{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LDILW7NAOHDJFRP7OH7D76RC36","short_pith_number":"pith:LDILW7NA","schema_version":"1.0","canonical_sha256":"58d0bb7da071c692c5ff71fe3ffa22df84fd38a2e5416786d800addb1d976a10","source":{"kind":"arxiv","id":"2608.07335","version":1},"attestation_state":"computed","paper":{"title":"Aftab: A Comprehensive Benchmark of CNN Encoders and Advanced Value Functions in Parallelized Q-Networks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Loris Nanni, Shabnam Zareshahraki, Taha Shieenavaz","submitted_at":"2026-08-07T15:29:15Z","abstract_excerpt":"Recent advancements in deep reinforcement learning have increasingly favored simplified, highly parallelized paradigms. Notably, the Parallelized Q-Network (PQN) algorithm achieves stable off-policy learning without relying on computationally expensive replay buffers or target networks. However, the representational capacity and parameter efficiency of visual encoders operating in these buffer-free settings remain underexplored. In this work, we systematically investigate the architectural design space of Convolutional Neural Networks for PQN. We design and rigorously evaluate eight distinct C"},"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":"2608.07335","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-07T15:29:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"88f77ca06edb9ec40c5a0e4bab6649b368607fba4ce49dfcf33fc2dffd07a445","abstract_canon_sha256":"a31cf504c88362cc144de2417fa2d68ef2ca667d1d96fd8b6aa4890943ac63d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-10T01:15:03.403471Z","signature_b64":"uG8uf9znQO3lox8IECLZhifyqvO5CZqCeOYPhrSow3XKc6TBgbSSvlfZJz0ef9QToDjyIv5MZX54ewE/XtbBDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58d0bb7da071c692c5ff71fe3ffa22df84fd38a2e5416786d800addb1d976a10","last_reissued_at":"2026-08-10T01:15:03.399931Z","signature_status":"signed_v1","first_computed_at":"2026-08-10T01:15:03.399931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Aftab: A Comprehensive Benchmark of CNN Encoders and Advanced Value Functions in Parallelized Q-Networks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Loris Nanni, Shabnam Zareshahraki, Taha Shieenavaz","submitted_at":"2026-08-07T15:29:15Z","abstract_excerpt":"Recent advancements in deep reinforcement learning have increasingly favored simplified, highly parallelized paradigms. Notably, the Parallelized Q-Network (PQN) algorithm achieves stable off-policy learning without relying on computationally expensive replay buffers or target networks. However, the representational capacity and parameter efficiency of visual encoders operating in these buffer-free settings remain underexplored. In this work, we systematically investigate the architectural design space of Convolutional Neural Networks for PQN. We design and rigorously evaluate eight distinct C"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.07335","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/2608.07335/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":"2608.07335","created_at":"2026-08-10T01:15:03.401833+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.07335v1","created_at":"2026-08-10T01:15:03.401833+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.07335","created_at":"2026-08-10T01:15:03.401833+00:00"},{"alias_kind":"pith_short_12","alias_value":"LDILW7NAOHDJ","created_at":"2026-08-10T01:15:03.401833+00:00"},{"alias_kind":"pith_short_16","alias_value":"LDILW7NAOHDJFRP7","created_at":"2026-08-10T01:15:03.401833+00:00"},{"alias_kind":"pith_short_8","alias_value":"LDILW7NA","created_at":"2026-08-10T01:15:03.401833+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/LDILW7NAOHDJFRP7OH7D76RC36","json":"https://pith.science/pith/LDILW7NAOHDJFRP7OH7D76RC36.json","graph_json":"https://pith.science/api/pith-number/LDILW7NAOHDJFRP7OH7D76RC36/graph.json","events_json":"https://pith.science/api/pith-number/LDILW7NAOHDJFRP7OH7D76RC36/events.json","paper":"https://pith.science/paper/LDILW7NA"},"agent_actions":{"view_html":"https://pith.science/pith/LDILW7NAOHDJFRP7OH7D76RC36","download_json":"https://pith.science/pith/LDILW7NAOHDJFRP7OH7D76RC36.json","view_paper":"https://pith.science/paper/LDILW7NA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.07335&json=true","fetch_graph":"https://pith.science/api/pith-number/LDILW7NAOHDJFRP7OH7D76RC36/graph.json","fetch_events":"https://pith.science/api/pith-number/LDILW7NAOHDJFRP7OH7D76RC36/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LDILW7NAOHDJFRP7OH7D76RC36/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LDILW7NAOHDJFRP7OH7D76RC36/action/storage_attestation","attest_author":"https://pith.science/pith/LDILW7NAOHDJFRP7OH7D76RC36/action/author_attestation","sign_citation":"https://pith.science/pith/LDILW7NAOHDJFRP7OH7D76RC36/action/citation_signature","submit_replication":"https://pith.science/pith/LDILW7NAOHDJFRP7OH7D76RC36/action/replication_record"}},"created_at":"2026-08-10T01:15:03.401833+00:00","updated_at":"2026-08-10T01:15:03.401833+00:00"}