{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:U5ZCRHIZFF32TPQTKXVOJFIAWH","short_pith_number":"pith:U5ZCRHIZ","schema_version":"1.0","canonical_sha256":"a772289d192977a9be1355eae49500b1ed8eb0e842ef1bdf67de3b0b9c95e9de","source":{"kind":"arxiv","id":"2608.06015","version":1},"attestation_state":"computed","paper":{"title":"ProDVI: Programmatic Dynamics Priors for Value Network Initialization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jianting Zhang, Junyuan Liang, Wuhui Chen, Xinwei Liu","submitted_at":"2026-08-06T13:19:29Z","abstract_excerpt":"Deep Reinforcement Learning (RL) is notoriously sample inefficient. One contributing factor is that RL agents are typically initialized from scratch, forcing them to acquire task-relevant knowledge through online interaction. Existing approaches obtain informative initializations through pre-collected datasets, high-fidelity simulators, or meta-learning over related tasks, but these prerequisites may be difficult to access or even unavailable. In this paper, we propose Programmatic Dynamics Priors for Value Network Initialization (ProDVI), a framework that leverages the commonsense and domain "},"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":"2608.06015","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-06T13:19:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d6f9f31686858ec676b59b48f54e56c8c4013c8b52fb8073e91e1e9afd796617","abstract_canon_sha256":"52023f0cbd3e28f506661eceba4d63870ac50bfa97ccd389a2f0b7268d083aef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-07T00:55:02.623117Z","signature_b64":"sU68xw2InKFWobf3aitDqOkzE0PORHAS8xrRWeJaTJS1rlvBaHOJpV2aD3o+0yBFpTETdBm0iYafeja63sv4Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a772289d192977a9be1355eae49500b1ed8eb0e842ef1bdf67de3b0b9c95e9de","last_reissued_at":"2026-08-07T00:55:02.621646Z","signature_status":"signed_v1","first_computed_at":"2026-08-07T00:55:02.621646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ProDVI: Programmatic Dynamics Priors for Value Network Initialization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jianting Zhang, Junyuan Liang, Wuhui Chen, Xinwei Liu","submitted_at":"2026-08-06T13:19:29Z","abstract_excerpt":"Deep Reinforcement Learning (RL) is notoriously sample inefficient. One contributing factor is that RL agents are typically initialized from scratch, forcing them to acquire task-relevant knowledge through online interaction. Existing approaches obtain informative initializations through pre-collected datasets, high-fidelity simulators, or meta-learning over related tasks, but these prerequisites may be difficult to access or even unavailable. In this paper, we propose Programmatic Dynamics Priors for Value Network Initialization (ProDVI), a framework that leverages the commonsense and domain "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.06015","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/2608.06015/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":"2608.06015","created_at":"2026-08-07T00:55:02.623257+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.06015v1","created_at":"2026-08-07T00:55:02.623257+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.06015","created_at":"2026-08-07T00:55:02.623257+00:00"},{"alias_kind":"pith_short_12","alias_value":"U5ZCRHIZFF32","created_at":"2026-08-07T00:55:02.623257+00:00"},{"alias_kind":"pith_short_16","alias_value":"U5ZCRHIZFF32TPQT","created_at":"2026-08-07T00:55:02.623257+00:00"},{"alias_kind":"pith_short_8","alias_value":"U5ZCRHIZ","created_at":"2026-08-07T00:55:02.623257+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/U5ZCRHIZFF32TPQTKXVOJFIAWH","json":"https://pith.science/pith/U5ZCRHIZFF32TPQTKXVOJFIAWH.json","graph_json":"https://pith.science/api/pith-number/U5ZCRHIZFF32TPQTKXVOJFIAWH/graph.json","events_json":"https://pith.science/api/pith-number/U5ZCRHIZFF32TPQTKXVOJFIAWH/events.json","paper":"https://pith.science/paper/U5ZCRHIZ"},"agent_actions":{"view_html":"https://pith.science/pith/U5ZCRHIZFF32TPQTKXVOJFIAWH","download_json":"https://pith.science/pith/U5ZCRHIZFF32TPQTKXVOJFIAWH.json","view_paper":"https://pith.science/paper/U5ZCRHIZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.06015&json=true","fetch_graph":"https://pith.science/api/pith-number/U5ZCRHIZFF32TPQTKXVOJFIAWH/graph.json","fetch_events":"https://pith.science/api/pith-number/U5ZCRHIZFF32TPQTKXVOJFIAWH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U5ZCRHIZFF32TPQTKXVOJFIAWH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U5ZCRHIZFF32TPQTKXVOJFIAWH/action/storage_attestation","attest_author":"https://pith.science/pith/U5ZCRHIZFF32TPQTKXVOJFIAWH/action/author_attestation","sign_citation":"https://pith.science/pith/U5ZCRHIZFF32TPQTKXVOJFIAWH/action/citation_signature","submit_replication":"https://pith.science/pith/U5ZCRHIZFF32TPQTKXVOJFIAWH/action/replication_record"}},"created_at":"2026-08-07T00:55:02.623257+00:00","updated_at":"2026-08-07T00:55:02.623257+00:00"}