{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:ADAIKR3EZHHR34STBOQ4J3UTUF","short_pith_number":"pith:ADAIKR3E","canonical_record":{"source":{"id":"1610.05735","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-10-18T18:35:09Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"1b73861a93fb5bf786c87614ead975a70e188cbe8d88f37f9116d6ff2bf58cf4","abstract_canon_sha256":"379c383730e3923a84091279dd6dcd58b51c63ca4fcf8eebeff2aa66f9328b4d"},"schema_version":"1.0"},"canonical_sha256":"00c0854764c9cf1df2530ba1c4ee93a16582a8dbb95e9a5aa7d6f847dbba31e8","source":{"kind":"arxiv","id":"1610.05735","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.05735","created_at":"2026-05-18T01:01:58Z"},{"alias_kind":"arxiv_version","alias_value":"1610.05735v1","created_at":"2026-05-18T01:01:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.05735","created_at":"2026-05-18T01:01:58Z"},{"alias_kind":"pith_short_12","alias_value":"ADAIKR3EZHHR","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_16","alias_value":"ADAIKR3EZHHR34ST","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_8","alias_value":"ADAIKR3E","created_at":"2026-05-18T12:30:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:ADAIKR3EZHHR34STBOQ4J3UTUF","target":"record","payload":{"canonical_record":{"source":{"id":"1610.05735","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-10-18T18:35:09Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"1b73861a93fb5bf786c87614ead975a70e188cbe8d88f37f9116d6ff2bf58cf4","abstract_canon_sha256":"379c383730e3923a84091279dd6dcd58b51c63ca4fcf8eebeff2aa66f9328b4d"},"schema_version":"1.0"},"canonical_sha256":"00c0854764c9cf1df2530ba1c4ee93a16582a8dbb95e9a5aa7d6f847dbba31e8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:01:58.499517Z","signature_b64":"aDXbbFTZWRe2m+D61p4KGWM16GD7UxvWmalTRinH1AfIs4PFIqo8M/Eiyq2mwS4Q2EMsmsbSHPyzz+oXcEJnBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00c0854764c9cf1df2530ba1c4ee93a16582a8dbb95e9a5aa7d6f847dbba31e8","last_reissued_at":"2026-05-18T01:01:58.498947Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:01:58.498947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1610.05735","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":"2026-05-18T01:01:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6t3MnXfShmEctOK04y139iFn2LePOXuOoxhb17d9qINEVP7FFtypgn41OxzfH1AylatcMrLOSdhrWHzLVyHQAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T13:53:20.837167Z"},"content_sha256":"41a921adf5e4ea862b558afa4ac60baf33e76b46a425f681b78ecc59b5413ef1","schema_version":"1.0","event_id":"sha256:41a921adf5e4ea862b558afa4ac60baf33e76b46a425f681b78ecc59b5413ef1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:ADAIKR3EZHHR34STBOQ4J3UTUF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Amortized Inference for Probabilistic Programs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Daniel Ritchie, Noah D. Goodman, Paul Horsfall","submitted_at":"2016-10-18T18:35:09Z","abstract_excerpt":"Probabilistic programming languages (PPLs) are a powerful modeling tool, able to represent any computable probability distribution. Unfortunately, probabilistic program inference is often intractable, and existing PPLs mostly rely on expensive, approximate sampling-based methods. To alleviate this problem, one could try to learn from past inferences, so that future inferences run faster. This strategy is known as amortized inference; it has recently been applied to Bayesian networks and deep generative models. This paper proposes a system for amortized inference in PPLs. In our system, amortiz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.05735","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":""},"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":"2026-05-18T01:01:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EMeip/y8EniUBzwX6kyXw2Gjbv3OiL71Gd0eXz/42dVWjA7gLA9MFlcbJT8WXEScitN84a0tbh9X6wejs9vQAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T13:53:20.837926Z"},"content_sha256":"fc26f103c5b65c130f4595b771a87bfea42812114bf69b439eff41aa6feb180b","schema_version":"1.0","event_id":"sha256:fc26f103c5b65c130f4595b771a87bfea42812114bf69b439eff41aa6feb180b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ADAIKR3EZHHR34STBOQ4J3UTUF/bundle.json","state_url":"https