{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:YL2UTCIQZH2DETA37TS65VKZVB","short_pith_number":"pith:YL2UTCIQ","canonical_record":{"source":{"id":"2605.08253","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-07T19:05:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8f1de45d5c5fa5cfca37a95d0668f5d2a280f260bae70ef254b4460868c5aead","abstract_canon_sha256":"ad05c7ad54970ab15a01c138808279e97e8b709b2b3d00f6d050b285446159b7"},"schema_version":"1.0"},"canonical_sha256":"c2f5498910c9f4324c1bfce5eed559a84860f86e6108f7c95dee30386050b7ae","source":{"kind":"arxiv","id":"2605.08253","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.08253","created_at":"2026-06-05T00:13:46Z"},{"alias_kind":"arxiv_version","alias_value":"2605.08253v2","created_at":"2026-06-05T00:13:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.08253","created_at":"2026-06-05T00:13:46Z"},{"alias_kind":"pith_short_12","alias_value":"YL2UTCIQZH2D","created_at":"2026-06-05T00:13:46Z"},{"alias_kind":"pith_short_16","alias_value":"YL2UTCIQZH2DETA3","created_at":"2026-06-05T00:13:46Z"},{"alias_kind":"pith_short_8","alias_value":"YL2UTCIQ","created_at":"2026-06-05T00:13:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:YL2UTCIQZH2DETA37TS65VKZVB","target":"record","payload":{"canonical_record":{"source":{"id":"2605.08253","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-07T19:05:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8f1de45d5c5fa5cfca37a95d0668f5d2a280f260bae70ef254b4460868c5aead","abstract_canon_sha256":"ad05c7ad54970ab15a01c138808279e97e8b709b2b3d00f6d050b285446159b7"},"schema_version":"1.0"},"canonical_sha256":"c2f5498910c9f4324c1bfce5eed559a84860f86e6108f7c95dee30386050b7ae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T00:13:46.841300Z","signature_b64":"JBY+ivk4clYB+KeH08cfiAPqB7pd1APHrNkIWq30fbQ84u8KdelHoY46+K25htNmtqwpIu44klxULxwSP9ZkDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2f5498910c9f4324c1bfce5eed559a84860f86e6108f7c95dee30386050b7ae","last_reissued_at":"2026-06-05T00:13:46.840649Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T00:13:46.840649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.08253","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":"2026-06-05T00:13:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9CoaOewLRZCib/qh/btW/88syuyaaAaYhCw4V/MtgTNRAC1e5THYj7uJ0Zsqm2iGqoE9t4t4fJQ5X4caSTd1Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:12:54.583589Z"},"content_sha256":"c4256e939a4cc674b121675154e013ade40449efb6aca13677576dd38ef31087","schema_version":"1.0","event_id":"sha256:c4256e939a4cc674b121675154e013ade40449efb6aca13677576dd38ef31087"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:YL2UTCIQZH2DETA37TS65VKZVB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Path-Coupled Bellman Flows for Distributional Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Path-Coupled Bellman Flows learn return distributions by matching flows along source-consistent paths that couple current and successor distributions through shared noise.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Boyang Xu, Hao Yan, Qing Zou, Siqin Yang","submitted_at":"2026-05-07T19:05:01Z","abstract_excerpt":"Distributional reinforcement learning (DRL) models the full return distribution, but existing finite-support or quantile-based methods rely on projections, while recent flow-based approaches can suffer from \\emph{boundary mismatch} at the flow source or from \\emph{high-variance} bootstrapping when current and successor noises are independent. We propose Path-Coupled Bellman Flows (PCBF), a continuous-time DRL method that learns return distributions with flow matching using \\textbf{source-consistent Bellman-coupled paths}: the current path starts from the required base prior at $t{=}0$, reaches"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"PCBF learns return distributions with flow matching using source-consistent Bellman-coupled paths: the current path starts from the required base prior at t=0, reaches the Bellman target at t=1, and maintains a pathwise affine relation to the successor flow at intermediate times, with a lambda-parameterized control-variate target that trades controlled bias for variance reduction.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the pathwise affine relation and coupling via shared base noise preserve the necessary distributional properties for correct Bellman updates without requiring time-t marginals to satisfy a distributional Bellman fixed point for all t, and that this coupling does not introduce new inconsistencies in the continuous-time flow.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Path-Coupled Bellman Flows use source-consistent Bellman-coupled paths and a lambda-parameterized control-variate to learn return distributions via flow matching, improving fidelity and stability over prior DRL approaches.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Path-Coupled Bellman Flows learn return distributions by matching flows along source-consistent paths that couple current and successor distributions through shared noise.