{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:DLZRE7UOHO4CBDC43WGNHLTDYD","short_pith_number":"pith:DLZRE7UO","canonical_record":{"source":{"id":"2601.18175","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-01-26T05:54:39Z","cross_cats_sorted":["cs.LG","cs.SY","eess.SY","stat.ML"],"title_canon_sha256":"5f0156d8c79911266459b58e35ac4057213e45433ba1d7ec387e2861f080f1ec","abstract_canon_sha256":"ada8455ad063d0c7677b253c9bf8f341461af4b0316780f1975f29ed8325c396"},"schema_version":"1.0"},"canonical_sha256":"1af3127e8e3bb8208c5cdd8cd3ae63c0fdf9a75e0d866b8fa138ebdc098fdb8f","source":{"kind":"arxiv","id":"2601.18175","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.18175","created_at":"2026-06-04T00:06:50Z"},{"alias_kind":"arxiv_version","alias_value":"2601.18175v2","created_at":"2026-06-04T00:06:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.18175","created_at":"2026-06-04T00:06:50Z"},{"alias_kind":"pith_short_12","alias_value":"DLZRE7UOHO4C","created_at":"2026-06-04T00:06:50Z"},{"alias_kind":"pith_short_16","alias_value":"DLZRE7UOHO4CBDC4","created_at":"2026-06-04T00:06:50Z"},{"alias_kind":"pith_short_8","alias_value":"DLZRE7UO","created_at":"2026-06-04T00:06:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:DLZRE7UOHO4CBDC43WGNHLTDYD","target":"record","payload":{"canonical_record":{"source":{"id":"2601.18175","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-01-26T05:54:39Z","cross_cats_sorted":["cs.LG","cs.SY","eess.SY","stat.ML"],"title_canon_sha256":"5f0156d8c79911266459b58e35ac4057213e45433ba1d7ec387e2861f080f1ec","abstract_canon_sha256":"ada8455ad063d0c7677b253c9bf8f341461af4b0316780f1975f29ed8325c396"},"schema_version":"1.0"},"canonical_sha256":"1af3127e8e3bb8208c5cdd8cd3ae63c0fdf9a75e0d866b8fa138ebdc098fdb8f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T00:06:50.611858Z","signature_b64":"/c82ZvsZhZGAl87b/Ygk0d8WpRw9/9GeSt3tUTDaBrnL6D+9suwnqYnCYknPpeqob41Y0KeiHGvzlfFY1xNoAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1af3127e8e3bb8208c5cdd8cd3ae63c0fdf9a75e0d866b8fa138ebdc098fdb8f","last_reissued_at":"2026-06-04T00:06:50.611361Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T00:06:50.611361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2601.18175","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":"2026-06-04T00:06:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dgas+tqYcvvpIZwalkGDkh1OhKW45aIQE5QnioX/At4j/rupWM5sLVWrlPpddzKlgaphH5+6yNY0VeBjZj0sAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T12:32:04.372608Z"},"content_sha256":"76518fb489e8c6417cb5f966a63258266b9af94a1c92a151892ca69c6175fe3e","schema_version":"1.0","event_id":"sha256:76518fb489e8c6417cb5f966a63258266b9af94a1c92a151892ca69c6175fe3e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:DLZRE7UOHO4CBDC43WGNHLTDYD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Success Conditioning as Policy Improvement: The Optimization Problem Solved by Imitating Success","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SY","eess.SY","stat.ML"],"primary_cat":"cs.AI","authors_text":"Daniel Russo","submitted_at":"2026-01-26T05:54:39Z","abstract_excerpt":"A widely used technique for improving policies is success conditioning, in which one collects trajectories, identifies those that achieve a desired outcome, and updates the policy to imitate the actions taken along successful trajectories. This principle appears under many names -- rejection sampling with SFT, goal-conditioned RL, Decision Transformers -- yet what optimization problem it solves, if any, has remained unclear. We prove that success conditioning exactly solves a trust-region optimization problem, maximizing policy improvement subject to a $\\chi^2$ divergence constraint whose radi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.18175","kind":"arxiv","version":2},"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/2601.18175/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":"2026-06-04T00:06:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"04Ns6arwn6Z3o6a/xwr/i20foSDSI65/o+Omo9bmvH0nir2+Rln9PARJndepU7DcLg2OK6o+nza/ukmZQ64uBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T12:32:04.373471Z"},"content_sha256":"e7fd3e942da7901345b82d1327cbbb1f3b4947ccbec75183d77a8f20b65251b2","schema_version":"1.0","event_id":"sha256:e7fd3e942da7901345b82d1327cbbb1f3b4947ccbec75183d77a8f20b65251b2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DLZRE7UOHO4CBDC43WGNHLTDYD/bundle.json","state_url":"https://pith.science