{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GOMHCDMSONLZTYP7URERIXS6SX","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":"b02b4761b266e8fbbb659b4a32ac641a76f8d9baa7ac6d5b0eca07637e412f19","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T12:18:19Z","title_canon_sha256":"330d3e37afbc6e36534e4a7febafe3e2867055c4590c5f912ab260844c5128dc"},"schema_version":"1.0","source":{"id":"2405.18110","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.18110","created_at":"2026-07-05T08:24:15Z"},{"alias_kind":"arxiv_version","alias_value":"2405.18110v1","created_at":"2026-07-05T08:24:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18110","created_at":"2026-07-05T08:24:15Z"},{"alias_kind":"pith_short_12","alias_value":"GOMHCDMSONLZ","created_at":"2026-07-05T08:24:15Z"},{"alias_kind":"pith_short_16","alias_value":"GOMHCDMSONLZTYP7","created_at":"2026-07-05T08:24:15Z"},{"alias_kind":"pith_short_8","alias_value":"GOMHCDMS","created_at":"2026-07-05T08:24:15Z"}],"graph_snapshots":[{"event_id":"sha256:7deaf2760cd75ca82a9d7b892b86ee243f362012b1582ed3e2229df5282f7cd8","target":"graph","created_at":"2026-07-05T08:24:15Z","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/2405.18110/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In multi-agent reinforcement learning (MARL), effective exploration is critical, especially in sparse reward environments. Although introducing global intrinsic rewards can foster exploration in such settings, it often complicates credit assignment among agents. To address this difficulty, we propose Individual Contributions as intrinsic Exploration Scaffolds (ICES), a novel approach to motivate exploration by assessing each agent's contribution from a global view. In particular, ICES constructs exploration scaffolds with Bayesian surprise, leveraging global transition information during centr","authors_text":"Jun Zhang, Shibo Chen, Xinran Li, Zifan Liu","cross_cats":["cs.AI","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T12:18:19Z","title":"Individual Contributions as Intrinsic Exploration Scaffolds for Multi-agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18110","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":"sha256:3a14b415b8f43858cebc18a37d7110b692662307e95d961af13a2bd66cd45f55","target":"record","created_at":"2026-07-05T08:24:15Z","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":"b02b4761b266e8fbbb659b4a32ac641a76f8d9baa7ac6d5b0eca07637e412f19","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T12:18:19Z","title_canon_sha256":"330d3e37afbc6e36534e4a7febafe3e2867055c4590c5f912ab260844c5128dc"},"schema_version":"1.0","source":{"id":"2405.18110","kind":"arxiv","version":1}},"canonical_sha256":"3398710d92735799e1ffa449145e5e95ff143ed64f61b460f7ebc430050449e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3398710d92735799e1ffa449145e5e95ff143ed64f61b460f7ebc430050449e4","first_computed_at":"2026-07-05T08:24:15.779063Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:24:15.779063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v8TcF2lTEhS9enFvHc351izi51hcDHN2Qm7676Xjky9p6QC7zjgK02I9mg2TeJv+FcXBl2MXOsJhfds06vsFBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:24:15.779423Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.18110","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3a14b415b8f43858cebc18a37d7110b692662307e95d961af13a2bd66cd45f55","sha256:7deaf2760cd75ca82a9d7b892b86ee243f362012b1582ed3e2229df5282f7cd8"],"state_sha256":"818aa351b837226ee92c32f5bd94bd5f20b389ed05fc1edfe9a3e7f55bc27cf6"}