{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MGGRI3XXY7MDOZIDHFGIMFCYEA","short_pith_number":"pith:MGGRI3XX","canonical_record":{"source":{"id":"2411.14860","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-22T11:18:20Z","cross_cats_sorted":[],"title_canon_sha256":"4b19a1ce187d0d41bec550a59d0f4e8a119583c50f2eb537c41940922425ce29","abstract_canon_sha256":"73277dbb7958c10ea8a4de7c5a05a95d17a425ef6111eb56c351c7fcc2757b3b"},"schema_version":"1.0"},"canonical_sha256":"618d146ef7c7d8376503394c861458202120da84bf4305cf7e7625a451dd497c","source":{"kind":"arxiv","id":"2411.14860","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14860","created_at":"2026-07-05T09:39:12Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14860v1","created_at":"2026-07-05T09:39:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14860","created_at":"2026-07-05T09:39:12Z"},{"alias_kind":"pith_short_12","alias_value":"MGGRI3XXY7MD","created_at":"2026-07-05T09:39:12Z"},{"alias_kind":"pith_short_16","alias_value":"MGGRI3XXY7MDOZID","created_at":"2026-07-05T09:39:12Z"},{"alias_kind":"pith_short_8","alias_value":"MGGRI3XX","created_at":"2026-07-05T09:39:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MGGRI3XXY7MDOZIDHFGIMFCYEA","target":"record","payload":{"canonical_record":{"source":{"id":"2411.14860","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-22T11:18:20Z","cross_cats_sorted":[],"title_canon_sha256":"4b19a1ce187d0d41bec550a59d0f4e8a119583c50f2eb537c41940922425ce29","abstract_canon_sha256":"73277dbb7958c10ea8a4de7c5a05a95d17a425ef6111eb56c351c7fcc2757b3b"},"schema_version":"1.0"},"canonical_sha256":"618d146ef7c7d8376503394c861458202120da84bf4305cf7e7625a451dd497c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:12.798708Z","signature_b64":"9Mts2gP8DeBOR5Q36XFgUKmd+8ypNzufWAb96H8bACpM+lLHuOlvAsOB+zn6y/G4TjmV9tNqYZSHVp2cx9slBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"618d146ef7c7d8376503394c861458202120da84bf4305cf7e7625a451dd497c","last_reissued_at":"2026-07-05T09:39:12.797448Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:12.797448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.14860","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:39:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"byWL1oIW3VSt04pZWwDkWWiZqw8Tztb7j6awl9kqp81PGu1s1T4VR1qofTXlpzT1APeUMKGEJUyxw+2f7/JIDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T01:41:44.111447Z"},"content_sha256":"39ff44e2331cd08d71fbb5c2f11bf4b30427e8feac543d2347854ee1c6f9907f","schema_version":"1.0","event_id":"sha256:39ff44e2331cd08d71fbb5c2f11bf4b30427e8feac543d2347854ee1c6f9907f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MGGRI3XXY7MDOZIDHFGIMFCYEA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Ex Uno Pluria: Insights on Ensembling in Low Precision Number Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Giung Nam, Juho Lee","submitted_at":"2024-11-22T11:18:20Z","abstract_excerpt":"While ensembling deep neural networks has shown promise in improving generalization performance, scaling current ensemble methods for large models remains challenging. Given that recent progress in deep learning is largely driven by the scale, exemplified by the widespread adoption of large-scale neural network architectures, scalability emerges an increasingly critical issue for machine learning algorithms in the era of large-scale models. In this work, we first showcase the potential of low precision ensembling, where ensemble members are derived from a single model within low precision numb"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14860","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/2411.14860/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":"2026-07-05T09:39:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pgwkXxi0yzH5LZINiw3HBMaRPc9wyTj9x6LNrdiqx5tPo0km7FnWHMRfjX+UJ6IAAkeIemAmplrvRhfmJuHgCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T01:41:44.112029Z"},"content_sha256":"c5fae5145a90047d18c830041c0e86b72a77564ccef1a4f44f78ed0f09e45a38","schema_version":"1.0","event_id":"sha256:c5fae5145a90047d18c830041c0e86b72a77564ccef1a4f44f78ed0f09e45a38"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MGGRI3XXY7MDOZIDHFGIMFCYEA/bundle.json","state_url":"https://pith.science/pith/MGGRI3XXY7MDOZIDHFGIMFCYEA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MGGRI3XXY7MDOZIDHFGIMFCYEA/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":"2026-08-13T01:41:44Z","links":{"resolver":"https://pith.science/pith/MGGRI3XXY7MDOZIDHFGIMFCYEA","bundle":"https://pith.science/pith/MGGRI3XXY7MDOZIDHFGIMFCYEA/bundle.json","state":"https://pith.science/pith/MGGRI3XXY7MDOZIDHFGIMFCYEA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MGGRI3XXY7MDOZIDHFGIMFCYEA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MGGRI3XXY7MDOZIDHFGIMFCYEA","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":"73277dbb7958c10ea8a4de7c5a05a95d17a425ef6111eb56c351c7fcc2757b3b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-22T11:18:20Z","title_canon_sha256":"4b19a1ce187d0d41bec550a59d0f4e8a119583c50f2eb537c41940922425ce29"},"schema_version":"1.0","source":{"id":"2411.14860","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14860","created_at":"2026-07-05T09:39:12Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14860v1","created_at":"2026-07-05T09:39:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14860","created_at":"2026-07-05T09:39:12Z"},{"alias_kind":"pith_short_12","alias_value":"MGGRI3XXY7MD","created_at":"2026-07-05T09:39:12Z"},{"alias_kind":"pith_short_16","alias_value":"MGGRI3XXY7MDOZID","created_at":"2026-07-05T09:39:12Z"},{"alias_kind":"pith_short_8","alias_value":"MGGRI3XX","created_at":"2026-07-05T09:39:12Z"}],"graph_snapshots":[{"event_id":"sha256:c5fae5145a90047d18c830041c0e86b72a77564ccef1a4f44f78ed0f09e45a38","target":"graph","created_at":"2026-07-05T09:39:12Z","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/2411.14860/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While ensembling deep neural networks has shown promise in improving generalization performance, scaling current ensemble methods for large models remains challenging. Given that recent progress in deep learning is largely driven by the scale, exemplified by the widespread adoption of large-scale neural network architectures, scalability emerges an increasingly critical issue for machine learning algorithms in the era of large-scale models. In this work, we first showcase the potential of low precision ensembling, where ensemble members are derived from a single model within low precision numb","authors_text":"Giung Nam, Juho Lee","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-22T11:18:20Z","title":"Ex Uno Pluria: Insights on Ensembling in Low Precision Number Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14860","kind":"arxiv","version":1},"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":"sha256:39ff44e2331cd08d71fbb5c2f11bf4b30427e8feac543d2347854ee1c6f9907f","target":"record","created_at":"2026-07-05T09:39:12Z","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":"73277dbb7958c10ea8a4de7c5a05a95d17a425ef6111eb56c351c7fcc2757b3b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-22T11:18:20Z","title_canon_sha256":"4b19a1ce187d0d41bec550a59d0f4e8a119583c50f2eb537c41940922425ce29"},"schema_version":"1.0","source":{"id":"2411.14860","kind":"arxiv","version":1}},"canonical_sha256":"618d146ef7c7d8376503394c861458202120da84bf4305cf7e7625a451dd497c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"618d146ef7c7d8376503394c861458202120da84bf4305cf7e7625a451dd497c","first_computed_at":"2026-07-05T09:39:12.797448Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:39:12.797448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9Mts2gP8DeBOR5Q36XFgUKmd+8ypNzufWAb96H8bACpM+lLHuOlvAsOB+zn6y/G4TjmV9tNqYZSHVp2cx9slBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:39:12.798708Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.14860","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:39ff44e2331cd08d71fbb5c2f11bf4b30427e8feac543d2347854ee1c6f9907f","sha256:c5fae5145a90047d18c830041c0e86b72a77564ccef1a4f44f78ed0f09e45a38"],"state_sha256":"16f03be712eb3ee655459616d368c8e9bfd4d565cfbdf71f7147cd0a68759dae"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S0C04NjeUngEh1HPDzTjiSVZHo1EdbwkOVh1cL6covzHIFrnFjxamJkDIEyGgaDYijvPIdRAPcKMuFVhsqwkCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T01:41:44.115608Z","bundle_sha256":"b7fa7a3c051264b972acb9191825bd16e7b6a0239de0c0c669c08cd6c1df6fa6"}}