{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:5WC5NBKCCD66TVMEBJSMZSQAJJ","short_pith_number":"pith:5WC5NBKC","canonical_record":{"source":{"id":"2605.02961","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-03T05:36:52Z","cross_cats_sorted":["cond-mat.stat-mech","cs.AI","cs.SY","eess.SY","math.OC"],"title_canon_sha256":"a2ed6d962a5898c1cd9afbdc381148d95c3d42128a87c9c9d5ae2ffc7c441436","abstract_canon_sha256":"8c2d71ca8a3590411b5500d826071e7a4a1f85a515c54f9191d958edd36d1d64"},"schema_version":"1.0"},"canonical_sha256":"ed85d6854210fde9d5840a64ccca004a652adccafbaf8e38d043ed6bce9ce32e","source":{"kind":"arxiv","id":"2605.02961","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.02961","created_at":"2026-08-13T00:21:22Z"},{"alias_kind":"arxiv_version","alias_value":"2605.02961v2","created_at":"2026-08-13T00:21:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.02961","created_at":"2026-08-13T00:21:22Z"},{"alias_kind":"pith_short_12","alias_value":"5WC5NBKCCD66","created_at":"2026-08-13T00:21:22Z"},{"alias_kind":"pith_short_16","alias_value":"5WC5NBKCCD66TVME","created_at":"2026-08-13T00:21:22Z"},{"alias_kind":"pith_short_8","alias_value":"5WC5NBKC","created_at":"2026-08-13T00:21:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:5WC5NBKCCD66TVMEBJSMZSQAJJ","target":"record","payload":{"canonical_record":{"source":{"id":"2605.02961","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-03T05:36:52Z","cross_cats_sorted":["cond-mat.stat-mech","cs.AI","cs.SY","eess.SY","math.OC"],"title_canon_sha256":"a2ed6d962a5898c1cd9afbdc381148d95c3d42128a87c9c9d5ae2ffc7c441436","abstract_canon_sha256":"8c2d71ca8a3590411b5500d826071e7a4a1f85a515c54f9191d958edd36d1d64"},"schema_version":"1.0"},"canonical_sha256":"ed85d6854210fde9d5840a64ccca004a652adccafbaf8e38d043ed6bce9ce32e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-13T00:21:22.740287Z","signature_b64":"NUkNSYMXtk88Uy6RLk7NWnXSYax3rwtAf51Say7Vz+Hm0/NxdfgCPuJBj5Hitnwwlbfnb8dVNWLrgqixsg8CCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed85d6854210fde9d5840a64ccca004a652adccafbaf8e38d043ed6bce9ce32e","last_reissued_at":"2026-08-13T00:21:22.738784Z","signature_status":"signed_v1","first_computed_at":"2026-08-13T00:21:22.738784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.02961","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":"2026-08-13T00:21:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iLAiwi+o7NHtqabbUzv5S7ZO1kLCmZlrffqWksXV0+KKmEXLrqBfMJMg1PDqPj33LnekFU691GdoB3MzwSB+BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T09:40:04.959790Z"},"content_sha256":"6050a22c10f9e786601841e597e352d53f60e01464c1fa31b4661b916dbe2462","schema_version":"1.0","event_id":"sha256:6050a22c10f9e786601841e597e352d53f60e01464c1fa31b4661b916dbe2462"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:5WC5NBKCCD66TVMEBJSMZSQAJJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Analytic Bridge Diffusions for Controlled Path Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Linear-quadratic-Gaussian control with Gaussian-mixture boundaries supplies closed-form scores, marginals, and protocols for bridge diffusions.","cross_cats":["cond-mat.stat-mech","cs.AI","cs.SY","eess.SY","math.OC"],"primary_cat":"cs.LG","authors_text":"Michael Chertkov","submitted_at":"2026-05-03T05:36:52Z","abstract_excerpt":"Most modern bridge-diffusion methods achieve finite-time transport by specifying an interpolation, Schrodinger-bridge, or stochastic-control objective and then learning the associated score or drift field with a neural network. In contrast, we identify a restricted but sufficiently broad analytically solvable class in which, for a deterministic source and a Gaussian-mixture target, the score and all intermediate marginals are explicit and protocol objectives of the type used in this paper can be differentiated without inner stochastic simulation loops. We recast the classical linear--quadratic"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"In LQ-GM-PID the score, intermediate marginals, and protocol gradients are available in closed form without inner stochastic simulation loops and without neural networks in the optimization loop.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that linear dynamics, Gaussian noise, quadratic costs, and Gaussian-mixture initial/terminal laws are together sufficient to keep the Riccati-based solution closed-form when the terminal target is a prescribed density rather than a point.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"LQ-GM-PID recasts LQG control as a path-integral diffusion problem with Gaussian-mixture terminals to deliver closed-form bridge diffusion quantities for controlled path generation.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Linear-quadratic-Gaussian control with Gaussian-mixture boundaries supplies closed-form scores, marginals, and protocols for bridge diffusions.