{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KODKOR4NMZ7PWGKTXYNBJI6O7G","short_pith_number":"pith:KODKOR4N","schema_version":"1.0","canonical_sha256":"5386a7478d667efb1953be1a14a3cef9b6c7c386c6cadfea334d94b5be1ea2ec","source":{"kind":"arxiv","id":"2209.15256","version":1},"attestation_state":"computed","paper":{"title":"S2P: State-conditioned Image Synthesis for Data Augmentation in Offline Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Daesol Cho, Dongseok Shim, H. Jin Kim","submitted_at":"2022-09-30T06:32:26Z","abstract_excerpt":"Offline reinforcement learning (Offline RL) suffers from the innate distributional shift as it cannot interact with the physical environment during training. To alleviate such limitation, state-based offline RL leverages a learned dynamics model from the logged experience and augments the predicted state transition to extend the data distribution. For exploiting such benefit also on the image-based RL, we firstly propose a generative model, S2P (State2Pixel), which synthesizes the raw pixel of the agent from its corresponding state. It enables bridging the gap between the state and the image d"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2209.15256","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-30T06:32:26Z","cross_cats_sorted":["cs.CV","cs.RO"],"title_canon_sha256":"dfaa7129a13fc090902db185560c1493f61ff0c1a8f677ffdface646dc1374bc","abstract_canon_sha256":"815d7bb2427b992ede417df79a3d5bbc6497527318765a4aa58bf9fcc3a57134"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:02:18.058436Z","signature_b64":"vMy+MnqBqVbZ0OHKXsQfl2NCTMVO4nRxymbsGDvFXHeUMJUvPaSHbrrrWUSfnoCSgJjWOmUiGkva1yeCssXtBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5386a7478d667efb1953be1a14a3cef9b6c7c386c6cadfea334d94b5be1ea2ec","last_reissued_at":"2026-07-05T05:02:18.058088Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:02:18.058088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"S2P: State-conditioned Image Synthesis for Data Augmentation in Offline Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Daesol Cho, Dongseok Shim, H. Jin Kim","submitted_at":"2022-09-30T06:32:26Z","abstract_excerpt":"Offline reinforcement learning (Offline RL) suffers from the innate distributional shift as it cannot interact with the physical environment during training. To alleviate such limitation, state-based offline RL leverages a learned dynamics model from the logged experience and augments the predicted state transition to extend the data distribution. For exploiting such benefit also on the image-based RL, we firstly propose a generative model, S2P (State2Pixel), which synthesizes the raw pixel of the agent from its corresponding state. It enables bridging the gap between the state and the image d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.15256","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/2209.15256/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2209.15256","created_at":"2026-07-05T05:02:18.058142+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.15256v1","created_at":"2026-07-05T05:02:18.058142+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.15256","created_at":"2026-07-05T05:02:18.058142+00:00"},{"alias_kind":"pith_short_12","alias_value":"KODKOR4NMZ7P","created_at":"2026-07-05T05:02:18.058142+00:00"},{"alias_kind":"pith_short_16","alias_value":"KODKOR4NMZ7PWGKT","created_at":"2026-07-05T05:02:18.058142+00:00"},{"alias_kind":"pith_short_8","alias_value":"KODKOR4N","created_at":"2026-07-05T05:02:18.058142+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KODKOR4NMZ7PWGKTXYNBJI6O7G","json":"https://pith.science/pith/KODKOR4NMZ7PWGKTXYNBJI6O7G.json","graph_json":"https://pith.science/api/pith-number/KODKOR4NMZ7PWGKTXYNBJI6O7G/graph.json","events_json":"https://pith.science/api/pith-number/KODKOR4NMZ7PWGKTXYNBJI6O7G/events.json","paper":"https://pith.science/paper/KODKOR4N"},"agent_actions":{"view_html":"https://pith.science/pith/KODKOR4NMZ7PWGKTXYNBJI6O7G","download_json":"https://pith.science/pith/KODKOR4NMZ7PWGKTXYNBJI6O7G.json","view_paper":"https://pith.science/paper/KODKOR4N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.15256&json=true","fetch_graph":"https://pith.science/api/pith-number/KODKOR4NMZ7PWGKTXYNBJI6O7G/graph.json","fetch_events":"https://pith.science/api/pith-number/KODKOR4NMZ7PWGKTXYNBJI6O7G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KODKOR4NMZ7PWGKTXYNBJI6O7G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KODKOR4NMZ7PWGKTXYNBJI6O7G/action/storage_attestation","attest_author":"https://pith.science/pith/KODKOR4NMZ7PWGKTXYNBJI6O7G/action/author_attestation","sign_citation":"https://pith.science/pith/KODKOR4NMZ7PWGKTXYNBJI6O7G/action/citation_signature","submit_replication":"https://pith.science/pith/KODKOR4NMZ7PWGKTXYNBJI6O7G/action/replication_record"}},"created_at":"2026-07-05T05:02:18.058142+00:00","updated_at":"2026-07-05T05:02:18.058142+00:00"}