{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4R2R67XDEZK3JPEZCLCFPDUGB4","short_pith_number":"pith:4R2R67XD","schema_version":"1.0","canonical_sha256":"e4751f7ee32655b4bc9912c4578e860f0b05974a28715be4b3337246761f1f54","source":{"kind":"arxiv","id":"2305.18464","version":2},"attestation_state":"computed","paper":{"title":"Bridging the Sim-to-Real Gap from the Information Bottleneck Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Chenjia Bai, Hang Lai, Haoran He, Ling Pan, Lingxiao Wang, Peilin Wu, Weinan Zhang, Xiaolin Hu","submitted_at":"2023-05-29T07:51:00Z","abstract_excerpt":"Reinforcement Learning (RL) has recently achieved remarkable success in robotic control. However, most works in RL operate in simulated environments where privileged knowledge (e.g., dynamics, surroundings, terrains) is readily available. Conversely, in real-world scenarios, robot agents usually rely solely on local states (e.g., proprioceptive feedback of robot joints) to select actions, leading to a significant sim-to-real gap. Existing methods address this gap by either gradually reducing the reliance on privileged knowledge or performing a two-stage policy imitation. However, we argue that"},"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":"2305.18464","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-29T07:51:00Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"0c78d72b35bfd3e77c970d89212304fb10756540cdfc817a9dcd69a635923c9b","abstract_canon_sha256":"a2d764c2f6bb5442f7ec507cf4c4cebac6d95eb4cf13c55e39a7d912407b0ab7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:51.150390Z","signature_b64":"W0rrsCinEo50bkgIWz5uo3ayvoq5TGZ/15W503F6lLCvaBI8mkPVdfSyV9v9Y76LpBn8BPKuy7ICifhA50vdDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4751f7ee32655b4bc9912c4578e860f0b05974a28715be4b3337246761f1f54","last_reissued_at":"2026-07-05T09:19:51.149947Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:51.149947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bridging the Sim-to-Real Gap from the Information Bottleneck Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Chenjia Bai, Hang Lai, Haoran He, Ling Pan, Lingxiao Wang, Peilin Wu, Weinan Zhang, Xiaolin Hu","submitted_at":"2023-05-29T07:51:00Z","abstract_excerpt":"Reinforcement Learning (RL) has recently achieved remarkable success in robotic control. However, most works in RL operate in simulated environments where privileged knowledge (e.g., dynamics, surroundings, terrains) is readily available. Conversely, in real-world scenarios, robot agents usually rely solely on local states (e.g., proprioceptive feedback of robot joints) to select actions, leading to a significant sim-to-real gap. Existing methods address this gap by either gradually reducing the reliance on privileged knowledge or performing a two-stage policy imitation. However, we argue that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18464","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/2305.18464/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":"2305.18464","created_at":"2026-07-05T09:19:51.150004+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.18464v2","created_at":"2026-07-05T09:19:51.150004+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18464","created_at":"2026-07-05T09:19:51.150004+00:00"},{"alias_kind":"pith_short_12","alias_value":"4R2R67XDEZK3","created_at":"2026-07-05T09:19:51.150004+00:00"},{"alias_kind":"pith_short_16","alias_value":"4R2R67XDEZK3JPEZ","created_at":"2026-07-05T09:19:51.150004+00:00"},{"alias_kind":"pith_short_8","alias_value":"4R2R67XD","created_at":"2026-07-05T09:19:51.150004+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.04452","citing_title":"SimLauncher: Launching Sample-Efficient Real-world Robotic Reinforcement Learning via Simulation Pre-training","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4R2R67XDEZK3JPEZCLCFPDUGB4","json":"https://pith.science/pith/4R2R67XDEZK3JPEZCLCFPDUGB4.json","graph_json":"https://pith.science/api/pith-number/4R2R67XDEZK3JPEZCLCFPDUGB4/graph.json","events_json":"https://pith.science/api/pith-number/4R2R67XDEZK3JPEZCLCFPDUGB4/events.json","paper":"https://pith.science/paper/4R2R67XD"},"agent_actions":{"view_html":"https://pith.science/pith/4R2R67XDEZK3JPEZCLCFPDUGB4","download_json":"https://pith.science/pith/4R2R67XDEZK3JPEZCLCFPDUGB4.json","view_paper":"https://pith.science/paper/4R2R67XD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.18464&json=true","fetch_graph":"https://pith.science/api/pith-number/4R2R67XDEZK3JPEZCLCFPDUGB4/graph.json","fetch_events":"https://pith.science/api/pith-number/4R2R67XDEZK3JPEZCLCFPDUGB4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4R2R67XDEZK3JPEZCLCFPDUGB4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4R2R67XDEZK3JPEZCLCFPDUGB4/action/storage_attestation","attest_author":"https://pith.science/pith/4R2R67XDEZK3JPEZCLCFPDUGB4/action/author_attestation","sign_citation":"https://pith.science/pith/4R2R67XDEZK3JPEZCLCFPDUGB4/action/citation_signature","submit_replication":"https://pith.science/pith/4R2R67XDEZK3JPEZCLCFPDUGB4/action/replication_record"}},"created_at":"2026-07-05T09:19:51.150004+00:00","updated_at":"2026-07-05T09:19:51.150004+00:00"}