{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WQLPZQJYR42TVXSW7BFRQLLDZF","short_pith_number":"pith:WQLPZQJY","schema_version":"1.0","canonical_sha256":"b416fcc1388f353ade56f84b182d63c969a4f4bd0f29053b25df2a1e3f84747c","source":{"kind":"arxiv","id":"2405.06263","version":2},"attestation_state":"computed","paper":{"title":"Learning Latent Dynamic Robust Representations for World Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hongyu Zang, Riashat Islam, Ruixiang Sun, Xin Li","submitted_at":"2024-05-10T06:28:42Z","abstract_excerpt":"Visual Model-Based Reinforcement Learning (MBRL) promises to encapsulate agent's knowledge about the underlying dynamics of the environment, enabling learning a world model as a useful planner. However, top MBRL agents such as Dreamer often struggle with visual pixel-based inputs in the presence of exogenous or irrelevant noise in the observation space, due to failure to capture task-specific features while filtering out irrelevant spatio-temporal details. To tackle this problem, we apply a spatio-temporal masking strategy, a bisimulation principle, combined with latent reconstruction, to capt"},"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":"2405.06263","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-10T06:28:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ba163dd2322ab03f273cf16aecdc617139281375bef35798baa716922a71bb62","abstract_canon_sha256":"ce36bec4e74204630a40003db8772bbe4d78ec5eab42c8b20f9234bf4bed6605"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:03.275865Z","signature_b64":"cOh1WS+eOf9ZneLeIciy4RMfvGJdyq+RVGjOu+nfxxS1482rEwJ2vBFQOzvNWZE4+DqhJoC2f3kuK1Dd0KXFBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b416fcc1388f353ade56f84b182d63c969a4f4bd0f29053b25df2a1e3f84747c","last_reissued_at":"2026-07-05T08:25:03.275372Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:03.275372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Latent Dynamic Robust Representations for World Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hongyu Zang, Riashat Islam, Ruixiang Sun, Xin Li","submitted_at":"2024-05-10T06:28:42Z","abstract_excerpt":"Visual Model-Based Reinforcement Learning (MBRL) promises to encapsulate agent's knowledge about the underlying dynamics of the environment, enabling learning a world model as a useful planner. However, top MBRL agents such as Dreamer often struggle with visual pixel-based inputs in the presence of exogenous or irrelevant noise in the observation space, due to failure to capture task-specific features while filtering out irrelevant spatio-temporal details. To tackle this problem, we apply a spatio-temporal masking strategy, a bisimulation principle, combined with latent reconstruction, to capt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.06263","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/2405.06263/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":"2405.06263","created_at":"2026-07-05T08:25:03.275432+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.06263v2","created_at":"2026-07-05T08:25:03.275432+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.06263","created_at":"2026-07-05T08:25:03.275432+00:00"},{"alias_kind":"pith_short_12","alias_value":"WQLPZQJYR42T","created_at":"2026-07-05T08:25:03.275432+00:00"},{"alias_kind":"pith_short_16","alias_value":"WQLPZQJYR42TVXSW","created_at":"2026-07-05T08:25:03.275432+00:00"},{"alias_kind":"pith_short_8","alias_value":"WQLPZQJY","created_at":"2026-07-05T08:25:03.275432+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23220","citing_title":"WMAttack: Automated Attack Search for Adversarial Evaluation of World-Model Agents","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16395","citing_title":"OrbiSim: World Models as Differentiable Physics Engines for Embodied Intelligence","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24661","citing_title":"Agent-Centric Observation Adaptation for Robust Visual Control under Dynamic Perturbations","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24661","citing_title":"Agent-Centric Observation Adaptation for Robust Visual Control under Dynamic Perturbations","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WQLPZQJYR42TVXSW7BFRQLLDZF","json":"https://pith.science/pith/WQLPZQJYR42TVXSW7BFRQLLDZF.json","graph_json":"https://pith.science/api/pith-number/WQLPZQJYR42TVXSW7BFRQLLDZF/graph.json","events_json":"https://pith.science/api/pith-number/WQLPZQJYR42TVXSW7BFRQLLDZF/events.json","paper":"https://pith.science/paper/WQLPZQJY"},"agent_actions":{"view_html":"https://pith.science/pith/WQLPZQJYR42TVXSW7BFRQLLDZF","download_json":"https://pith.science/pith/WQLPZQJYR42TVXSW7BFRQLLDZF.json","view_paper":"https://pith.science/paper/WQLPZQJY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.06263&json=true","fetch_graph":"https://pith.science/api/pith-number/WQLPZQJYR42TVXSW7BFRQLLDZF/graph.json","fetch_events":"https://pith.science/api/pith-number/WQLPZQJYR42TVXSW7BFRQLLDZF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WQLPZQJYR42TVXSW7BFRQLLDZF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WQLPZQJYR42TVXSW7BFRQLLDZF/action/storage_attestation","attest_author":"https://pith.science/pith/WQLPZQJYR42TVXSW7BFRQLLDZF/action/author_attestation","sign_citation":"https://pith.science/pith/WQLPZQJYR42TVXSW7BFRQLLDZF/action/citation_signature","submit_replication":"https://pith.science/pith/WQLPZQJYR42TVXSW7BFRQLLDZF/action/replication_record"}},"created_at":"2026-07-05T08:25:03.275432+00:00","updated_at":"2026-07-05T08:25:03.275432+00:00"}