://pith.science/pith/ADAIKR3EZHHR34STBOQ4J3UTUF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ADAIKR3EZHHR34STBOQ4J3UTUF/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":"2026-05-23T13:53:20Z","links":{"resolver":"https://pith.science/pith/ADAIKR3EZHHR34STBOQ4J3UTUF","bundle":"https://pith.science/pith/ADAIKR3EZHHR34STBOQ4J3UTUF/bundle.json","state":"https://pith.science/pith/ADAIKR3EZHHR34STBOQ4J3UTUF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ADAIKR3EZHHR34STBOQ4J3UTUF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:ADAIKR3EZHHR34STBOQ4J3UTUF","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":"379c383730e3923a84091279dd6dcd58b51c63ca4fcf8eebeff2aa66f9328b4d","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-10-18T18:35:09Z","title_canon_sha256":"1b73861a93fb5bf786c87614ead975a70e188cbe8d88f37f9116d6ff2bf58cf4"},"schema_version":"1.0","source":{"id":"1610.05735","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.05735","created_at":"2026-05-18T01:01:58Z"},{"alias_kind":"arxiv_version","alias_value":"1610.05735v1","created_at":"2026-05-18T01:01:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.05735","created_at":"2026-05-18T01:01:58Z"},{"alias_kind":"pith_short_12","alias_value":"ADAIKR3EZHHR","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_16","alias_value":"ADAIKR3EZHHR34ST","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_8","alias_value":"ADAIKR3E","created_at":"2026-05-18T12:30:07Z"}],"graph_snapshots":[{"event_id":"sha256:fc26f103c5b65c130f4595b771a87bfea42812114bf69b439eff41aa6feb180b","target":"graph","created_at":"2026-05-18T01:01:58Z","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"},"paper":{"abstract_excerpt":"Probabilistic programming languages (PPLs) are a powerful modeling tool, able to represent any computable probability distribution. Unfortunately, probabilistic program inference is often intractable, and existing PPLs mostly rely on expensive, approximate sampling-based methods. To alleviate this problem, one could try to learn from past inferences, so that future inferences run faster. This strategy is known as amortized inference; it has recently been applied to Bayesian networks and deep generative models. This paper proposes a system for amortized inference in PPLs. In our system, amortiz","authors_text":"Daniel Ritchie, Noah D. Goodman, Paul Horsfall","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-10-18T18:35:09Z","title":"Deep Amortized Inference for Probabilistic Programs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.05735","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":"sha256:41a921adf5e4ea862b558afa4ac60baf33e76b46a425f681b78ecc59b5413ef1","target":"record","created_at":"2026-05-18T01:01:58Z","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":"379c383730e3923a84091279dd6dcd58b51c63ca4fcf8eebeff2aa66f9328b4d","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-10-18T18:35:09Z","title_canon_sha256":"1b73861a93fb5bf786c87614ead975a70e188cbe8d88f37f9116d6ff2bf58cf4"},"schema_version":"1.0","source":{"id":"1610.05735","kind":"arxiv","version":1}},"canonical_sha256":"00c0854764c9cf1df2530ba1c4ee93a16582a8dbb95e9a5aa7d6f847dbba31e8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00c0854764c9cf1df2530ba1c4ee93a16582a8dbb95e9a5aa7d6f847dbba31e8","first_computed_at":"2026-05-18T01:01:58.498947Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:01:58.498947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aDXbbFTZWRe2m+D61p4KGWM16GD7UxvWmalTRinH1AfIs4PFIqo8M/Eiyq2mwS4Q2EMsmsbSHPyzz+oXcEJnBA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:01:58.499517Z","signed_message":"canonical_sha256_bytes"},"source_id":"1610.05735","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41a921adf5e4ea862b558afa4ac60baf33e76b46a425f681b78ecc59b5413ef1","sha256:fc26f103c5b65c130f4595b771a87bfea42812114bf69b439eff41aa6feb180b"],"state_sha256":"cc74c8a98fe170372f778a54381b7324c2431a500029c122a4112ae35c625e55"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/Kuj7/EVdK8lvHxg/233preYDYmCTiAn2BVrPCewyUpbR/0Dp5WqSjnDhgLrC/HFozNpj6fOeABngeunG5qMBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T13:53:20.841565Z","bundle_sha256":"118b1cb2e3e5adec74820421e9abb8a55742899767e98507943acb150ed4222d"}}