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"214261ee552933750b4c946a2b81f1a48a0127fac4c3863347b646fe618112ea"},"source":{"id":"2605.02961","kind":"arxiv","version":2},"verdict":{"id":"433c2f52-e589-4346-81a7-7f7340428ea7","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T19:23:50.811643Z","strongest_claim":"In LQ-GM-PID the score, intermediate marginals, and protocol gradients are available in closed form without inner stochastic simulation loops and without neural networks in the optimization loop.","one_line_summary":"LQ-GM-PID recasts LQG control as a path-integral diffusion problem with Gaussian-mixture terminals to deliver closed-form bridge diffusion quantities for controlled path generation.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that linear dynamics, Gaussian noise, quadratic costs, and Gaussian-mixture initial/terminal laws are together sufficient to keep the Riccati-based solution closed-form when the terminal target is a prescribed density rather than a point.","pith_extraction_headline":"Linear-quadratic-Gaussian control with Gaussian-mixture boundaries supplies closed-form scores, marginals, and protocols for bridge diffusions."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.02961/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T17:37:38.980039Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-20T05:01:23.166017Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T17:00:51.361587Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"85bee2f72c3d5198861bd57f0e4276462b4dc44c6dedd4098af1503dad753f05"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":3,"snapshot_sha256":"42cc0477ceb33519fb4cc4172fd4c6e4fec25ba4f1bf605d9b77473ceb3780a7"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"433c2f52-e589-4346-81a7-7f7340428ea7"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-13T00:21:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GHYXCcAdiGXLDhl9eLuWtSSWXVfeM07ZTnB4T2rPa9287sbvUUZmumu/MC8aw9dSmRGgrq2rVzKGL8ymHrrkBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T09:40:04.961003Z"},"content_sha256":"a27073f59a980a9fd304f47ffda96de203593c0f6f14a30c297797fa50876f56","schema_version":"1.0","event_id":"sha256:a27073f59a980a9fd304f47ffda96de203593c0f6f14a30c297797fa50876f56"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5WC5NBKCCD66TVMEBJSMZSQAJJ/bundle.json","state_url":"https://pith.science/pith/5WC5NBKCCD66TVMEBJSMZSQAJJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5WC5NBKCCD66TVMEBJSMZSQAJJ/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":"2026-08-17T09:40:04Z","links":{"resolver":"https://pith.science/pith/5WC5NBKCCD66TVMEBJSMZSQAJJ","bundle":"https://pith.science/pith/5WC5NBKCCD66TVMEBJSMZSQAJJ/bundle.json","state":"https://pith.science/pith/5WC5NBKCCD66TVMEBJSMZSQAJJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5WC5NBKCCD66TVMEBJSMZSQAJJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5WC5NBKCCD66TVMEBJSMZSQAJJ","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":"8c2d71ca8a3590411b5500d826071e7a4a1f85a515c54f9191d958edd36d1d64","cross_cats_sorted":["cond-mat.stat-mech","cs.AI","cs.SY","eess.SY","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-03T05:36:52Z","title_canon_sha256":"a2ed6d962a5898c1cd9afbdc381148d95c3d42128a87c9c9d5ae2ffc7c441436"},"schema_version":"1.0","source":{"id":"2605.02961","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.02961","created_at":"2026-08-13T00:21:22Z"},{"alias_kind":"arxiv_version","alias_value":"2605.02961v2","created_at":"2026-08-13T00:21:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.02961","created_at":"2026-08-13T00:21:22Z"},{"alias_kind":"pith_short_12","alias_value":"5WC5NBKCCD66","created_at":"2026-08-13T00:21:22Z"},{"alias_kind":"pith_short_16","alias_value":"5WC5NBKCCD66TVME","created_at":"2026-08-13T00:21:22Z"},{"alias_kind":"pith_short_8","alias_value":"5WC5NBKC","created_at":"2026-08-13T00:21:22Z"}],"graph_snapshots":[{"event_id":"sha256:a27073f59a980a9fd304f47ffda96de203593c0f6f14a30c297797fa50876f56","target":"graph","created_at":"2026-08-13T00:21:22Z","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":"In LQ-GM-PID the score, intermediate marginals, and protocol gradients are available in closed form without inner stochastic simulation loops and without neural networks in the optimization loop."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that linear dynamics, Gaussian noise, quadratic costs, and Gaussian-mixture initial/terminal laws are together sufficient to keep the Riccati-based solution closed-form when the terminal target is a prescribed density rather than a point."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"LQ-GM-PID recasts LQG control as a path-integral diffusion problem with Gaussian-mixture terminals to deliver closed-form bridge diffusion quantities for controlled path generation."