{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:4JQIM7AMZKZHPEQQVE3OHULGHQ","short_pith_number":"pith:4JQIM7AM","canonical_record":{"source":{"id":"2110.14182","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-27T05:32:25Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","stat.ML"],"title_canon_sha256":"e64e0d11f0b9672b422fd8c4f69e925f2e44a6d0d8c988d7cefa2964a753bc5b","abstract_canon_sha256":"7ee3e124c302527714755bc9ddd871bc38313f8e12d5625f99329415c5aa221d"},"schema_version":"1.0"},"canonical_sha256":"e260867c0ccab2779210a936e3d1663c3dcf3ba75f1659824a41daf2521d2095","source":{"kind":"arxiv","id":"2110.14182","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.14182","created_at":"2026-07-05T03:26:24Z"},{"alias_kind":"arxiv_version","alias_value":"2110.14182v1","created_at":"2026-07-05T03:26:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.14182","created_at":"2026-07-05T03:26:24Z"},{"alias_kind":"pith_short_12","alias_value":"4JQIM7AMZKZH","created_at":"2026-07-05T03:26:24Z"},{"alias_kind":"pith_short_16","alias_value":"4JQIM7AMZKZHPEQQ","created_at":"2026-07-05T03:26:24Z"},{"alias_kind":"pith_short_8","alias_value":"4JQIM7AM","created_at":"2026-07-05T03:26:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:4JQIM7AMZKZHPEQQVE3OHULGHQ","target":"record","payload":{"canonical_record":{"source":{"id":"2110.14182","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-27T05:32:25Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","stat.ML"],"title_canon_sha256":"e64e0d11f0b9672b422fd8c4f69e925f2e44a6d0d8c988d7cefa2964a753bc5b","abstract_canon_sha256":"7ee3e124c302527714755bc9ddd871bc38313f8e12d5625f99329415c5aa221d"},"schema_version":"1.0"},"canonical_sha256":"e260867c0ccab2779210a936e3d1663c3dcf3ba75f1659824a41daf2521d2095","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:26:24.627886Z","signature_b64":"QIgFx3uEsfp3gIY7KM145RsAjDFJtXP02aJPtBxQ7Do0/wJFkOfAM40P2sszDHXo3DLnnHe9kC0g1RoA1nnBAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e260867c0ccab2779210a936e3d1663c3dcf3ba75f1659824a41daf2521d2095","last_reissued_at":"2026-07-05T03:26:24.627447Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:26:24.627447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.14182","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":"2026-07-05T03:26:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V+2lsyRrJxSUDpHMkXI0ERUg2OaA/f8oPIeLf8ou0pp0WWr/+gnDVEAns9QhyvpOIq+HIekEzwMBEqy9jCkcDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T10:01:52.521868Z"},"content_sha256":"4bc7a5672a240d613486d51b7d002852fd5dbcb0e7ee446bbce5ad0ad08afc0f","schema_version":"1.0","event_id":"sha256:4bc7a5672a240d613486d51b7d002852fd5dbcb0e7ee446bbce5ad0ad08afc0f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:4JQIM7AMZKZHPEQQVE3OHULGHQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evidential Softmax for Sparse Multimodal Distributions in Deep Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Masha Itkina, Mykel J. Kochenderfer, Phil Chen, Ransalu Senanayake","submitted_at":"2021-10-27T05:32:25Z","abstract_excerpt":"Many applications of generative models rely on the marginalization of their high-dimensional output probability distributions. Normalization functions that yield sparse probability distributions can make exact marginalization more computationally tractable. However, sparse normalization functions usually require alternative loss functions for training since the log-likelihood is undefined for sparse probability distributions. Furthermore, many sparse normalization functions often collapse the multimodality of distributions. In this work, we present $\\textit{ev-softmax}$, a sparse normalization"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.14182","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/2110.14182/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":"2026-07-05T03:26:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T/NHmt7eILHnHq9MZtSK4lS/3DGfijvYALYdmHcFz/LteEccQJwwZM1Th8MzzXSHPo7Xgq1mqNChIp7ZiqZgBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T10:01:52.522385Z"},"content_sha256":"9e1ba99f83ae030fb1715c0ceb750c5147e1fbe75f5c40b8d742e25812b81eb7","schema_version":"1.0","event_id":"sha256:9e1ba99f83ae030fb1715c0ceb750c5147e1fbe75f5c40b8d742e25812b81eb7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4JQIM7AMZKZHPEQQVE3OHULGHQ/bundle.json","state_url