{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:U5ZCRHIZFF32TPQTKXVOJFIAWH","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"52023f0cbd3e28f506661eceba4d63870ac50bfa97ccd389a2f0b7268d083aef","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-06T13:19:29Z","title_canon_sha256":"d6f9f31686858ec676b59b48f54e56c8c4013c8b52fb8073e91e1e9afd796617"},"schema_version":"1.0","source":{"id":"2608.06015","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.06015","created_at":"2026-08-07T00:55:02Z"},{"alias_kind":"arxiv_version","alias_value":"2608.06015v1","created_at":"2026-08-07T00:55:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.06015","created_at":"2026-08-07T00:55:02Z"},{"alias_kind":"pith_short_12","alias_value":"U5ZCRHIZFF32","created_at":"2026-08-07T00:55:02Z"},{"alias_kind":"pith_short_16","alias_value":"U5ZCRHIZFF32TPQT","created_at":"2026-08-07T00:55:02Z"},{"alias_kind":"pith_short_8","alias_value":"U5ZCRHIZ","created_at":"2026-08-07T00:55:02Z"}],"graph_snapshots":[{"event_id":"sha256:97c1f11d5e96819e329fe1ed362cafb0080898484dfd51a6ba58599ac1019e9a","target":"graph","created_at":"2026-08-07T00:55:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2608.06015/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Jianting Zhang, Junyuan Liang, Wuhui Chen, Xinwei Liu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-06T13:19:29Z","title":"ProDVI: Programmatic Dynamics Priors for Value Network Initialization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.06015","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a2f2d311f377b36d2f790caf03fc9c57517e01134690338d4d818242dc071266","target":"record","created_at":"2026-08-07T00:55:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"52023f0cbd3e28f506661eceba4d63870ac50bfa97ccd389a2f0b7268d083aef","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-06T13:19:29Z","title_canon_sha256":"d6f9f31686858ec676b59b48f54e56c8c4013c8b52fb8073e91e1e9afd796617"},"schema_version":"1.0","source":{"id":"2608.06015","kind":"arxiv","version":1}},"canonical_sha256":"a772289d192977a9be1355eae49500b1ed8eb0e842ef1bdf67de3b0b9c95e9de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a772289d192977a9be1355eae49500b1ed8eb0e842ef1bdf67de3b0b9c95e9de","first_computed_at":"2026-08-07T00:55:02.621646Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-07T00:55:02.621646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sU68xw2InKFWobf3aitDqOkzE0PORHAS8xrRWeJaTJS1rlvBaHOJpV2aD3o+0yBFpTETdBm0iYafeja63sv4Aw==","signature_status":"signed_v1","signed_at":"2026-08-07T00:55:02.623117Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.06015","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a2f2d311f377b36d2f790caf03fc9c57517e01134690338d4d818242dc071266","sha256:97c1f11d5e96819e329fe1ed362cafb0080898484dfd51a6ba58599ac1019e9a"],"state_sha256":"2141aa088829158741033a0be5523de04557b108e9066393bce17aad50d9ddf5"}