{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:2XH64ZE5WWWXQHJZU5W6QVLGAX","short_pith_number":"pith:2XH64ZE5","canonical_record":{"source":{"id":"2606.07400","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T15:41:25Z","cross_cats_sorted":[],"title_canon_sha256":"8daa963420096195e73878fa9b47de6e9312b6caa8ddaab24c1d0912dafc372f","abstract_canon_sha256":"506619d7b39541c1f397829bd6508eac895c52345f749a4f03d7f080e1738eef"},"schema_version":"1.0"},"canonical_sha256":"d5cfee649db5ad781d39a76de8556605f6590585979a462b0281dba6f26817e6","source":{"kind":"arxiv","id":"2606.07400","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07400","created_at":"2026-06-08T01:05:24Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07400v1","created_at":"2026-06-08T01:05:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07400","created_at":"2026-06-08T01:05:24Z"},{"alias_kind":"pith_short_12","alias_value":"2XH64ZE5WWWX","created_at":"2026-06-08T01:05:24Z"},{"alias_kind":"pith_short_16","alias_value":"2XH64ZE5WWWXQHJZ","created_at":"2026-06-08T01:05:24Z"},{"alias_kind":"pith_short_8","alias_value":"2XH64ZE5","created_at":"2026-06-08T01:05:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:2XH64ZE5WWWXQHJZU5W6QVLGAX","target":"record","payload":{"canonical_record":{"source":{"id":"2606.07400","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T15:41:25Z","cross_cats_sorted":[],"title_canon_sha256":"8daa963420096195e73878fa9b47de6e9312b6caa8ddaab24c1d0912dafc372f","abstract_canon_sha256":"506619d7b39541c1f397829bd6508eac895c52345f749a4f03d7f080e1738eef"},"schema_version":"1.0"},"canonical_sha256":"d5cfee649db5ad781d39a76de8556605f6590585979a462b0281dba6f26817e6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:05:24.891125Z","signature_b64":"RQBFknq7lRvvEELh4qEN77LKIdKd6VZKul+RmhJqkw5dh+mJ2DScFoYDN+zKHvSBqTrKPrYxVeKG4JgiWyGGDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5cfee649db5ad781d39a76de8556605f6590585979a462b0281dba6f26817e6","last_reissued_at":"2026-06-08T01:05:24.890235Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:05:24.890235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.07400","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":"2026-06-08T01:05:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QATFwoR5PpZRSClMUtZp7u/0L1z0OBW+9C1/aYFuMqA9R4Ty0ln5zHemZKHfNJaokZDaYiqG7VHb75Lp5fxTCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T03:47:43.843666Z"},"content_sha256":"113d730bd01ecabd30e7bad5af9afb4f5e5f617ddd95174494df3a33d82a9644","schema_version":"1.0","event_id":"sha256:113d730bd01ecabd30e7bad5af9afb4f5e5f617ddd95174494df3a33d82a9644"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:2XH64ZE5WWWXQHJZU5W6QVLGAX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generative Modeling of Discrete Latent Structures via Dynamic Policy Gradients","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ge Liu, Mohammed El-Kebir, Stefan Ivanovic","submitted_at":"2026-06-05T15:41:25Z","abstract_excerpt":"Many scientific problems require inferring unobserved mechanistic latent states from indirect observations. While classical approaches, including expectation maximization, do not scale to combinatorially large spaces, deep learning approaches such as variational autoencoders typically form artificial latent states rather than reconstructing the mechanistic ground-truth states. Here, we introduce GReinSS, a policy learning framework that uses dynamically rescaled rewards to learn latent state distributions that maximize the observed data likelihood. We show that GReinSS accurately reconstructs "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07400","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/2606.07400/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":"2026-06-08T01:05:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CuTe9sLMzMkpXc73jJpKT9K/+v04t3Cfu7+eNQvP5UXNSrkIc6uuYUgpcatvLrJqo4LxsvU0sonQ2T/AargiBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T03:47:43.844426Z"},"content_sha256":"a18c8c17f1a7a6746fe015d1471753330a560be69afd2a082d8887bbbdfdb3ad","schema_version":"1.0","event_id":"sha256:a18c8c17f1a7a6746fe015d1471753330a560be69afd2a082d8887bbbdfdb3ad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2XH64ZE5WWWXQHJZU5W6QVLGAX/bundle.json","state_url":"https://pith.science