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Linear-quadratic-Gaussian control with Gaussian-mixture boundaries supplies closed-form scores, marginals, and protocols for bridge diffusions."}],"snapshot_sha256":"214261ee552933750b4c946a2b81f1a48a0127fac4c3863347b646fe618112ea"},"formal_canon":{"evidence_count":3,"snapshot_sha256":"42cc0477ceb33519fb4cc4172fd4c6e4fec25ba4f1bf605d9b77473ceb3780a7"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T17:37:38.980039Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-20T05:01:23.166017Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T17:00:51.361587Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.02961/integrity.json","findings":[],"snapshot_sha256":"85bee2f72c3d5198861bd57f0e4276462b4dc44c6dedd4098af1503dad753f05","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most modern bridge-diffusion methods achieve finite-time transport by specifying an interpolation, Schrodinger-bridge, or stochastic-control objective and then learning the associated score or drift field with a neural network. In contrast, we identify a restricted but sufficiently broad analytically solvable class in which, for a deterministic source and a Gaussian-mixture target, the score and all intermediate marginals are explicit and protocol objectives of the type used in this paper can be differentiated without inner stochastic simulation loops. We recast the classical linear--quadratic","authors_text":"Michael Chertkov","cross_cats":["cond-mat.stat-mech","cs.AI","cs.SY","eess.SY","math.OC"],"headline":"Linear-quadratic-Gaussian control with Gaussian-mixture boundaries supplies closed-form scores, marginals, and protocols for bridge diffusions.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-03T05:36:52Z","title":"Analytic Bridge Diffusions for Controlled Path Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.02961","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-08T19:23:50.811643Z","id":"433c2f52-e589-4346-81a7-7f7340428ea7","model_set":{"reader":"grok-4.3"},"one_line_summary":"LQ-GM-PID recasts LQG control as a path-integral diffusion problem with Gaussian-mixture terminals to deliver closed-form bridge diffusion quantities for controlled path generation.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Linear-quadratic-Gaussian control with Gaussian-mixture boundaries supplies closed-form scores, marginals, and protocols for bridge diffusions.","strongest_claim":"In LQ-GM-PID the score, intermediate marginals, and protocol gradients are available in closed form without inner stochastic simulation loops and without neural networks in the optimization loop.","weakest_assumption":"The assumption that linear dynamics, Gaussian noise, quadratic costs, and Gaussian-mixture initial/terminal laws are together sufficient to keep the Riccati-based solution closed-form when the terminal target is a prescribed density rather than a point."}},"verdict_id":"433c2f52-e589-4346-81a7-7f7340428ea7"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6050a22c10f9e786601841e597e352d53f60e01464c1fa31b4661b916dbe2462","target":"record","created_at":"2026-08-13T00:21:22Z","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":"8c2d71ca8a3590411b5500d826071e7a4a1f85a515c54f9191d958edd36d1d64","cross_cats_sorted":["cond-mat.stat-mech","cs.AI","cs.SY","eess.SY","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-03T05:36:52Z","title_canon_sha256":"a2ed6d962a5898c1cd9afbdc381148d95c3d42128a87c9c9d5ae2ffc7c441436"},"schema_version":"1.0","source":{"id":"2605.02961","kind":"arxiv","version":2}},"canonical_sha256":"ed85d6854210fde9d5840a64ccca004a652adccafbaf8e38d043ed6bce9ce32e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed85d6854210fde9d5840a64ccca004a652adccafbaf8e38d043ed6bce9ce32e","first_computed_at":"2026-08-13T00:21:22.738784Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-13T00:21:22.738784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NUkNSYMXtk88Uy6RLk7NWnXSYax3rwtAf51Say7Vz+Hm0/NxdfgCPuJBj5Hitnwwlbfnb8dVNWLrgqixsg8CCw==","signature_status":"signed_v1","signed_at":"2026-08-13T00:21:22.740287Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.02961","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6050a22c10f9e786601841e597e352d53f60e01464c1fa31b4661b916dbe2462","sha256:a27073f59a980a9fd304f47ffda96de203593c0f6f14a30c297797fa50876f56"],"state_sha256":"1dccbcb76f50d0101836a4e25db08c6f30469159b00684703ab262c365004db1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0cda0xOJsJfCkca6mfNKPPL9DWbK4/vi5UwRYhA6bBvGXScW7ShktGYTL+wlyuAvbfDNQllqp/eeeVh41/ytDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T09:40:04.968054Z","bundle_sha256":"246e1586ed11b0b3ec8401efca4c615067720882ca69a58401585c73450631b3"}}