{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XWTECPAJ3L6TVL2WZPXPU2IJWQ","short_pith_number":"pith:XWTECPAJ","canonical_record":{"source":{"id":"2505.22866","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T20:59:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e31a629278a966a2b60d2e4c3aa3f35b774d53ba2766516dd5c4b6966ba5946e","abstract_canon_sha256":"44aa202c570fdf5b08ce23f7aca96b52c967c39507bb6c42c68e29378174487e"},"schema_version":"1.0"},"canonical_sha256":"bda6413c09dafd3aaf56cbeefa6909b40cdce5803571a8b02966401a20386ecf","source":{"kind":"arxiv","id":"2505.22866","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22866","created_at":"2026-07-05T11:11:51Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22866v1","created_at":"2026-07-05T11:11:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22866","created_at":"2026-07-05T11:11:51Z"},{"alias_kind":"pith_short_12","alias_value":"XWTECPAJ3L6T","created_at":"2026-07-05T11:11:51Z"},{"alias_kind":"pith_short_16","alias_value":"XWTECPAJ3L6TVL2W","created_at":"2026-07-05T11:11:51Z"},{"alias_kind":"pith_short_8","alias_value":"XWTECPAJ","created_at":"2026-07-05T11:11:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XWTECPAJ3L6TVL2WZPXPU2IJWQ","target":"record","payload":{"canonical_record":{"source":{"id":"2505.22866","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T20:59:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e31a629278a966a2b60d2e4c3aa3f35b774d53ba2766516dd5c4b6966ba5946e","abstract_canon_sha256":"44aa202c570fdf5b08ce23f7aca96b52c967c39507bb6c42c68e29378174487e"},"schema_version":"1.0"},"canonical_sha256":"bda6413c09dafd3aaf56cbeefa6909b40cdce5803571a8b02966401a20386ecf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:51.103535Z","signature_b64":"wtX7iPI19oN98Vw73hYhZeOQtaJm7iIqj5pwHXTNylfVoQhT8JkUpN7AB9haNUTcwlYKxsntHW6zpC1aq9yKAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bda6413c09dafd3aaf56cbeefa6909b40cdce5803571a8b02966401a20386ecf","last_reissued_at":"2026-07-05T11:11:51.102811Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:51.102811Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.22866","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":"2026-07-05T11:11:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LiXL9gz4n9r7BDQMWbxxmcythUjHafz3dpqOHIXdrCxAmYvuEb4MBwAHlw5BnnLa2qfdojtH5SVQc7UZ84eYDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:57:23.668900Z"},"content_sha256":"10d0158c05afe3792c53fb1ec69d8bcfbc76cf5438ba3a1abfbe7f4611704d61","schema_version":"1.0","event_id":"sha256:10d0158c05afe3792c53fb1ec69d8bcfbc76cf5438ba3a1abfbe7f4611704d61"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XWTECPAJ3L6TVL2WZPXPU2IJWQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scaling Offline RL via Efficient and Expressive Shortcut Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bradley Guo, Gokul Swamy, Kiante Brantley, Nicolas Espinosa-Dice, Owen Oertell, Wen Sun, Yiding Chen, Yiyi Zhang","submitted_at":"2025-05-28T20:59:22Z","abstract_excerpt":"Diffusion and flow models have emerged as powerful generative approaches capable of modeling diverse and multimodal behavior. However, applying these models to offline reinforcement learning (RL) remains challenging due to the iterative nature of their noise sampling processes, making policy optimization difficult. In this paper, we introduce Scalable Offline Reinforcement Learning (SORL), a new offline RL algorithm that leverages shortcut models - a novel class of generative models - to scale both training and inference. SORL's policy can capture complex data distributions and can be trained "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22866","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/2505.22866/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":"2026-07-05T11:11:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZmGQfiUnNuJUK+nA4id+TSm/n5wrm1IpvWxjThkRk9jKw8yuxkcF5WvC0FSKOgZccMmxCmcNNam8ok41YcNeAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:57:23.669417Z"},"content_sha256":"55a0c1622b39fdf03c7d3628a1ab10e1578c4eb195ca2696d5812cfbfb786866","schema_version":"1.0","event_id":"sha256:55a0c1622b39fdf03c7d3628a1ab10e1578c4eb195ca2696d5812cfbfb786866"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XWTECPAJ3L6TVL2WZPXPU2IJWQ/bundle.json","state_url":"https