/pith/2XH64ZE5WWWXQHJZU5W6QVLGAX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2XH64ZE5WWWXQHJZU5W6QVLGAX/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":"2026-06-11T03:47:43Z","links":{"resolver":"https://pith.science/pith/2XH64ZE5WWWXQHJZU5W6QVLGAX","bundle":"https://pith.science/pith/2XH64ZE5WWWXQHJZU5W6QVLGAX/bundle.json","state":"https://pith.science/pith/2XH64ZE5WWWXQHJZU5W6QVLGAX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2XH64ZE5WWWXQHJZU5W6QVLGAX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2XH64ZE5WWWXQHJZU5W6QVLGAX","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":"506619d7b39541c1f397829bd6508eac895c52345f749a4f03d7f080e1738eef","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T15:41:25Z","title_canon_sha256":"8daa963420096195e73878fa9b47de6e9312b6caa8ddaab24c1d0912dafc372f"},"schema_version":"1.0","source":{"id":"2606.07400","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07400","created_at":"2026-06-08T01:05:24Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07400v1","created_at":"2026-06-08T01:05:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07400","created_at":"2026-06-08T01:05:24Z"},{"alias_kind":"pith_short_12","alias_value":"2XH64ZE5WWWX","created_at":"2026-06-08T01:05:24Z"},{"alias_kind":"pith_short_16","alias_value":"2XH64ZE5WWWXQHJZ","created_at":"2026-06-08T01:05:24Z"},{"alias_kind":"pith_short_8","alias_value":"2XH64ZE5","created_at":"2026-06-08T01:05:24Z"}],"graph_snapshots":[{"event_id":"sha256:a18c8c17f1a7a6746fe015d1471753330a560be69afd2a082d8887bbbdfdb3ad","target":"graph","created_at":"2026-06-08T01:05:24Z","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/2606.07400/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many scientific problems require inferring unobserved mechanistic latent states from indirect observations. While classical approaches, including expectation maximization, do not scale to combinatorially large spaces, deep learning approaches such as variational autoencoders typically form artificial latent states rather than reconstructing the mechanistic ground-truth states. Here, we introduce GReinSS, a policy learning framework that uses dynamically rescaled rewards to learn latent state distributions that maximize the observed data likelihood. We show that GReinSS accurately reconstructs ","authors_text":"Ge Liu, Mohammed El-Kebir, Stefan Ivanovic","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T15:41:25Z","title":"Generative Modeling of Discrete Latent Structures via Dynamic Policy Gradients"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07400","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":"sha256:113d730bd01ecabd30e7bad5af9afb4f5e5f617ddd95174494df3a33d82a9644","target":"record","created_at":"2026-06-08T01:05:24Z","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":"506619d7b39541c1f397829bd6508eac895c52345f749a4f03d7f080e1738eef","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T15:41:25Z","title_canon_sha256":"8daa963420096195e73878fa9b47de6e9312b6caa8ddaab24c1d0912dafc372f"},"schema_version":"1.0","source":{"id":"2606.07400","kind":"arxiv","version":1}},"canonical_sha256":"d5cfee649db5ad781d39a76de8556605f6590585979a462b0281dba6f26817e6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d5cfee649db5ad781d39a76de8556605f6590585979a462b0281dba6f26817e6","first_computed_at":"2026-06-08T01:05:24.890235Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T01:05:24.890235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RQBFknq7lRvvEELh4qEN77LKIdKd6VZKul+RmhJqkw5dh+mJ2DScFoYDN+zKHvSBqTrKPrYxVeKG4JgiWyGGDQ==","signature_status":"signed_v1","signed_at":"2026-06-08T01:05:24.891125Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.07400","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:113d730bd01ecabd30e7bad5af9afb4f5e5f617ddd95174494df3a33d82a9644","sha256:a18c8c17f1a7a6746fe015d1471753330a560be69afd2a082d8887bbbdfdb3ad"],"state_sha256":"27de8b57ff2c19a10dff80635cf009f5cee74f0cb22e93d701e39716c4586679"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t9JF90IvllJiQZccLgXsS8Tr1nK0idMMyFTTeBIiXmKE6ZuzHEc8ZjDEMbwvOQHRjBySGPFhBwrG5dGE6DosBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T03:47:43.848311Z","bundle_sha256":"2affe235f3d9f683f0f2ea63acf2b85291afdd50a5d9a594c067daf4177c6ae8"}}