/pith/DLZRE7UOHO4CBDC43WGNHLTDYD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DLZRE7UOHO4CBDC43WGNHLTDYD/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":"2026-08-21T12:32:04Z","links":{"resolver":"https://pith.science/pith/DLZRE7UOHO4CBDC43WGNHLTDYD","bundle":"https://pith.science/pith/DLZRE7UOHO4CBDC43WGNHLTDYD/bundle.json","state":"https://pith.science/pith/DLZRE7UOHO4CBDC43WGNHLTDYD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DLZRE7UOHO4CBDC43WGNHLTDYD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DLZRE7UOHO4CBDC43WGNHLTDYD","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":"ada8455ad063d0c7677b253c9bf8f341461af4b0316780f1975f29ed8325c396","cross_cats_sorted":["cs.LG","cs.SY","eess.SY","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-01-26T05:54:39Z","title_canon_sha256":"5f0156d8c79911266459b58e35ac4057213e45433ba1d7ec387e2861f080f1ec"},"schema_version":"1.0","source":{"id":"2601.18175","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.18175","created_at":"2026-06-04T00:06:50Z"},{"alias_kind":"arxiv_version","alias_value":"2601.18175v2","created_at":"2026-06-04T00:06:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.18175","created_at":"2026-06-04T00:06:50Z"},{"alias_kind":"pith_short_12","alias_value":"DLZRE7UOHO4C","created_at":"2026-06-04T00:06:50Z"},{"alias_kind":"pith_short_16","alias_value":"DLZRE7UOHO4CBDC4","created_at":"2026-06-04T00:06:50Z"},{"alias_kind":"pith_short_8","alias_value":"DLZRE7UO","created_at":"2026-06-04T00:06:50Z"}],"graph_snapshots":[{"event_id":"sha256:e7fd3e942da7901345b82d1327cbbb1f3b4947ccbec75183d77a8f20b65251b2","target":"graph","created_at":"2026-06-04T00:06:50Z","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/2601.18175/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A widely used technique for improving policies is success conditioning, in which one collects trajectories, identifies those that achieve a desired outcome, and updates the policy to imitate the actions taken along successful trajectories. This principle appears under many names -- rejection sampling with SFT, goal-conditioned RL, Decision Transformers -- yet what optimization problem it solves, if any, has remained unclear. We prove that success conditioning exactly solves a trust-region optimization problem, maximizing policy improvement subject to a $\\chi^2$ divergence constraint whose radi","authors_text":"Daniel Russo","cross_cats":["cs.LG","cs.SY","eess.SY","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-01-26T05:54:39Z","title":"Success Conditioning as Policy Improvement: The Optimization Problem Solved by Imitating Success"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.18175","kind":"arxiv","version":2},"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":"sha256:76518fb489e8c6417cb5f966a63258266b9af94a1c92a151892ca69c6175fe3e","target":"record","created_at":"2026-06-04T00:06:50Z","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":"ada8455ad063d0c7677b253c9bf8f341461af4b0316780f1975f29ed8325c396","cross_cats_sorted":["cs.LG","cs.SY","eess.SY","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-01-26T05:54:39Z","title_canon_sha256":"5f0156d8c79911266459b58e35ac4057213e45433ba1d7ec387e2861f080f1ec"},"schema_version":"1.0","source":{"id":"2601.18175","kind":"arxiv","version":2}},"canonical_sha256":"1af3127e8e3bb8208c5cdd8cd3ae63c0fdf9a75e0d866b8fa138ebdc098fdb8f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1af3127e8e3bb8208c5cdd8cd3ae63c0fdf9a75e0d866b8fa138ebdc098fdb8f","first_computed_at":"2026-06-04T00:06:50.611361Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T00:06:50.611361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/c82ZvsZhZGAl87b/Ygk0d8WpRw9/9GeSt3tUTDaBrnL6D+9suwnqYnCYknPpeqob41Y0KeiHGvzlfFY1xNoAg==","signature_status":"signed_v1","signed_at":"2026-06-04T00:06:50.611858Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.18175","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:76518fb489e8c6417cb5f966a63258266b9af94a1c92a151892ca69c6175fe3e","sha256:e7fd3e942da7901345b82d1327cbbb1f3b4947ccbec75183d77a8f20b65251b2"],"state_sha256":"df003513abc8a33839e8344647c24bf768e3042d035ae71d38433507e66b7250"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LBuwM3Dbe5a/dsn55AYUq59NiFQXGTJGyYZUlarwwH+oGk3wKV8ESqMNidUVkh2DPE7MFpimvMR40utc+88qDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T12:32:04.380350Z","bundle_sha256":"92608c7cccd1a1d0b005a8335bd51fae6f80d64ab3d777bc6120198149c70631"}}