://pith.science/pith/XWTECPAJ3L6TVL2WZPXPU2IJWQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XWTECPAJ3L6TVL2WZPXPU2IJWQ/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":"2026-08-08T13:57:23Z","links":{"resolver":"https://pith.science/pith/XWTECPAJ3L6TVL2WZPXPU2IJWQ","bundle":"https://pith.science/pith/XWTECPAJ3L6TVL2WZPXPU2IJWQ/bundle.json","state":"https://pith.science/pith/XWTECPAJ3L6TVL2WZPXPU2IJWQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XWTECPAJ3L6TVL2WZPXPU2IJWQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XWTECPAJ3L6TVL2WZPXPU2IJWQ","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":"44aa202c570fdf5b08ce23f7aca96b52c967c39507bb6c42c68e29378174487e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T20:59:22Z","title_canon_sha256":"e31a629278a966a2b60d2e4c3aa3f35b774d53ba2766516dd5c4b6966ba5946e"},"schema_version":"1.0","source":{"id":"2505.22866","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22866","created_at":"2026-07-05T11:11:51Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22866v1","created_at":"2026-07-05T11:11:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22866","created_at":"2026-07-05T11:11:51Z"},{"alias_kind":"pith_short_12","alias_value":"XWTECPAJ3L6T","created_at":"2026-07-05T11:11:51Z"},{"alias_kind":"pith_short_16","alias_value":"XWTECPAJ3L6TVL2W","created_at":"2026-07-05T11:11:51Z"},{"alias_kind":"pith_short_8","alias_value":"XWTECPAJ","created_at":"2026-07-05T11:11:51Z"}],"graph_snapshots":[{"event_id":"sha256:55a0c1622b39fdf03c7d3628a1ab10e1578c4eb195ca2696d5812cfbfb786866","target":"graph","created_at":"2026-07-05T11:11:51Z","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/2505.22866/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion and flow models have emerged as powerful generative approaches capable of modeling diverse and multimodal behavior. However, applying these models to offline reinforcement learning (RL) remains challenging due to the iterative nature of their noise sampling processes, making policy optimization difficult. In this paper, we introduce Scalable Offline Reinforcement Learning (SORL), a new offline RL algorithm that leverages shortcut models - a novel class of generative models - to scale both training and inference. SORL's policy can capture complex data distributions and can be trained ","authors_text":"Bradley Guo, Gokul Swamy, Kiante Brantley, Nicolas Espinosa-Dice, Owen Oertell, Wen Sun, Yiding Chen, Yiyi Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T20:59:22Z","title":"Scaling Offline RL via Efficient and Expressive Shortcut Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22866","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":"sha256:10d0158c05afe3792c53fb1ec69d8bcfbc76cf5438ba3a1abfbe7f4611704d61","target":"record","created_at":"2026-07-05T11:11:51Z","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":"44aa202c570fdf5b08ce23f7aca96b52c967c39507bb6c42c68e29378174487e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T20:59:22Z","title_canon_sha256":"e31a629278a966a2b60d2e4c3aa3f35b774d53ba2766516dd5c4b6966ba5946e"},"schema_version":"1.0","source":{"id":"2505.22866","kind":"arxiv","version":1}},"canonical_sha256":"bda6413c09dafd3aaf56cbeefa6909b40cdce5803571a8b02966401a20386ecf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bda6413c09dafd3aaf56cbeefa6909b40cdce5803571a8b02966401a20386ecf","first_computed_at":"2026-07-05T11:11:51.102811Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:51.102811Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wtX7iPI19oN98Vw73hYhZeOQtaJm7iIqj5pwHXTNylfVoQhT8JkUpN7AB9haNUTcwlYKxsntHW6zpC1aq9yKAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:51.103535Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.22866","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:10d0158c05afe3792c53fb1ec69d8bcfbc76cf5438ba3a1abfbe7f4611704d61","sha256:55a0c1622b39fdf03c7d3628a1ab10e1578c4eb195ca2696d5812cfbfb786866"],"state_sha256":"4bdf98d34bd0a06769288893f6b16c5ab60fb4ebcc47197533d537d3f820b3e1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sx0uiVNSp8+v7RDg6H3tsfgeqdXXpuvFmhWhQQuEduMKXk6Ijuqwfy2CXwjt4Gt+9Vaif7Ruxg1YiXNMUNscBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T13:57:23.674442Z","bundle_sha256":"ba76a754eaea880e58400910c5c6d66ce6aef56ccca3505c5d91c5d19f6bd616"}}