{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RPVPFU2JO7B23WCUNHIUIXCXTC","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":"34079c9295c1885dc93323d765ffdc717e05761879e479d3b2d231944c3c02d6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-05-17T05:41:01Z","title_canon_sha256":"6af38eec6ac56c9daa9e2771420cfc020187e38bd974263dee9327ac3819c828"},"schema_version":"1.0","source":{"id":"2605.17271","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17271","created_at":"2026-05-20T00:03:49Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17271v1","created_at":"2026-05-20T00:03:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17271","created_at":"2026-05-20T00:03:49Z"},{"alias_kind":"pith_short_12","alias_value":"RPVPFU2JO7B2","created_at":"2026-05-20T00:03:49Z"},{"alias_kind":"pith_short_16","alias_value":"RPVPFU2JO7B23WCU","created_at":"2026-05-20T00:03:49Z"},{"alias_kind":"pith_short_8","alias_value":"RPVPFU2J","created_at":"2026-05-20T00:03:49Z"}],"graph_snapshots":[{"event_id":"sha256:3c6890beaf8e969aada56ae491ea13b1c5f302be970c502abef9233c1bcdeba3","target":"graph","created_at":"2026-05-20T00:03:49Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"We establish dynamic programming principles for both the original and relaxed formulations, prove that the relaxed problem converges to the original bi-causal OT problem as the penalty grows, and derive explicit policy-gradient representations for the relaxed objective. Building on these results, we propose a practical policy-gradient algorithm with unbiased mini-batch estimators, variance reduction, and nonasymptotic regret guarantees."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The framework assumes that the KL relaxation preserves the recursive structure of the bi-causal problem sufficiently for dynamic programming and policy gradient methods to apply directly, and that marginal laws can be sampled to enable the stochastic optimization procedure described."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A KL-relaxed formulation of bi-causal optimal transport is solved via policy gradients with proven convergence to the original problem and nonasymptotic regret guarantees for the resulting algorithm."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"KL relaxation turns bi-causal optimal transport into a policy-gradient problem"}],"snapshot_sha256":"9dee8f7222e87e2119b5d5502b43a9a10ff7b3a725594bf29f7b23b5349d46fe"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"0d510d0506d2ab9762e536e8083e2e38ddeb5ba1fd4029059a5cf1789c2ca1b9"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T23:31:20.216522Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T23:13:21.007701Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T22:01:57.836529Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.778072Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.17271/integrity.json","findings":[],"snapshot_sha256":"533ace73c6130e27e4071f3b93844809ddf63219741c0afb53d5e879dd24b21c","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Bi-causal optimal transport (OT) is a natural framework for comparing and coupling stochastic processes under nonanticipative information constraints, with important applications in robust finance, sequential uncertainty quantification, and multistage stochastic optimization. In particular, a learned bi-causal coupling naturally serves as a simulator for generating joint sample paths that respect both prescribed marginal laws and the underlying information flow. Its practical use, however, is limited by the computational difficulty of enforcing bi-causal coupling constraints over path space, e","authors_text":"Haoyang Cao, Jesse Hoekstra, Renyuan Xu, Ruixun Zhang, Yumin Xu","cross_cats":["cs.LG"],"headline":"KL relaxation turns bi-causal optimal transport into a policy-gradient problem","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-05-17T05:41:01Z","title":"Scalable Bi-causal Optimal Transport via KL Relaxation and Policy Gradients"},"references":{"count":23,"internal_anchors":0,"resolved_work":23,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Here, the first inequality follows fromJπ n+1 ≥V n+1 and the monotonicity of operatorQπ n+1, and the last inequality follows from (15)","work_id":"95dd3457-e2d9-4af2-b89c-d36057606821","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"NX n=0 cn(Yn, Y ′ n) # =E π","work_id":"92e2157a-694f-45d2-9eac-bed3823b4161","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"43 The definition ofWbc in (5) as the infimum overπ∈ΠΠΠbc yieldsW bc(µ, µ′)≥inf π0∈Π(µ0,µ′ 0) Eπ0[V0]","work_id":"c18fb885-1533-4079-8484-d7398c1e9c12","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Notice that (A.3) holds for any initial coupling inΠ(µ0, µ′ 0)","work_id":"5b93d9f2-82ae-4ce9-ae32-b5e2e90bcdeb","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"To establish the second equivalent representation, notice thatγ ϵ ∈ M bc(µ, µ′)⊂Π ΠΠbc and Wbc(µ, µ′) = inf π0∈Π(µ0,µ′","work_id":"64f761fb-aff7-4675-ac60-d1ad02cfc366","year":null}],"snapshot_sha256":"62ca0d2ec3fc558ce01777bcf5f3d855e632f47dc06d0e8c47267ec71f3bb2bd"},"source":{"id":"2605.17271","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T23:06:42.062019Z","id":"a35e1a80-85ed-45cb-9e7b-cbefb76d5d55","model_set":{"reader":"grok-4.3"},"one_line_summary":"A KL-relaxed formulation of bi-causal optimal transport is solved via policy gradients with proven convergence to the original problem and nonasymptotic regret guarantees for the resulting algorithm.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"KL relaxation turns bi-causal optimal transport into a policy-gradient problem","strongest_claim":"We establish dynamic programming principles for both the original and relaxed formulations, prove that the relaxed problem converges to the original bi-causal OT problem as the penalty grows, and derive explicit policy-gradient representations for the relaxed objective. Building on these results, we propose a practical policy-gradient algorithm with unbiased mini-batch estimators, variance reduction, and nonasymptotic regret guarantees.","weakest_assumption":"The framework assumes that the KL relaxation preserves the recursive structure of the bi-causal problem sufficiently for dynamic programming and policy gradient methods to apply directly, and that marginal laws can be sampled to enable the stochastic optimization procedure described."}},"verdict_id":"a35e1a80-85ed-45cb-9e7b-cbefb76d5d55"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:63d5a1909a25962b1f39a15290c7ff689b61f7308f4596d1187f6f01b7b7d3e4","target":"record","created_at":"2026-05-20T00:03:49Z","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":"34079c9295c1885dc93323d765ffdc717e05761879e479d3b2d231944c3c02d6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-05-17T05:41:01Z","title_canon_sha256":"6af38eec6ac56c9daa9e2771420cfc020187e38bd974263dee9327ac3819c828"},"schema_version":"1.0","source":{"id":"2605.17271","kind":"arxiv","version":1}},"canonical_sha256":"8beaf2d34977c3add85469d1445c579894158e37994a26423efae65a99af3cf3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8beaf2d34977c3add85469d1445c579894158e37994a26423efae65a99af3cf3","first_computed_at":"2026-05-20T00:03:49.075129Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:49.075129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O1j5Zn51A0kq8YE7QefHab/RbMBOWxRCQy5e/Vbfy5I8EZBmvnBB4k33TMnzo2G2LI+kv1afcMC9FQraV+k/AA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:49.075984Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.17271","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:63d5a1909a25962b1f39a15290c7ff689b61f7308f4596d1187f6f01b7b7d3e4","sha256:3c6890beaf8e969aada56ae491ea13b1c5f302be970c502abef9233c1bcdeba3"],"state_sha256":"63e6f9d187f2966e84ec396292b5b89e926a39a60f38ce19b750d38d54ead82b"}