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"c999209a3a003948ddfefab264abec217fd4b1b4105355e3ddf829567aa73d63"},"source":{"id":"2605.08253","kind":"arxiv","version":2},"verdict":{"id":"bfbb9445-33a8-44e6-a159-7e3da3345d02","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T02:03:35.025384Z","strongest_claim":"PCBF learns return distributions with flow matching using source-consistent Bellman-coupled paths: the current path starts from the required base prior at t=0, reaches the Bellman target at t=1, and maintains a pathwise affine relation to the successor flow at intermediate times, with a lambda-parameterized control-variate target that trades controlled bias for variance reduction.","one_line_summary":"Path-Coupled Bellman Flows use source-consistent Bellman-coupled paths and a lambda-parameterized control-variate to learn return distributions via flow matching, improving fidelity and stability over prior DRL approaches.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the pathwise affine relation and coupling via shared base noise preserve the necessary distributional properties for correct Bellman updates without requiring time-t marginals to satisfy a distributional Bellman fixed point for all t, and that this coupling does not introduce new inconsistencies in the continuous-time flow.","pith_extraction_headline":"Path-Coupled Bellman Flows learn return distributions by matching flows along source-consistent paths that couple current and successor distributions through shared noise."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.08253/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T12:02:03.721352Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-20T07:33:40.011882Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T17:31:19.623104Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T12:20:49.106433Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"a542f4b50cbea51e8d3eaa106e7723854b849f88c5e79bd802d127aaff35983c"},"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":"bfbb9445-33a8-44e6-a159-7e3da3345d02"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-05T00:13:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"czQVBJ2zagxWQ4kShpVB6d5fZtAEUm4hLm75eigZxX0ib0pzUoeupkVwqdumPUuFk9SahSkjuUgtU6JUb9mrCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:12:54.584086Z"},"content_sha256":"b35e68cb027f9540c2671380082662c6dce2f01fde1cdc82557c1d233f0db861","schema_version":"1.0","event_id":"sha256:b35e68cb027f9540c2671380082662c6dce2f01fde1cdc82557c1d233f0db861"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YL2UTCIQZH2DETA37TS65VKZVB/bundle.json","state_url":"https://pith.science/pith/YL2UTCIQZH2DETA37TS65VKZVB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YL2UTCIQZH2DETA37TS65VKZVB/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":"2026-07-07T08:12:54Z","links":{"resolver":"https://pith.science/pith/YL2UTCIQZH2DETA37TS65VKZVB","bundle":"https://pith.science/pith/YL2UTCIQZH2DETA37TS65VKZVB/bundle.json","state":"https://pith.science/pith/YL2UTCIQZH2DETA37TS65VKZVB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YL2UTCIQZH2DETA37TS65VKZVB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YL2UTCIQZH2DETA37TS65VKZVB","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":"ad05c7ad54970ab15a01c138808279e97e8b709b2b3d00f6d050b285446159b7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-07T19:05:01Z","title_canon_sha256":"8f1de45d5c5fa5cfca37a95d0668f5d2a280f260bae70ef254b4460868c5aead"},"schema_version":"1.0","source":{"id":"2605.08253","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.08253","created_at":"2026-06-05T00:13:46Z"},{"alias_kind":"arxiv_version","alias_value":"2605.08253v2","created_at":"2026-06-05T00:13:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.08253","created_at":"2026-06-05T00:13:46Z"},{"alias_kind":"pith_short_12","alias_value":"YL2UTCIQZH2D","created_at":"2026-06-05T00:13:46Z"},{"alias_kind":"pith_short_16","alias_value":"YL2UTCIQZH2DETA3","created_at":"2026-06-05T00:13:46Z"},{"alias_kind":"pith_short_8","alias_value":"YL2UTCIQ","created_at":"2026-06-05T00:13:46Z"}],"graph_snapshots":[{"event_id":"sha256:b35e68cb027f9540c2671380082662c6dce2f01fde1cdc82557c1d233f0db861","target":"graph","created_at":"2026-06-05T00:13:46Z","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":"PCBF learns return distributions with flow matching using source-consistent Bellman-coupled paths: the current path starts from the required base prior at t=0, reaches the Bellman target at t=1, and maintains a pathwise affine relation to the successor flow at intermediate times, with a lambda-parameterized control-variate target that trades controlled bias for variance reduction."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the pathwise affine relation and coupling via shared base noise preserve the necessary distributional properties for correct Bellman updates without requiring time-t marginals to satisfy a distributional Bellman fixed point for all t, and that this coupling does not introduce new inconsistencies in the continuous-time flow."