.00600","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:231ea24247037c2fd9386e73e90db6c8e1bdcb4322b91f799bc46db50479474a","sha256:bd5a2c9e3fa9e107eb195654d89dbbd5b67affa608b86f75ac6125c65d6a1d6a"],"state_sha256":"54ae075fbee80c9e03cdf85f1a563dd9a6ffa991b9da7d88bc266013c7435c2d"}