{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:L67N5ETMKQZ5PUFWIBTRXZ6SQ5","short_pith_number":"pith:L67N5ETM","canonical_record":{"source":{"id":"2402.07752","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.MA","submitted_at":"2024-02-12T16:21:50Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"2af55659e18da412f13e835311573a6ed980f566ca222e9bd35a2a001363f32c","abstract_canon_sha256":"cd372e2a769a5eb5a30adcf7e0506dc90940ae4b9a176f4105aa6af294cf2c73"},"schema_version":"1.0"},"canonical_sha256":"5fbede926c5433d7d0b640671be7d2877b0d59d10f7b32052abf59f94200e6f2","source":{"kind":"arxiv","id":"2402.07752","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.07752","created_at":"2026-07-05T07:44:11Z"},{"alias_kind":"arxiv_version","alias_value":"2402.07752v1","created_at":"2026-07-05T07:44:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07752","created_at":"2026-07-05T07:44:11Z"},{"alias_kind":"pith_short_12","alias_value":"L67N5ETMKQZ5","created_at":"2026-07-05T07:44:11Z"},{"alias_kind":"pith_short_16","alias_value":"L67N5ETMKQZ5PUFW","created_at":"2026-07-05T07:44:11Z"},{"alias_kind":"pith_short_8","alias_value":"L67N5ETM","created_at":"2026-07-05T07:44:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:L67N5ETMKQZ5PUFWIBTRXZ6SQ5","target":"record","payload":{"canonical_record":{"source":{"id":"2402.07752","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.MA","submitted_at":"2024-02-12T16:21:50Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"2af55659e18da412f13e835311573a6ed980f566ca222e9bd35a2a001363f32c","abstract_canon_sha256":"cd372e2a769a5eb5a30adcf7e0506dc90940ae4b9a176f4105aa6af294cf2c73"},"schema_version":"1.0"},"canonical_sha256":"5fbede926c5433d7d0b640671be7d2877b0d59d10f7b32052abf59f94200e6f2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:44:11.847307Z","signature_b64":"hZQ+f5kk7khbTMXaOCdBlDjcUnlBl8CuJpQi3nIn3wQrdyZr5lQhTHiQ6iiGIegdjntWHF+V2NfyuqtMdkK/DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fbede926c5433d7d0b640671be7d2877b0d59d10f7b32052abf59f94200e6f2","last_reissued_at":"2026-07-05T07:44:11.846950Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:44:11.846950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.07752","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":"2026-07-05T07:44:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9I0aMvFaAwfnZzIsZ4Uu4A6hgzi0213KWywY1spf6VRr78slcf6LMRfLi3YVORnUyndR51xsEPHUAqMlZH/KBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T12:30:39.525960Z"},"content_sha256":"84e675491c43dda681c8c0e741aed5ecc66d4e0db7039f62435bf9969b7c3df2","schema_version":"1.0","event_id":"sha256:84e675491c43dda681c8c0e741aed5ecc66d4e0db7039f62435bf9969b7c3df2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:L67N5ETMKQZ5PUFWIBTRXZ6SQ5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mixed Q-Functionals: Advancing Value-Based Methods in Cooperative MARL with Continuous Action Domains","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.MA","authors_text":"S. Reza Ahmadzadeh, Yasin Findik","submitted_at":"2024-02-12T16:21:50Z","abstract_excerpt":"Tackling multi-agent learning problems efficiently is a challenging task in continuous action domains. While value-based algorithms excel in sample efficiency when applied to discrete action domains, they are usually inefficient when dealing with continuous actions. Policy-based algorithms, on the other hand, attempt to address this challenge by leveraging critic networks for guiding the learning process and stabilizing the gradient estimation. The limitations in the estimation of true return and falling into local optima in these methods result in inefficient and often sub-optimal policies. I"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07752","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/2402.07752/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":"2026-07-05T07:44:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QGR8yaVa2/wjGw3p2oR5aPWZg9Wj2uPYXXk/MSItZvKgM8ne4hjqX/VkZLObNKOExaXPDbcxPr7nN0Q6gkH9CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T12:30:39.526612Z"},"content_sha256":"489e65442c4f1bc724cedc77a8a81e2e114bd49342354928ddd0760411186d95","schema_version":"1.0","event_id":"sha256:489e65442c4f1bc724cedc77a8a81e2e114bd49342354928ddd0760411186d95"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L67N5ETMKQZ5PUFWIBTRXZ6SQ5/bundle.json","state_url":"https://pith.science/pith/L67N5ETMKQZ5PUFWIBTRXZ6SQ5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L67N5ETMKQZ5PUFWIBTRXZ6SQ5/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":"2026-08-18T12:30:39Z","links":{"resolver":"https://pith.science/pith/L67N5ETMKQZ5PUFWIBTRXZ6SQ5","bundle":"https://pith.science/pith/L67N5ETMKQZ5PUFWIBTRXZ6SQ5/bundle.json","state":"https://pith.science/pith/L67N5ETMKQZ5PUFWIBTRXZ6SQ5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L67N5ETMKQZ5PUFWIBTRXZ6SQ5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:L67N5ETMKQZ5PUFWIBTRXZ6SQ5","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":"cd372e2a769a5eb5a30adcf7e0506dc90940ae4b9a176f4105aa6af294cf2c73","cross_cats_sorted":["cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.MA","submitted_at":"2024-02-12T16:21:50Z","title_canon_sha256":"2af55659e18da412f13e835311573a6ed980f566ca222e9bd35a2a001363f32c"},"schema_version":"1.0","source":{"id":"2402.07752","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.07752","created_at":"2026-07-05T07:44:11Z"},{"alias_kind":"arxiv_version","alias_value":"2402.07752v1","created_at":"2026-07-05T07:44:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07752","created_at":"2026-07-05T07:44:11Z"},{"alias_kind":"pith_short_12","alias_value":"L67N5ETMKQZ5","created_at":"2026-07-05T07:44:11Z"},{"alias_kind":"pith_short_16","alias_value":"L67N5ETMKQZ5PUFW","created_at":"2026-07-05T07:44:11Z"},{"alias_kind":"pith_short_8","alias_value":"L67N5ETM","created_at":"2026-07-05T07:44:11Z"}],"graph_snapshots":[{"event_id":"sha256:489e65442c4f1bc724cedc77a8a81e2e114bd49342354928ddd0760411186d95","target":"graph","created_at":"2026-07-05T07:44:11Z","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/2402.07752/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tackling multi-agent learning problems efficiently is a challenging task in continuous action domains. While value-based algorithms excel in sample efficiency when applied to discrete action domains, they are usually inefficient when dealing with continuous actions. Policy-based algorithms, on the other hand, attempt to address this challenge by leveraging critic networks for guiding the learning process and stabilizing the gradient estimation. The limitations in the estimation of true return and falling into local optima in these methods result in inefficient and often sub-optimal policies. I","authors_text":"S. Reza Ahmadzadeh, Yasin Findik","cross_cats":["cs.LG","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.MA","submitted_at":"2024-02-12T16:21:50Z","title":"Mixed Q-Functionals: Advancing Value-Based Methods in Cooperative MARL with Continuous Action Domains"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07752","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":"sha256:84e675491c43dda681c8c0e741aed5ecc66d4e0db7039f62435bf9969b7c3df2","target":"record","created_at":"2026-07-05T07:44:11Z","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":"cd372e2a769a5eb5a30adcf7e0506dc90940ae4b9a176f4105aa6af294cf2c73","cross_cats_sorted":["cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.MA","submitted_at":"2024-02-12T16:21:50Z","title_canon_sha256":"2af55659e18da412f13e835311573a6ed980f566ca222e9bd35a2a001363f32c"},"schema_version":"1.0","source":{"id":"2402.07752","kind":"arxiv","version":1}},"canonical_sha256":"5fbede926c5433d7d0b640671be7d2877b0d59d10f7b32052abf59f94200e6f2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5fbede926c5433d7d0b640671be7d2877b0d59d10f7b32052abf59f94200e6f2","first_computed_at":"2026-07-05T07:44:11.846950Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:44:11.846950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hZQ+f5kk7khbTMXaOCdBlDjcUnlBl8CuJpQi3nIn3wQrdyZr5lQhTHiQ6iiGIegdjntWHF+V2NfyuqtMdkK/DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:44:11.847307Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.07752","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:84e675491c43dda681c8c0e741aed5ecc66d4e0db7039f62435bf9969b7c3df2","sha256:489e65442c4f1bc724cedc77a8a81e2e114bd49342354928ddd0760411186d95"],"state_sha256":"2ef93f1c3b0599a0033f88c6855d61bff65d87e4070eb12c8483634359bfb6b7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rY6Je9P+vPv9+XgQS0jUPOodAkxHJAWGx/4UfegXKvGP9FDNm7/izbJo30QTtLFCH/jkm4gpUQbQyfLNrWv9BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T12:30:39.531796Z","bundle_sha256":"0fe077958e48c77764c96699c9a476e49b9af5e20627031572715307201539bf"}}