":"https://pith.science/pith/4JQIM7AMZKZHPEQQVE3OHULGHQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4JQIM7AMZKZHPEQQVE3OHULGHQ/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":"2026-08-16T10:01:52Z","links":{"resolver":"https://pith.science/pith/4JQIM7AMZKZHPEQQVE3OHULGHQ","bundle":"https://pith.science/pith/4JQIM7AMZKZHPEQQVE3OHULGHQ/bundle.json","state":"https://pith.science/pith/4JQIM7AMZKZHPEQQVE3OHULGHQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4JQIM7AMZKZHPEQQVE3OHULGHQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:4JQIM7AMZKZHPEQQVE3OHULGHQ","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":"7ee3e124c302527714755bc9ddd871bc38313f8e12d5625f99329415c5aa221d","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-27T05:32:25Z","title_canon_sha256":"e64e0d11f0b9672b422fd8c4f69e925f2e44a6d0d8c988d7cefa2964a753bc5b"},"schema_version":"1.0","source":{"id":"2110.14182","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.14182","created_at":"2026-07-05T03:26:24Z"},{"alias_kind":"arxiv_version","alias_value":"2110.14182v1","created_at":"2026-07-05T03:26:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.14182","created_at":"2026-07-05T03:26:24Z"},{"alias_kind":"pith_short_12","alias_value":"4JQIM7AMZKZH","created_at":"2026-07-05T03:26:24Z"},{"alias_kind":"pith_short_16","alias_value":"4JQIM7AMZKZHPEQQ","created_at":"2026-07-05T03:26:24Z"},{"alias_kind":"pith_short_8","alias_value":"4JQIM7AM","created_at":"2026-07-05T03:26:24Z"}],"graph_snapshots":[{"event_id":"sha256:9e1ba99f83ae030fb1715c0ceb750c5147e1fbe75f5c40b8d742e25812b81eb7","target":"graph","created_at":"2026-07-05T03:26:24Z","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/2110.14182/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many applications of generative models rely on the marginalization of their high-dimensional output probability distributions. Normalization functions that yield sparse probability distributions can make exact marginalization more computationally tractable. However, sparse normalization functions usually require alternative loss functions for training since the log-likelihood is undefined for sparse probability distributions. Furthermore, many sparse normalization functions often collapse the multimodality of distributions. In this work, we present $\\textit{ev-softmax}$, a sparse normalization","authors_text":"Masha Itkina, Mykel J. Kochenderfer, Phil Chen, Ransalu Senanayake","cross_cats":["cs.AI","cs.CL","cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-27T05:32:25Z","title":"Evidential Softmax for Sparse Multimodal Distributions in Deep Generative Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.14182","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":"sha256:4bc7a5672a240d613486d51b7d002852fd5dbcb0e7ee446bbce5ad0ad08afc0f","target":"record","created_at":"2026-07-05T03:26:24Z","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":"7ee3e124c302527714755bc9ddd871bc38313f8e12d5625f99329415c5aa221d","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-27T05:32:25Z","title_canon_sha256":"e64e0d11f0b9672b422fd8c4f69e925f2e44a6d0d8c988d7cefa2964a753bc5b"},"schema_version":"1.0","source":{"id":"2110.14182","kind":"arxiv","version":1}},"canonical_sha256":"e260867c0ccab2779210a936e3d1663c3dcf3ba75f1659824a41daf2521d2095","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e260867c0ccab2779210a936e3d1663c3dcf3ba75f1659824a41daf2521d2095","first_computed_at":"2026-07-05T03:26:24.627447Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:26:24.627447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QIgFx3uEsfp3gIY7KM145RsAjDFJtXP02aJPtBxQ7Do0/wJFkOfAM40P2sszDHXo3DLnnHe9kC0g1RoA1nnBAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:26:24.627886Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.14182","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4bc7a5672a240d613486d51b7d002852fd5dbcb0e7ee446bbce5ad0ad08afc0f","sha256:9e1ba99f83ae030fb1715c0ceb750c5147e1fbe75f5c40b8d742e25812b81eb7"],"state_sha256":"7d047907c0fd9e8a1969453cb14ebcbc4aeef7e33780b482f9ab73d15f420fc0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lkv7bouhLOfg9x6J8DFIXS6clKkWtGLn4TcCq4xoDibldSSCHzqFBORmaU1YaNglH768YjWPQVKeh4YYQ1YZAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T10:01:52.526053Z","bundle_sha256":"efd5a135d273f157c13d03bf4b842b2d58d6c5d5d39b43ec9361d3b49fe3c4ac"}}