{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:EJ4G3ZTKGEMGHM64VLL2YGOTR3","short_pith_number":"pith:EJ4G3ZTK","schema_version":"1.0","canonical_sha256":"22786de66a311863b3dcaad7ac19d38ed27d31466c979161ea9b7fa57719b3ae","source":{"kind":"arxiv","id":"2210.08572","version":3},"attestation_state":"computed","paper":{"title":"Automatic Differentiation of Programs with Discrete Randomness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MS","cs.NA","math.NA","math.PR"],"primary_cat":"cs.LG","authors_text":"Chris Rackauckas, Frank Sch\\\"afer, Gaurav Arya, Moritz Schauer","submitted_at":"2022-10-16T16:05:50Z","abstract_excerpt":"Automatic differentiation (AD), a technique for constructing new programs which compute the derivative of an original program, has become ubiquitous throughout scientific computing and deep learning due to the improved performance afforded by gradient-based optimization. However, AD systems have been restricted to the subset of programs that have a continuous dependence on parameters. Programs that have discrete stochastic behaviors governed by distribution parameters, such as flipping a coin with probability $p$ of being heads, pose a challenge to these systems because the connection between "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2210.08572","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-16T16:05:50Z","cross_cats_sorted":["cs.MS","cs.NA","math.NA","math.PR"],"title_canon_sha256":"e39815a8b75db66e94aace1c6e8d3a2399363614665824e48fdf4ee148eee757","abstract_canon_sha256":"993347d3c22009d49075d227fe3a4114bfb5c286be50226a19775884d83d8d48"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:31:17.989363Z","signature_b64":"GRz+3CrtxiQ9dQVmdK1dSOUjZremFviMFM8vEDKVpLZc/xyuehdnjAmQmGsJb4bAh66isGrTP3IDlGa98GT3AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22786de66a311863b3dcaad7ac19d38ed27d31466c979161ea9b7fa57719b3ae","last_reissued_at":"2026-07-05T05:31:17.988888Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:31:17.988888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automatic Differentiation of Programs with Discrete Randomness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MS","cs.NA","math.NA","math.PR"],"primary_cat":"cs.LG","authors_text":"Chris Rackauckas, Frank Sch\\\"afer, Gaurav Arya, Moritz Schauer","submitted_at":"2022-10-16T16:05:50Z","abstract_excerpt":"Automatic differentiation (AD), a technique for constructing new programs which compute the derivative of an original program, has become ubiquitous throughout scientific computing and deep learning due to the improved performance afforded by gradient-based optimization. However, AD systems have been restricted to the subset of programs that have a continuous dependence on parameters. Programs that have discrete stochastic behaviors governed by distribution parameters, such as flipping a coin with probability $p$ of being heads, pose a challenge to these systems because the connection between "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.08572","kind":"arxiv","version":3},"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/2210.08572/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2210.08572","created_at":"2026-07-05T05:31:17.988945+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.08572v3","created_at":"2026-07-05T05:31:17.988945+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.08572","created_at":"2026-07-05T05:31:17.988945+00:00"},{"alias_kind":"pith_short_12","alias_value":"EJ4G3ZTKGEMG","created_at":"2026-07-05T05:31:17.988945+00:00"},{"alias_kind":"pith_short_16","alias_value":"EJ4G3ZTKGEMGHM64","created_at":"2026-07-05T05:31:17.988945+00:00"},{"alias_kind":"pith_short_8","alias_value":"EJ4G3ZTK","created_at":"2026-07-05T05:31:17.988945+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.17962","citing_title":"A Principled Bayesian Framework for Training Binary and Spiking Neural Networks","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EJ4G3ZTKGEMGHM64VLL2YGOTR3","json":"https://pith.science/pith/EJ4G3ZTKGEMGHM64VLL2YGOTR3.json","graph_json":"https://pith.science/api/pith-number/EJ4G3ZTKGEMGHM64VLL2YGOTR3/graph.json","events_json":"https://pith.science/api/pith-number/EJ4G3ZTKGEMGHM64VLL2YGOTR3/events.json","paper":"https://pith.science/paper/EJ4G3ZTK"},"agent_actions":{"view_html":"https://pith.science/pith/EJ4G3ZTKGEMGHM64VLL2YGOTR3","download_json":"https://pith.science/pith/EJ4G3ZTKGEMGHM64VLL2YGOTR3.json","view_paper":"https://pith.science/paper/EJ4G3ZTK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.08572&json=true","fetch_graph":"https://pith.science/api/pith-number/EJ4G3ZTKGEMGHM64VLL2YGOTR3/graph.json","fetch_events":"https://pith.science/api/pith-number/EJ4G3ZTKGEMGHM64VLL2YGOTR3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EJ4G3ZTKGEMGHM64VLL2YGOTR3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EJ4G3ZTKGEMGHM64VLL2YGOTR3/action/storage_attestation","attest_author":"https://pith.science/pith/EJ4G3ZTKGEMGHM64VLL2YGOTR3/action/author_attestation","sign_citation":"https://pith.science/pith/EJ4G3ZTKGEMGHM64VLL2YGOTR3/action/citation_signature","submit_replication":"https://pith.science/pith/EJ4G3ZTKGEMGHM64VLL2YGOTR3/action/replication_record"}},"created_at":"2026-07-05T05:31:17.988945+00:00","updated_at":"2026-07-05T05:31:17.988945+00:00"}