{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7LNPCA2XBNEHJL7JU2SSMFMQVW","short_pith_number":"pith:7LNPCA2X","schema_version":"1.0","canonical_sha256":"fadaf103570b4874afe9a6a5261590ad822f26c6ec21c22411e0ed80552dc7b8","source":{"kind":"arxiv","id":"2608.05989","version":1},"attestation_state":"computed","paper":{"title":"Observation-Grounded Self-Predictive Reinforcement Learning for Visual Continuous Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Jianting Zhang, Junyuan Liang, Wuhui Chen, Xinwei Liu","submitted_at":"2026-08-06T13:02:59Z","abstract_excerpt":"Sample-efficient policy learning from pixels is a long-standing challenge in reinforcement learning (RL). Recent dynamics-based representation learning methods have significantly improved the sample efficiency of model-free visual RL by learning dynamics-aware representations through auxiliary prediction performed either in latent space (self-prediction) or observation space (observation prediction). However, state-of-the-art methods from both categories still struggle on challenging visual control tasks when training data is limited. We posit that relying on either predictive objective alone "},"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":"2608.05989","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-06T13:02:59Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"3d68cb046216f5284fa12b431a41c844ccb624b7870a49e4cf5045f854226d57","abstract_canon_sha256":"c6afbefd8f3d81494e3e60058a46e1295cdebd5546b25212b1f868f61d89b8e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-07T00:54:52.467677Z","signature_b64":"c3OvRhGq4y/RM0pyF2g4zt+Z19CRuOKt6nyzJf2CLKzCOwbzsjeKjS23fijJ7s2SIaQlolpghAVQHuosrjUBAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fadaf103570b4874afe9a6a5261590ad822f26c6ec21c22411e0ed80552dc7b8","last_reissued_at":"2026-08-07T00:54:52.465858Z","signature_status":"signed_v1","first_computed_at":"2026-08-07T00:54:52.465858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Observation-Grounded Self-Predictive Reinforcement Learning for Visual Continuous Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Jianting Zhang, Junyuan Liang, Wuhui Chen, Xinwei Liu","submitted_at":"2026-08-06T13:02:59Z","abstract_excerpt":"Sample-efficient policy learning from pixels is a long-standing challenge in reinforcement learning (RL). Recent dynamics-based representation learning methods have significantly improved the sample efficiency of model-free visual RL by learning dynamics-aware representations through auxiliary prediction performed either in latent space (self-prediction) or observation space (observation prediction). However, state-of-the-art methods from both categories still struggle on challenging visual control tasks when training data is limited. We posit that relying on either predictive objective alone "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05989","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/2608.05989/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":"2608.05989","created_at":"2026-08-07T00:54:52.467567+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.05989v1","created_at":"2026-08-07T00:54:52.467567+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05989","created_at":"2026-08-07T00:54:52.467567+00:00"},{"alias_kind":"pith_short_12","alias_value":"7LNPCA2XBNEH","created_at":"2026-08-07T00:54:52.467567+00:00"},{"alias_kind":"pith_short_16","alias_value":"7LNPCA2XBNEHJL7J","created_at":"2026-08-07T00:54:52.467567+00:00"},{"alias_kind":"pith_short_8","alias_value":"7LNPCA2X","created_at":"2026-08-07T00:54:52.467567+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/7LNPCA2XBNEHJL7JU2SSMFMQVW","json":"https://pith.science/pith/7LNPCA2XBNEHJL7JU2SSMFMQVW.json","graph_json":"https://pith.science/api/pith-number/7LNPCA2XBNEHJL7JU2SSMFMQVW/graph.json","events_json":"https://pith.science/api/pith-number/7LNPCA2XBNEHJL7JU2SSMFMQVW/events.json","paper":"https://pith.science/paper/7LNPCA2X"},"agent_actions":{"view_html":"https://pith.science/pith/7LNPCA2XBNEHJL7JU2SSMFMQVW","download_json":"https://pith.science/pith/7LNPCA2XBNEHJL7JU2SSMFMQVW.json","view_paper":"https://pith.science/paper/7LNPCA2X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.05989&json=true","fetch_graph":"https://pith.science/api/pith-number/7LNPCA2XBNEHJL7JU2SSMFMQVW/graph.json","fetch_events":"https://pith.science/api/pith-number/7LNPCA2XBNEHJL7JU2SSMFMQVW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7LNPCA2XBNEHJL7JU2SSMFMQVW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7LNPCA2XBNEHJL7JU2SSMFMQVW/action/storage_attestation","attest_author":"https://pith.science/pith/7LNPCA2XBNEHJL7JU2SSMFMQVW/action/author_attestation","sign_citation":"https://pith.science/pith/7LNPCA2XBNEHJL7JU2SSMFMQVW/action/citation_signature","submit_replication":"https://pith.science/pith/7LNPCA2XBNEHJL7JU2SSMFMQVW/action/replication_record"}},"created_at":"2026-08-07T00:54:52.467567+00:00","updated_at":"2026-08-07T00:54:52.467567+00:00"}