{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EELWG5VN4PFIKIKSP6KTOK3GVN","short_pith_number":"pith:EELWG5VN","schema_version":"1.0","canonical_sha256":"21176376ade3ca8521527f95372b66ab7b933a2ccdf782026a179a9eef0aeaed","source":{"kind":"arxiv","id":"2501.12199","version":2},"attestation_state":"computed","paper":{"title":"Experience-replay Innovative Dynamics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GT","cs.MA"],"primary_cat":"cs.LG","authors_text":"Julian Barreiro-Gomez, Leonardo Stella, Tuo Zhang","submitted_at":"2025-01-21T15:10:14Z","abstract_excerpt":"Despite its groundbreaking success, multi-agent reinforcement learning (MARL) still suffers from instability and nonstationarity. Replicator dynamics, the most well-known model from evolutionary game theory (EGT), provide a theoretical framework for the convergence of the trajectories to Nash equilibria and, as a result, have been used to ensure formal guarantees for MARL algorithms in stable game settings. However, they exhibit the opposite behavior in other settings, which poses the problem of finding alternatives to ensure convergence. In contrast, innovative dynamics, such as the Brown-von"},"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":"2501.12199","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-21T15:10:14Z","cross_cats_sorted":["cs.GT","cs.MA"],"title_canon_sha256":"34b45388595bf9259f5631582943f86aaddcb48279c7e8bdf7ffcd5e942c4e25","abstract_canon_sha256":"afa3657a169303216c9b1f905215532f634d819a32e3cf30a0d4d03bb83dbcdb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:48.398303Z","signature_b64":"2UGmMzi+CU7lbWwxMJbG4mv0kmA4HldURDGvcv6nv7X6twCxN6cNEx81GOdJOvqPJi//X2Z11TfE/ZoxYktPDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21176376ade3ca8521527f95372b66ab7b933a2ccdf782026a179a9eef0aeaed","last_reissued_at":"2026-07-05T10:05:48.397805Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:48.397805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Experience-replay Innovative Dynamics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GT","cs.MA"],"primary_cat":"cs.LG","authors_text":"Julian Barreiro-Gomez, Leonardo Stella, Tuo Zhang","submitted_at":"2025-01-21T15:10:14Z","abstract_excerpt":"Despite its groundbreaking success, multi-agent reinforcement learning (MARL) still suffers from instability and nonstationarity. Replicator dynamics, the most well-known model from evolutionary game theory (EGT), provide a theoretical framework for the convergence of the trajectories to Nash equilibria and, as a result, have been used to ensure formal guarantees for MARL algorithms in stable game settings. However, they exhibit the opposite behavior in other settings, which poses the problem of finding alternatives to ensure convergence. In contrast, innovative dynamics, such as the Brown-von"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12199","kind":"arxiv","version":2},"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/2501.12199/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":"2501.12199","created_at":"2026-07-05T10:05:48.397865+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.12199v2","created_at":"2026-07-05T10:05:48.397865+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12199","created_at":"2026-07-05T10:05:48.397865+00:00"},{"alias_kind":"pith_short_12","alias_value":"EELWG5VN4PFI","created_at":"2026-07-05T10:05:48.397865+00:00"},{"alias_kind":"pith_short_16","alias_value":"EELWG5VN4PFIKIKS","created_at":"2026-07-05T10:05:48.397865+00:00"},{"alias_kind":"pith_short_8","alias_value":"EELWG5VN","created_at":"2026-07-05T10:05:48.397865+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20087","citing_title":"Multi-Head Attention-Based Feature Extractor Integration with Soft Actor-Critic for Porosity Prediction and Process Parameter Optimization in Additive Manufacturing","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EELWG5VN4PFIKIKSP6KTOK3GVN","json":"https://pith.science/pith/EELWG5VN4PFIKIKSP6KTOK3GVN.json","graph_json":"https://pith.science/api/pith-number/EELWG5VN4PFIKIKSP6KTOK3GVN/graph.json","events_json":"https://pith.science/api/pith-number/EELWG5VN4PFIKIKSP6KTOK3GVN/events.json","paper":"https://pith.science/paper/EELWG5VN"},"agent_actions":{"view_html":"https://pith.science/pith/EELWG5VN4PFIKIKSP6KTOK3GVN","download_json":"https://pith.science/pith/EELWG5VN4PFIKIKSP6KTOK3GVN.json","view_paper":"https://pith.science/paper/EELWG5VN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.12199&json=true","fetch_graph":"https://pith.science/api/pith-number/EELWG5VN4PFIKIKSP6KTOK3GVN/graph.json","fetch_events":"https://pith.science/api/pith-number/EELWG5VN4PFIKIKSP6KTOK3GVN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EELWG5VN4PFIKIKSP6KTOK3GVN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EELWG5VN4PFIKIKSP6KTOK3GVN/action/storage_attestation","attest_author":"https://pith.science/pith/EELWG5VN4PFIKIKSP6KTOK3GVN/action/author_attestation","sign_citation":"https://pith.science/pith/EELWG5VN4PFIKIKSP6KTOK3GVN/action/citation_signature","submit_replication":"https://pith.science/pith/EELWG5VN4PFIKIKSP6KTOK3GVN/action/replication_record"}},"created_at":"2026-07-05T10:05:48.397865+00:00","updated_at":"2026-07-05T10:05:48.397865+00:00"}