{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:77MB5KML7H22JTHAXXWQJVGCDZ","short_pith_number":"pith:77MB5KML","canonical_record":{"source":{"id":"2407.14151","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-19T09:29:38Z","cross_cats_sorted":[],"title_canon_sha256":"8e93452ff7f674f591230066197ea903c9d0b7732c8aa5018b4c420cc54acd0a","abstract_canon_sha256":"33b86a4dcfa17bb15517719f2b586c542716440df6944480f96289163f3f0218"},"schema_version":"1.0"},"canonical_sha256":"ffd81ea98bf9f5a4cce0bded04d4c21e6a385c2c688744e37f4cb3e3b3ef4377","source":{"kind":"arxiv","id":"2407.14151","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.14151","created_at":"2026-07-05T08:45:59Z"},{"alias_kind":"arxiv_version","alias_value":"2407.14151v1","created_at":"2026-07-05T08:45:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.14151","created_at":"2026-07-05T08:45:59Z"},{"alias_kind":"pith_short_12","alias_value":"77MB5KML7H22","created_at":"2026-07-05T08:45:59Z"},{"alias_kind":"pith_short_16","alias_value":"77MB5KML7H22JTHA","created_at":"2026-07-05T08:45:59Z"},{"alias_kind":"pith_short_8","alias_value":"77MB5KML","created_at":"2026-07-05T08:45:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:77MB5KML7H22JTHAXXWQJVGCDZ","target":"record","payload":{"canonical_record":{"source":{"id":"2407.14151","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-19T09:29:38Z","cross_cats_sorted":[],"title_canon_sha256":"8e93452ff7f674f591230066197ea903c9d0b7732c8aa5018b4c420cc54acd0a","abstract_canon_sha256":"33b86a4dcfa17bb15517719f2b586c542716440df6944480f96289163f3f0218"},"schema_version":"1.0"},"canonical_sha256":"ffd81ea98bf9f5a4cce0bded04d4c21e6a385c2c688744e37f4cb3e3b3ef4377","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:59.135133Z","signature_b64":"dFJD+p475tUmnAOBmlGsAaeQ69QlTdLz7EEJtJOpDUe3FvytOap3/o0emfh5GxAcDIT2jWaxoJR4WrqHkDl/Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ffd81ea98bf9f5a4cce0bded04d4c21e6a385c2c688744e37f4cb3e3b3ef4377","last_reissued_at":"2026-07-05T08:45:59.134665Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:59.134665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.14151","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:45:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qKRgosLd1qkgOl6v3rltgsa4+jmmqk2daRaReygwbccE9vukRt8BLqAQmIDjxDCWJ1HDcqMlM+mIZIkDCj7UCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:42:26.730225Z"},"content_sha256":"462285bed0c2fce17e1ff0e2168821215436b33b4cb10ee365b5a8164fe1e45a","schema_version":"1.0","event_id":"sha256:462285bed0c2fce17e1ff0e2168821215436b33b4cb10ee365b5a8164fe1e45a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:77MB5KML7H22JTHAXXWQJVGCDZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Comparative Study of Deep Reinforcement Learning Models: DQN vs PPO vs A2C","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniel A. Vidal Guerra, Neil De La Fuente","submitted_at":"2024-07-19T09:29:38Z","abstract_excerpt":"This study conducts a comparative analysis of three advanced Deep Reinforcement Learning models: Deep Q-Networks (DQN), Proximal Policy Optimization (PPO), and Advantage Actor-Critic (A2C), within the BreakOut Atari game environment. Our research assesses the performance and effectiveness of these models in a controlled setting. Through rigorous experimentation, we examine each model's learning efficiency, strategy development, and adaptability under dynamic game conditions. The findings provide critical insights into the practical applications of these models in game-based learning environmen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.14151","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/2407.14151/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:45:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mFZrOX7vz6Mltm8kSHvUyiWKfwVRXHkY4Ky6jmu9Rg+rcsFmwaZCnc40BmIgTXKNoVBTyc6tZfEs4xmqPOITDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:42:26.731183Z"},"content_sha256":"377a88dff97137a0d570b5a2be27fe9c9bdd45819e4a5b278b4b036b82a1ca74","schema_version":"1.0","event_id":"sha256:377a88dff97137a0d570b5a2be27fe9c9bdd45819e4a5b278b4b036b82a1ca74"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/77MB5KML7H22JTHAXXWQJVGCDZ/bundle.json","state_url":"https://pith.science/pith/77MB5KML7H22JTHAXXWQJVGCDZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/77MB5KML7H22JTHAXXWQJVGCDZ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T05:42:26Z","links":{"resolver":"https://pith.science/pith/77MB5KML7H22JTHAXXWQJVGCDZ","bundle":"https://pith.science/pith/77MB5KML7H22JTHAXXWQJVGCDZ/bundle.json","state":"https://pith.science/pith/77MB5KML7H22JTHAXXWQJVGCDZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/77MB5KML7H22JTHAXXWQJVGCDZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:77MB5KML7H22JTHAXXWQJVGCDZ","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":"33b86a4dcfa17bb15517719f2b586c542716440df6944480f96289163f3f0218","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-19T09:29:38Z","title_canon_sha256":"8e93452ff7f674f591230066197ea903c9d0b7732c8aa5018b4c420cc54acd0a"},"schema_version":"1.0","source":{"id":"2407.14151","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.14151","created_at":"2026-07-05T08:45:59Z"},{"alias_kind":"arxiv_version","alias_value":"2407.14151v1","created_at":"2026-07-05T08:45:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.14151","created_at":"2026-07-05T08:45:59Z"},{"alias_kind":"pith_short_12","alias_value":"77MB5KML7H22","created_at":"2026-07-05T08:45:59Z"},{"alias_kind":"pith_short_16","alias_value":"77MB5KML7H22JTHA","created_at":"2026-07-05T08:45:59Z"},{"alias_kind":"pith_short_8","alias_value":"77MB5KML","created_at":"2026-07-05T08:45:59Z"}],"graph_snapshots":[{"event_id":"sha256:377a88dff97137a0d570b5a2be27fe9c9bdd45819e4a5b278b4b036b82a1ca74","target":"graph","created_at":"2026-07-05T08:45:59Z","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/2407.14151/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This study conducts a comparative analysis of three advanced Deep Reinforcement Learning models: Deep Q-Networks (DQN), Proximal Policy Optimization (PPO), and Advantage Actor-Critic (A2C), within the BreakOut Atari game environment. Our research assesses the performance and effectiveness of these models in a controlled setting. Through rigorous experimentation, we examine each model's learning efficiency, strategy development, and adaptability under dynamic game conditions. The findings provide critical insights into the practical applications of these models in game-based learning environmen","authors_text":"Daniel A. Vidal Guerra, Neil De La Fuente","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-19T09:29:38Z","title":"A Comparative Study of Deep Reinforcement Learning Models: DQN vs PPO vs A2C"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.14151","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":"sha256:462285bed0c2fce17e1ff0e2168821215436b33b4cb10ee365b5a8164fe1e45a","target":"record","created_at":"2026-07-05T08:45:59Z","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":"33b86a4dcfa17bb15517719f2b586c542716440df6944480f96289163f3f0218","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-19T09:29:38Z","title_canon_sha256":"8e93452ff7f674f591230066197ea903c9d0b7732c8aa5018b4c420cc54acd0a"},"schema_version":"1.0","source":{"id":"2407.14151","kind":"arxiv","version":1}},"canonical_sha256":"ffd81ea98bf9f5a4cce0bded04d4c21e6a385c2c688744e37f4cb3e3b3ef4377","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ffd81ea98bf9f5a4cce0bded04d4c21e6a385c2c688744e37f4cb3e3b3ef4377","first_computed_at":"2026-07-05T08:45:59.134665Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:45:59.134665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dFJD+p475tUmnAOBmlGsAaeQ69QlTdLz7EEJtJOpDUe3FvytOap3/o0emfh5GxAcDIT2jWaxoJR4WrqHkDl/Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:45:59.135133Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.14151","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:462285bed0c2fce17e1ff0e2168821215436b33b4cb10ee365b5a8164fe1e45a","sha256:377a88dff97137a0d570b5a2be27fe9c9bdd45819e4a5b278b4b036b82a1ca74"],"state_sha256":"733e4b0f367741a99ea3c9b7d7d0dbd41f46233e258364fa372d5916e636293f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L/udtxH19C1OqxPsp+5kAHHC4t1mpJcWiKS3XT6pucYEMYov1xfoDxT9CEP4DZ4j17QsYRA4M0qpvi7TLB63Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T05:42:26.738409Z","bundle_sha256":"0414d3a0621dec21db1ff5c78ad6db4a4e36833bb0240377306c626c87319c4e"}}