{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6UYXQL2PVX76HJXL37LVIRLN6B","short_pith_number":"pith:6UYXQL2P","canonical_record":{"source":{"id":"2411.03603","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2024-11-06T01:40:21Z","cross_cats_sorted":[],"title_canon_sha256":"0bb30ea453b9a860c78f88e180cac70700cf8c22f65442c2694d4a581dd31576","abstract_canon_sha256":"6eeabf181a92a73a723211665d5966656566af20f2e9eba66f991291a8272553"},"schema_version":"1.0"},"canonical_sha256":"f531782f4fadffe3a6ebdfd754456df066be53a3b5ff14e455f344b680b29a8f","source":{"kind":"arxiv","id":"2411.03603","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.03603","created_at":"2026-07-05T09:45:16Z"},{"alias_kind":"arxiv_version","alias_value":"2411.03603v2","created_at":"2026-07-05T09:45:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.03603","created_at":"2026-07-05T09:45:16Z"},{"alias_kind":"pith_short_12","alias_value":"6UYXQL2PVX76","created_at":"2026-07-05T09:45:16Z"},{"alias_kind":"pith_short_16","alias_value":"6UYXQL2PVX76HJXL","created_at":"2026-07-05T09:45:16Z"},{"alias_kind":"pith_short_8","alias_value":"6UYXQL2P","created_at":"2026-07-05T09:45:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6UYXQL2PVX76HJXL37LVIRLN6B","target":"record","payload":{"canonical_record":{"source":{"id":"2411.03603","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2024-11-06T01:40:21Z","cross_cats_sorted":[],"title_canon_sha256":"0bb30ea453b9a860c78f88e180cac70700cf8c22f65442c2694d4a581dd31576","abstract_canon_sha256":"6eeabf181a92a73a723211665d5966656566af20f2e9eba66f991291a8272553"},"schema_version":"1.0"},"canonical_sha256":"f531782f4fadffe3a6ebdfd754456df066be53a3b5ff14e455f344b680b29a8f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:16.111406Z","signature_b64":"0co0o4UqmxyvMgBQEWAbq8Rj0C32O/MybG/H3vVMcczwSvz5El0xHBCt6DnnVMhByb8vbEAfse5t+SbD5iKMDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f531782f4fadffe3a6ebdfd754456df066be53a3b5ff14e455f344b680b29a8f","last_reissued_at":"2026-07-05T09:45:16.110919Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:16.110919Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.03603","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:45:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jnGaouUnWcI3+9sjQrj24ryRvqoXV1iNogQPZ7MbQb1kwYluK9KHV3fNTRe09P++d8NeDGUhbEUttKr0byYGCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T02:20:03.970665Z"},"content_sha256":"b1e8caa4526e0ee1be268449d8064149b3e5ad76d9e43a802713cf3310b5de4b","schema_version":"1.0","event_id":"sha256:b1e8caa4526e0ee1be268449d8064149b3e5ad76d9e43a802713cf3310b5de4b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6UYXQL2PVX76HJXL37LVIRLN6B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CPIG: Leveraging Consistency Policy with Intention Guidance for Multi-agent Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Dongbin Zhao, Haoran Li, Jiajun Chai, Yuanheng Zhu, Yuqian Fu, Zijie Zhao","submitted_at":"2024-11-06T01:40:21Z","abstract_excerpt":"Efficient exploration is crucial in cooperative multi-agent reinforcement learning (MARL), especially in sparse-reward settings. However, due to the reliance on the unimodal policy, existing methods are prone to falling into the local optima, hindering the effective exploration of better policies. Furthermore, in sparse-reward settings, each agent tends to receive a scarce reward, which poses significant challenges to inter-agent cooperation. This not only increases the difficulty of policy learning but also degrades the overall performance of multi-agent tasks. To address these issues, we pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.03603","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/2411.03603/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":"2026-07-05T09:45:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O7FTGLPxEOo+23DkhW8gxoHcUO7Nc/fUUIvpmoMMdHg5i8FyqA10p/v0qDl9z7it0c4bOWsIZ0b9eVoegZw0AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T02:20:04.034686Z"},"content_sha256":"b1a9a52d2cd67d8f4cd7b7e6f539a89541e8069350807a9c380ab71615f5d534","schema_version":"1.0","event_id":"sha256:b1a9a52d2cd67d8f4cd7b7e6f539a89541e8069350807a9c380ab71615f5d534"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6UYXQL2PVX76HJXL37LVIRLN6B/bundle.json","state_url":"https://pith.science/pith/6UYXQL2PVX76HJXL37LVIRLN6B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6UYXQL2PVX76HJXL37LVIRLN6B/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":"2026-08-11T02:20:04Z","links":{"resolver":"https://pith.science/pith/6UYXQL2PVX76HJXL37LVIRLN6B","bundle":"https://pith.science/pith/6UYXQL2PVX76HJXL37LVIRLN6B/bundle.json","state":"https://pith.science/pith/6UYXQL2PVX76HJXL37LVIRLN6B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6UYXQL2PVX76HJXL37LVIRLN6B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6UYXQL2PVX76HJXL37LVIRLN6B","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":"6eeabf181a92a73a723211665d5966656566af20f2e9eba66f991291a8272553","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2024-11-06T01:40:21Z","title_canon_sha256":"0bb30ea453b9a860c78f88e180cac70700cf8c22f65442c2694d4a581dd31576"},"schema_version":"1.0","source":{"id":"2411.03603","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.03603","created_at":"2026-07-05T09:45:16Z"},{"alias_kind":"arxiv_version","alias_value":"2411.03603v2","created_at":"2026-07-05T09:45:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.03603","created_at":"2026-07-05T09:45:16Z"},{"alias_kind":"pith_short_12","alias_value":"6UYXQL2PVX76","created_at":"2026-07-05T09:45:16Z"},{"alias_kind":"pith_short_16","alias_value":"6UYXQL2PVX76HJXL","created_at":"2026-07-05T09:45:16Z"},{"alias_kind":"pith_short_8","alias_value":"6UYXQL2P","created_at":"2026-07-05T09:45:16Z"}],"graph_snapshots":[{"event_id":"sha256:b1a9a52d2cd67d8f4cd7b7e6f539a89541e8069350807a9c380ab71615f5d534","target":"graph","created_at":"2026-07-05T09:45:16Z","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/2411.03603/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Efficient exploration is crucial in cooperative multi-agent reinforcement learning (MARL), especially in sparse-reward settings. However, due to the reliance on the unimodal policy, existing methods are prone to falling into the local optima, hindering the effective exploration of better policies. Furthermore, in sparse-reward settings, each agent tends to receive a scarce reward, which poses significant challenges to inter-agent cooperation. This not only increases the difficulty of policy learning but also degrades the overall performance of multi-agent tasks. To address these issues, we pro","authors_text":"Dongbin Zhao, Haoran Li, Jiajun Chai, Yuanheng Zhu, Yuqian Fu, Zijie Zhao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2024-11-06T01:40:21Z","title":"CPIG: Leveraging Consistency Policy with Intention Guidance for Multi-agent Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.03603","kind":"arxiv","version":2},"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:b1e8caa4526e0ee1be268449d8064149b3e5ad76d9e43a802713cf3310b5de4b","target":"record","created_at":"2026-07-05T09:45:16Z","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":"6eeabf181a92a73a723211665d5966656566af20f2e9eba66f991291a8272553","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2024-11-06T01:40:21Z","title_canon_sha256":"0bb30ea453b9a860c78f88e180cac70700cf8c22f65442c2694d4a581dd31576"},"schema_version":"1.0","source":{"id":"2411.03603","kind":"arxiv","version":2}},"canonical_sha256":"f531782f4fadffe3a6ebdfd754456df066be53a3b5ff14e455f344b680b29a8f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f531782f4fadffe3a6ebdfd754456df066be53a3b5ff14e455f344b680b29a8f","first_computed_at":"2026-07-05T09:45:16.110919Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:45:16.110919Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0co0o4UqmxyvMgBQEWAbq8Rj0C32O/MybG/H3vVMcczwSvz5El0xHBCt6DnnVMhByb8vbEAfse5t+SbD5iKMDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:45:16.111406Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.03603","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b1e8caa4526e0ee1be268449d8064149b3e5ad76d9e43a802713cf3310b5de4b","sha256:b1a9a52d2cd67d8f4cd7b7e6f539a89541e8069350807a9c380ab71615f5d534"],"state_sha256":"07f59ff0954a425a299b41435cc29932046bb154271afa75a44ccd7d275490f5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4713e4D5v/gbb0uOxxg5W9S5ReDh+jyE8LsdVZA+jn1bzDZ0Qbe5uJ5SVDb3sdJWKWIhM+jLDRabgFJnDz3eAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T02:20:04.165105Z","bundle_sha256":"1a5948c77fb64edcc1eddbc32be7ad31390a225669388504b40a1f19bf3c9db2"}}