{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CJHZPJGLIQXNPSMZSWMCGLR4ON","short_pith_number":"pith:CJHZPJGL","schema_version":"1.0","canonical_sha256":"124f97a4cb442ed7c9999598232e3c73682f2aca514e1f771f969b6e3327a068","source":{"kind":"arxiv","id":"2505.00546","version":2},"attestation_state":"computed","paper":{"title":"Directly Forecasting Belief for Reinforcement Learning with Delays","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chao Huang, Chen Lv, Chung-Wei Lin, J\\\"urgen Schmidhuber, Qingyuan Wu, Qi Zhu, Simon Sinong Zhan, Yixuan Wang, Yuhui Wang","submitted_at":"2025-05-01T14:20:48Z","abstract_excerpt":"Reinforcement learning (RL) with delays is challenging as sensory perceptions lag behind the actual events: the RL agent needs to estimate the real state of its environment based on past observations. State-of-the-art (SOTA) methods typically employ recursive, step-by-step forecasting of states. This can cause the accumulation of compounding errors. To tackle this problem, our novel belief estimation method, named Directly Forecasting Belief Transformer (DFBT), directly forecasts states from observations without incrementally estimating intermediate states step-by-step. We theoretically demons"},"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":"2505.00546","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-01T14:20:48Z","cross_cats_sorted":[],"title_canon_sha256":"33877068775bb9f0d7ec5bcd84ad1a8cceba6a293a1100e667fa1fd5517a07e4","abstract_canon_sha256":"3fb181722ae816af8501849abeca7228092364f3b88ddd58d90ec14884ec4a6f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:45.076198Z","signature_b64":"RhM/Rdcg5LV/FdOKm0Bpn32cFUorO9oIeDTgIhV5wckPYTx+65iD3VLo1zEhfMe+c9zeaetZm4k/Q+si4/g1DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"124f97a4cb442ed7c9999598232e3c73682f2aca514e1f771f969b6e3327a068","last_reissued_at":"2026-07-05T11:17:45.075721Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:45.075721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Directly Forecasting Belief for Reinforcement Learning with Delays","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chao Huang, Chen Lv, Chung-Wei Lin, J\\\"urgen Schmidhuber, Qingyuan Wu, Qi Zhu, Simon Sinong Zhan, Yixuan Wang, Yuhui Wang","submitted_at":"2025-05-01T14:20:48Z","abstract_excerpt":"Reinforcement learning (RL) with delays is challenging as sensory perceptions lag behind the actual events: the RL agent needs to estimate the real state of its environment based on past observations. State-of-the-art (SOTA) methods typically employ recursive, step-by-step forecasting of states. This can cause the accumulation of compounding errors. To tackle this problem, our novel belief estimation method, named Directly Forecasting Belief Transformer (DFBT), directly forecasts states from observations without incrementally estimating intermediate states step-by-step. We theoretically demons"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00546","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/2505.00546/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":"2505.00546","created_at":"2026-07-05T11:17:45.075782+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.00546v2","created_at":"2026-07-05T11:17:45.075782+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00546","created_at":"2026-07-05T11:17:45.075782+00:00"},{"alias_kind":"pith_short_12","alias_value":"CJHZPJGLIQXN","created_at":"2026-07-05T11:17:45.075782+00:00"},{"alias_kind":"pith_short_16","alias_value":"CJHZPJGLIQXNPSMZ","created_at":"2026-07-05T11:17:45.075782+00:00"},{"alias_kind":"pith_short_8","alias_value":"CJHZPJGL","created_at":"2026-07-05T11:17:45.075782+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/CJHZPJGLIQXNPSMZSWMCGLR4ON","json":"https://pith.science/pith/CJHZPJGLIQXNPSMZSWMCGLR4ON.json","graph_json":"https://pith.science/api/pith-number/CJHZPJGLIQXNPSMZSWMCGLR4ON/graph.json","events_json":"https://pith.science/api/pith-number/CJHZPJGLIQXNPSMZSWMCGLR4ON/events.json","paper":"https://pith.science/paper/CJHZPJGL"},"agent_actions":{"view_html":"https://pith.science/pith/CJHZPJGLIQXNPSMZSWMCGLR4ON","download_json":"https://pith.science/pith/CJHZPJGLIQXNPSMZSWMCGLR4ON.json","view_paper":"https://pith.science/paper/CJHZPJGL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.00546&json=true","fetch_graph":"https://pith.science/api/pith-number/CJHZPJGLIQXNPSMZSWMCGLR4ON/graph.json","fetch_events":"https://pith.science/api/pith-number/CJHZPJGLIQXNPSMZSWMCGLR4ON/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CJHZPJGLIQXNPSMZSWMCGLR4ON/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CJHZPJGLIQXNPSMZSWMCGLR4ON/action/storage_attestation","attest_author":"https://pith.science/pith/CJHZPJGLIQXNPSMZSWMCGLR4ON/action/author_attestation","sign_citation":"https://pith.science/pith/CJHZPJGLIQXNPSMZSWMCGLR4ON/action/citation_signature","submit_replication":"https://pith.science/pith/CJHZPJGLIQXNPSMZSWMCGLR4ON/action/replication_record"}},"created_at":"2026-07-05T11:17:45.075782+00:00","updated_at":"2026-07-05T11:17:45.075782+00:00"}