{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:UAD42CDFJ7L2INPCS5HJYRJW5Z","short_pith_number":"pith:UAD42CDF","canonical_record":{"source":{"id":"2110.01515","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-04T15:34:13Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2f08a1fdcfb94ac7b8cc034e9c474d17d4d5179577497ec903dd62d12240589b","abstract_canon_sha256":"58722061bacd0ebb900a581e3fff79c5ea5accc7ba3af9994d3e3196a0e9865e"},"schema_version":"1.0"},"canonical_sha256":"a007cd08654fd7a435e2974e9c4536ee71ff44f68c8255d24d6bebe0d5db3df5","source":{"kind":"arxiv","id":"2110.01515","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.01515","created_at":"2026-07-05T04:02:57Z"},{"alias_kind":"arxiv_version","alias_value":"2110.01515v2","created_at":"2026-07-05T04:02:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.01515","created_at":"2026-07-05T04:02:57Z"},{"alias_kind":"pith_short_12","alias_value":"UAD42CDFJ7L2","created_at":"2026-07-05T04:02:57Z"},{"alias_kind":"pith_short_16","alias_value":"UAD42CDFJ7L2INPC","created_at":"2026-07-05T04:02:57Z"},{"alias_kind":"pith_short_8","alias_value":"UAD42CDF","created_at":"2026-07-05T04:02:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:UAD42CDFJ7L2INPCS5HJYRJW5Z","target":"record","payload":{"canonical_record":{"source":{"id":"2110.01515","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-04T15:34:13Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2f08a1fdcfb94ac7b8cc034e9c474d17d4d5179577497ec903dd62d12240589b","abstract_canon_sha256":"58722061bacd0ebb900a581e3fff79c5ea5accc7ba3af9994d3e3196a0e9865e"},"schema_version":"1.0"},"canonical_sha256":"a007cd08654fd7a435e2974e9c4536ee71ff44f68c8255d24d6bebe0d5db3df5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:02:57.258468Z","signature_b64":"264vdeRT7xdZ7oEQMmnHPHWDCAc5peO4xYGmbrhsAcy4Br6kDFbbkzMzVsFHlY/CdIL72fxoVAO+0mF7laugCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a007cd08654fd7a435e2974e9c4536ee71ff44f68c8255d24d6bebe0d5db3df5","last_reissued_at":"2026-07-05T04:02:57.257961Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:02:57.257961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.01515","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:02:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zzrjHs8zURAhAKWxROpgPDAPuFIvULbeR6WoO9dHuK3NfbgrwTNeghlpQ3q5N/BkA/S7t/7O8RyhX3mYaEKVBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:43:22.068810Z"},"content_sha256":"7ea3e3880a01d4ad250ae0e00ed5a6f4cae6e03eadd833bc36dbbebeb6d426fa","schema_version":"1.0","event_id":"sha256:7ea3e3880a01d4ad250ae0e00ed5a6f4cae6e03eadd833bc36dbbebeb6d426fa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:UAD42CDFJ7L2INPCS5HJYRJW5Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Iris A. M. Huijben, Max B. Paulus, Ruud J. G. van Sloun, Wouter Kool","submitted_at":"2021-10-04T15:34:13Z","abstract_excerpt":"The Gumbel-max trick is a method to draw a sample from a categorical distribution, given by its unnormalized (log-)probabilities. Over the past years, the machine learning community has proposed several extensions of this trick to facilitate, e.g., drawing multiple samples, sampling from structured domains, or gradient estimation for error backpropagation in neural network optimization. The goal of this survey article is to present background about the Gumbel-max trick, and to provide a structured overview of its extensions to ease algorithm selection. Moreover, it presents a comprehensive out"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.01515","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/2110.01515/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":"2026-07-05T04:02:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gucr/PVEn+oGg+6F5LvmR05S0lzYjrcbwaICUBDw/HvVKe9mgG4o/++/SQDkfy9M1YCghqoBkLwe1lkL/tkHBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:43:22.069492Z"},"content_sha256":"e67837c91714f2ec316e1f752b57d407a56a427c0b021a9086684ed214b18dcc","schema_version":"1.0","event_id":"sha256:e67837c91714f2ec316e1f752b57d407a56a427c0b021a9086684ed214b18dcc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UAD42CDFJ7L2INPCS5HJYRJW5Z/bundle.json","state_url":"https://pith.science/pith/UAD42CDFJ7L2INPCS5HJYRJW5Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UAD42CDFJ7L2INPCS5HJYRJW5Z/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":"2026-07-09T05:43:22Z","links":{"resolver":"https://pith.science/pith/UAD42CDFJ7L2INPCS5HJYRJW5Z","bundle":"https://pith.science/pith/UAD42CDFJ7L2INPCS5HJYRJW5Z/bundle.json","state":"https://pith.science/pith/UAD42CDFJ7L2INPCS5HJYRJW5Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UAD42CDFJ7L2INPCS5HJYRJW5Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:UAD42CDFJ7L2INPCS5HJYRJW5Z","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":"58722061bacd0ebb900a581e3fff79c5ea5accc7ba3af9994d3e3196a0e9865e","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-04T15:34:13Z","title_canon_sha256":"2f08a1fdcfb94ac7b8cc034e9c474d17d4d5179577497ec903dd62d12240589b"},"schema_version":"1.0","source":{"id":"2110.01515","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.01515","created_at":"2026-07-05T04:02:57Z"},{"alias_kind":"arxiv_version","alias_value":"2110.01515v2","created_at":"2026-07-05T04:02:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.01515","created_at":"2026-07-05T04:02:57Z"},{"alias_kind":"pith_short_12","alias_value":"UAD42CDFJ7L2","created_at":"2026-07-05T04:02:57Z"},{"alias_kind":"pith_short_16","alias_value":"UAD42CDFJ7L2INPC","created_at":"2026-07-05T04:02:57Z"},{"alias_kind":"pith_short_8","alias_value":"UAD42CDF","created_at":"2026-07-05T04:02:57Z"}],"graph_snapshots":[{"event_id":"sha256:e67837c91714f2ec316e1f752b57d407a56a427c0b021a9086684ed214b18dcc","target":"graph","created_at":"2026-07-05T04:02:57Z","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/2110.01515/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Gumbel-max trick is a method to draw a sample from a categorical distribution, given by its unnormalized (log-)probabilities. Over the past years, the machine learning community has proposed several extensions of this trick to facilitate, e.g., drawing multiple samples, sampling from structured domains, or gradient estimation for error backpropagation in neural network optimization. The goal of this survey article is to present background about the Gumbel-max trick, and to provide a structured overview of its extensions to ease algorithm selection. Moreover, it presents a comprehensive out","authors_text":"Iris A. M. Huijben, Max B. Paulus, Ruud J. G. van Sloun, Wouter Kool","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-04T15:34:13Z","title":"A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.01515","kind":"arxiv","version":2},"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":"sha256:7ea3e3880a01d4ad250ae0e00ed5a6f4cae6e03eadd833bc36dbbebeb6d426fa","target":"record","created_at":"2026-07-05T04:02:57Z","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":"58722061bacd0ebb900a581e3fff79c5ea5accc7ba3af9994d3e3196a0e9865e","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-04T15:34:13Z","title_canon_sha256":"2f08a1fdcfb94ac7b8cc034e9c474d17d4d5179577497ec903dd62d12240589b"},"schema_version":"1.0","source":{"id":"2110.01515","kind":"arxiv","version":2}},"canonical_sha256":"a007cd08654fd7a435e2974e9c4536ee71ff44f68c8255d24d6bebe0d5db3df5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a007cd08654fd7a435e2974e9c4536ee71ff44f68c8255d24d6bebe0d5db3df5","first_computed_at":"2026-07-05T04:02:57.257961Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:02:57.257961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"264vdeRT7xdZ7oEQMmnHPHWDCAc5peO4xYGmbrhsAcy4Br6kDFbbkzMzVsFHlY/CdIL72fxoVAO+0mF7laugCw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:02:57.258468Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.01515","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ea3e3880a01d4ad250ae0e00ed5a6f4cae6e03eadd833bc36dbbebeb6d426fa","sha256:e67837c91714f2ec316e1f752b57d407a56a427c0b021a9086684ed214b18dcc"],"state_sha256":"c91555bfcf1ad307590272d2b09c9d25aa522d0d9c63d4e1afd994f1eceab1b7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WcE1XCVjVvjHKS1an7ObfpQr3kcHxmvq3EwaQV2NN6BIp4cr4Km6krw5oZJ6T1s2CkrdomM68ZvZQy+kq2NzCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T05:43:22.072860Z","bundle_sha256":"055b44ae2357482bdd91bd68ab7859d2f4c9d0a5f9111963419d0ea6035144f4"}}