{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:X2B4XJE4AAIAMFS76DZ7C7NIDM","short_pith_number":"pith:X2B4XJE4","canonical_record":{"source":{"id":"2402.00957","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-01T19:25:58Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"9ecc9080a9bc03f92cc473248761e24d910bb44fe069623dcb1ea98dab3e8f14","abstract_canon_sha256":"cc9e709c69f6f35903461e398af2181a3f58cb361712c619bdf4c52687b5a767"},"schema_version":"1.0"},"canonical_sha256":"be83cba49c001006165ff0f3f17da81b01038cafd51c0c60f2e1fd3b88456704","source":{"kind":"arxiv","id":"2402.00957","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.00957","created_at":"2026-07-05T09:24:56Z"},{"alias_kind":"arxiv_version","alias_value":"2402.00957v4","created_at":"2026-07-05T09:24:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.00957","created_at":"2026-07-05T09:24:56Z"},{"alias_kind":"pith_short_12","alias_value":"X2B4XJE4AAIA","created_at":"2026-07-05T09:24:56Z"},{"alias_kind":"pith_short_16","alias_value":"X2B4XJE4AAIAMFS7","created_at":"2026-07-05T09:24:56Z"},{"alias_kind":"pith_short_8","alias_value":"X2B4XJE4","created_at":"2026-07-05T09:24:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:X2B4XJE4AAIAMFS76DZ7C7NIDM","target":"record","payload":{"canonical_record":{"source":{"id":"2402.00957","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-01T19:25:58Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"9ecc9080a9bc03f92cc473248761e24d910bb44fe069623dcb1ea98dab3e8f14","abstract_canon_sha256":"cc9e709c69f6f35903461e398af2181a3f58cb361712c619bdf4c52687b5a767"},"schema_version":"1.0"},"canonical_sha256":"be83cba49c001006165ff0f3f17da81b01038cafd51c0c60f2e1fd3b88456704","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:56.432911Z","signature_b64":"FdLF7i7/M2DKsi4Vc9URFE2OUzxi2kYu9rhh3a+dPbCnGN9kC+LDaTf2oUJziOrEY+B9/g1QUpqPsS7of0lzBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be83cba49c001006165ff0f3f17da81b01038cafd51c0c60f2e1fd3b88456704","last_reissued_at":"2026-07-05T09:24:56.432517Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:56.432517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.00957","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:24:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TaTdpT4mhcpVUbfH9pdSqZ0Vvm3KfDMvFAPdaZNA+71m5fNqfickzwm2FL+y7THJjxdrYVHOhRrCNmpNAvWQCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T07:48:21.958704Z"},"content_sha256":"49befab67bdb619d09ab7a4a96bdcadb36661722030d86b0b6d62dd7e928c47f","schema_version":"1.0","event_id":"sha256:49befab67bdb619d09ab7a4a96bdcadb36661722030d86b0b6d62dd7e928c47f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:X2B4XJE4AAIAMFS76DZ7C7NIDM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Credal Learning Theory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Eleni Elia, Fabio Cuzzolin, Maryam Sultana, Michele Caprio","submitted_at":"2024-02-01T19:25:58Z","abstract_excerpt":"Statistical learning theory is the foundation of machine learning, providing theoretical bounds for the risk of models learned from a (single) training set, assumed to issue from an unknown probability distribution. In actual deployment, however, the data distribution may (and often does) vary, causing domain adaptation/generalization issues. In this paper we lay the foundations for a `credal' theory of learning, using convex sets of probabilities (credal sets) to model the variability in the data-generating distribution. Such credal sets, we argue, may be inferred from a finite sample of trai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.00957","kind":"arxiv","version":4},"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/2402.00957/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":"2026-07-05T09:24:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7fQD/7EDwMTIcY+yVWhaoBia4czuiaB+qaDEXGF+Z95BHuoAELUHQzWxFlZyKppdecFTDofZK0jCnWVJTEX0CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T07:48:21.959249Z"},"content_sha256":"149688489c278c5f7839c4e6f0e2d2572b0e7185f6f5c3009ee2a462f33d4f95","schema_version":"1.0","event_id":"sha256:149688489c278c5f7839c4e6f0e2d2572b0e7185f6f5c3009ee2a462f33d4f95"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X2B4XJE4AAIAMFS76DZ7C7NIDM/bundle.json","state_url":"https://pith.science/