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Path-Coupled Bellman Flows use source-consistent Bellman-coupled paths and a lambda-parameterized control-variate to learn return distributions via flow matching, improving fidelity and stability over prior DRL approaches."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Path-Coupled Bellman Flows learn return distributions by matching flows along source-consistent paths that couple current and successor distributions through shared noise."}],"snapshot_sha256":"c999209a3a003948ddfefab264abec217fd4b1b4105355e3ddf829567aa73d63"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T12:02:03.721352Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T07:33:40.011882Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T17:31:19.623104Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T12:20:49.106433Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.08253/integrity.json","findings":[],"snapshot_sha256":"a542f4b50cbea51e8d3eaa106e7723854b849f88c5e79bd802d127aaff35983c","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Distributional reinforcement learning (DRL) models the full return distribution, but existing finite-support or quantile-based methods rely on projections, while recent flow-based approaches can suffer from \\emph{boundary mismatch} at the flow source or from \\emph{high-variance} bootstrapping when current and successor noises are independent. We propose Path-Coupled Bellman Flows (PCBF), a continuous-time DRL method that learns return distributions with flow matching using \\textbf{source-consistent Bellman-coupled paths}: the current path starts from the required base prior at $t{=}0$, reaches","authors_text":"Boyang Xu, Hao Yan, Qing Zou, Siqin Yang","cross_cats":["cs.AI"],"headline":"Path-Coupled Bellman Flows learn return distributions by matching flows along source-consistent paths that couple current and successor distributions through shared noise.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-07T19:05:01Z","title":"Path-Coupled Bellman Flows for Distributional Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.08253","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-12T02:03:35.025384Z","id":"bfbb9445-33a8-44e6-a159-7e3da3345d02","model_set":{"reader":"grok-4.3"},"one_line_summary":"Path-Coupled Bellman Flows use source-consistent Bellman-coupled paths and a lambda-parameterized control-variate to learn return distributions via flow matching, improving fidelity and stability over prior DRL approaches.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Path-Coupled Bellman Flows learn return distributions by matching flows along source-consistent paths that couple current and successor distributions through shared noise.","strongest_claim":"PCBF learns return distributions with flow matching using source-consistent Bellman-coupled paths: the current path starts from the required base prior at t=0, reaches the Bellman target at t=1, and maintains a pathwise affine relation to the successor flow at intermediate times, with a lambda-parameterized control-variate target that trades controlled bias for variance reduction.","weakest_assumption":"That the pathwise affine relation and coupling via shared base noise preserve the necessary distributional properties for correct Bellman updates without requiring time-t marginals to satisfy a distributional Bellman fixed point for all t, and that this coupling does not introduce new inconsistencies in the continuous-time flow."}},"verdict_id":"bfbb9445-33a8-44e6-a159-7e3da3345d02"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c4256e939a4cc674b121675154e013ade40449efb6aca13677576dd38ef31087","target":"record","created_at":"2026-06-05T00:13:46Z","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":"ad05c7ad54970ab15a01c138808279e97e8b709b2b3d00f6d050b285446159b7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-07T19:05:01Z","title_canon_sha256":"8f1de45d5c5fa5cfca37a95d0668f5d2a280f260bae70ef254b4460868c5aead"},"schema_version":"1.0","source":{"id":"2605.08253","kind":"arxiv","version":2}},"canonical_sha256":"c2f5498910c9f4324c1bfce5eed559a84860f86e6108f7c95dee30386050b7ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c2f5498910c9f4324c1bfce5eed559a84860f86e6108f7c95dee30386050b7ae","first_computed_at":"2026-06-05T00:13:46.840649Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T00:13:46.840649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JBY+ivk4clYB+KeH08cfiAPqB7pd1APHrNkIWq30fbQ84u8KdelHoY46+K25htNmtqwpIu44klxULxwSP9ZkDA==","signature_status":"signed_v1","signed_at":"2026-06-05T00:13:46.841300Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.08253","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c4256e939a4cc674b121675154e013ade40449efb6aca13677576dd38ef31087","sha256:b35e68cb027f9540c2671380082662c6dce2f01fde1cdc82557c1d233f0db861"],"state_sha256":"0606ad0cd6edff852cf2cde64b0f980f33519ad4b2d279137444cc782b1c6e58"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mgPxXnx8WoU13gtLjTIHEuWLvu55TX+IR7sbyG+Kpl3eJCbigKKuoxpPptlbnFyLqpKeHlYOq/OpnA8wnaTOAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:12:54.586419Z","bundle_sha256":"b3f889b4b8caecc3ff4bc82b471aab18603dd5d8185cd6232a566addc523719d"}}