pith/X2B4XJE4AAIAMFS76DZ7C7NIDM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X2B4XJE4AAIAMFS76DZ7C7NIDM/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":"2026-08-08T07:48:21Z","links":{"resolver":"https://pith.science/pith/X2B4XJE4AAIAMFS76DZ7C7NIDM","bundle":"https://pith.science/pith/X2B4XJE4AAIAMFS76DZ7C7NIDM/bundle.json","state":"https://pith.science/pith/X2B4XJE4AAIAMFS76DZ7C7NIDM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X2B4XJE4AAIAMFS76DZ7C7NIDM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:X2B4XJE4AAIAMFS76DZ7C7NIDM","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":"cc9e709c69f6f35903461e398af2181a3f58cb361712c619bdf4c52687b5a767","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-01T19:25:58Z","title_canon_sha256":"9ecc9080a9bc03f92cc473248761e24d910bb44fe069623dcb1ea98dab3e8f14"},"schema_version":"1.0","source":{"id":"2402.00957","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.00957","created_at":"2026-07-05T09:24:56Z"},{"alias_kind":"arxiv_version","alias_value":"2402.00957v4","created_at":"2026-07-05T09:24:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.00957","created_at":"2026-07-05T09:24:56Z"},{"alias_kind":"pith_short_12","alias_value":"X2B4XJE4AAIA","created_at":"2026-07-05T09:24:56Z"},{"alias_kind":"pith_short_16","alias_value":"X2B4XJE4AAIAMFS7","created_at":"2026-07-05T09:24:56Z"},{"alias_kind":"pith_short_8","alias_value":"X2B4XJE4","created_at":"2026-07-05T09:24:56Z"}],"graph_snapshots":[{"event_id":"sha256:149688489c278c5f7839c4e6f0e2d2572b0e7185f6f5c3009ee2a462f33d4f95","target":"graph","created_at":"2026-07-05T09:24:56Z","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/2402.00957/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Statistical learning theory is the foundation of machine learning, providing theoretical bounds for the risk of models learned from a (single) training set, assumed to issue from an unknown probability distribution. In actual deployment, however, the data distribution may (and often does) vary, causing domain adaptation/generalization issues. In this paper we lay the foundations for a `credal' theory of learning, using convex sets of probabilities (credal sets) to model the variability in the data-generating distribution. Such credal sets, we argue, may be inferred from a finite sample of trai","authors_text":"Eleni Elia, Fabio Cuzzolin, Maryam Sultana, Michele Caprio","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-01T19:25:58Z","title":"Credal Learning Theory"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.00957","kind":"arxiv","version":4},"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":"sha256:49befab67bdb619d09ab7a4a96bdcadb36661722030d86b0b6d62dd7e928c47f","target":"record","created_at":"2026-07-05T09:24:56Z","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":"cc9e709c69f6f35903461e398af2181a3f58cb361712c619bdf4c52687b5a767","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-01T19:25:58Z","title_canon_sha256":"9ecc9080a9bc03f92cc473248761e24d910bb44fe069623dcb1ea98dab3e8f14"},"schema_version":"1.0","source":{"id":"2402.00957","kind":"arxiv","version":4}},"canonical_sha256":"be83cba49c001006165ff0f3f17da81b01038cafd51c0c60f2e1fd3b88456704","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be83cba49c001006165ff0f3f17da81b01038cafd51c0c60f2e1fd3b88456704","first_computed_at":"2026-07-05T09:24:56.432517Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:24:56.432517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FdLF7i7/M2DKsi4Vc9URFE2OUzxi2kYu9rhh3a+dPbCnGN9kC+LDaTf2oUJziOrEY+B9/g1QUpqPsS7of0lzBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:24:56.432911Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.00957","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:49befab67bdb619d09ab7a4a96bdcadb36661722030d86b0b6d62dd7e928c47f","sha256:149688489c278c5f7839c4e6f0e2d2572b0e7185f6f5c3009ee2a462f33d4f95"],"state_sha256":"6d44512e95d349c167305d93435867291238dd996941826517582c040f2951a5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5hpErR0+LpAPHWOsUXlO4izp43QGWFYB5VLz9R1yhMsCUw/2E9foNAFGOJraBsK4C3MR6v54qm9rCsz6XFrjAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T07:48:21.963161Z","bundle_sha256":"8b93af93fbdfd9b746c7afde848f5e562620580eaf938e7b164c30f7e6b9eaac"}}