{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:YCX5FCYE3OUM77GNMDOKGCYNKP","short_pith_number":"pith:YCX5FCYE","canonical_record":{"source":{"id":"2008.09369","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-21T08:23:33Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"a901ad8abeb37915904a9b944ed50803b1d230f2095edff3bd00a45aed38d251","abstract_canon_sha256":"d7663f90a9e9e84f6ac48f6f796b677a36804835e1ed83793eee61afbd81c536"},"schema_version":"1.0"},"canonical_sha256":"c0afd28b04dba8cffccd60dca30b0d53c613576dac3da9deaaf160610d1cd4e2","source":{"kind":"arxiv","id":"2008.09369","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.09369","created_at":"2026-07-05T01:31:30Z"},{"alias_kind":"arxiv_version","alias_value":"2008.09369v2","created_at":"2026-07-05T01:31:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.09369","created_at":"2026-07-05T01:31:30Z"},{"alias_kind":"pith_short_12","alias_value":"YCX5FCYE3OUM","created_at":"2026-07-05T01:31:30Z"},{"alias_kind":"pith_short_16","alias_value":"YCX5FCYE3OUM77GN","created_at":"2026-07-05T01:31:30Z"},{"alias_kind":"pith_short_8","alias_value":"YCX5FCYE","created_at":"2026-07-05T01:31:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:YCX5FCYE3OUM77GNMDOKGCYNKP","target":"record","payload":{"canonical_record":{"source":{"id":"2008.09369","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-21T08:23:33Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"a901ad8abeb37915904a9b944ed50803b1d230f2095edff3bd00a45aed38d251","abstract_canon_sha256":"d7663f90a9e9e84f6ac48f6f796b677a36804835e1ed83793eee61afbd81c536"},"schema_version":"1.0"},"canonical_sha256":"c0afd28b04dba8cffccd60dca30b0d53c613576dac3da9deaaf160610d1cd4e2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:31:30.467581Z","signature_b64":"bwDnsfRu5CD3o7vjbBvtnhPp1kZSXUO1+JqZiz6Fot+n3O2iLB/No57VuFTyappRdq47s6k23VZEG5soKBrmAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0afd28b04dba8cffccd60dca30b0d53c613576dac3da9deaaf160610d1cd4e2","last_reissued_at":"2026-07-05T01:31:30.467236Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:31:30.467236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2008.09369","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":"2026-07-05T01:31:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LFY0Sh2G18V2a9RSM9HCbo9BjZ1Eek6mc5izgBV3mkPJjqF27SRnKSwo9bz6WO/o4ranU+Q4AD/X2ViIXpVkBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T00:21:13.349165Z"},"content_sha256":"eff4acc85a7b7ba0cb77a5adfc381de116fc40d3d53ecc34d705f0b130bad36a","schema_version":"1.0","event_id":"sha256:eff4acc85a7b7ba0cb77a5adfc381de116fc40d3d53ecc34d705f0b130bad36a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:YCX5FCYE3OUM77GNMDOKGCYNKP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Collaborate in Multi-Module Recommendation via Multi-Agent Reinforcement Learning without Communication","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Bo An, Haikai Chen, Rundong Wang, Runsheng Yu, Xin Li, Xinrun Wang, Xu He, Yanghua Li, Zhirong Wang","submitted_at":"2020-08-21T08:23:33Z","abstract_excerpt":"With the rise of online e-commerce platforms, more and more customers prefer to shop online. To sell more products, online platforms introduce various modules to recommend items with different properties such as huge discounts. A web page often consists of different independent modules. The ranking policies of these modules are decided by different teams and optimized individually without cooperation, which might result in competition between modules. Thus, the global policy of the whole page could be sub-optimal. In this paper, we propose a novel multi-agent cooperative reinforcement learning"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.09369","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/2008.09369/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":"2026-07-05T01:31:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gv1r/tKIrA0hC3MmJP3/UGRciFZA6wH/asbeXyC6reBtaWrGUwA8H6Cqs1WB20FQglZdsf9TF1D41Z6EP4Q3DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T00:21:13.349591Z"},"content_sha256":"94306db83bbdc02a2b4d5e6963e5532451dac39a99313fe564faa5f63cc010e0","schema_version":"1.0","event_id":"sha256:94306db83bbdc02a2b4d5e6963e5532451dac39a99313fe564faa5f63cc010e0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YCX5FCYE3OUM77GNMDOKGCYNKP/bundle.json","state_url":"https://pith.science/pith/YCX5FCYE3OUM77GNMDOKGCYNKP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YCX5FCYE3OUM77GNMDOKGCYNKP/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":"2026-07-13T00:21:13Z","links":{"resolver":"https://pith.science/pith/YCX5FCYE3OUM77GNMDOKGCYNKP","bundle":"https://pith.science/pith/YCX5FCYE3OUM77GNMDOKGCYNKP/bundle.json","state":"https://pith.science/pith/YCX5FCYE3OUM77GNMDOKGCYNKP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YCX5FCYE3OUM77GNMDOKGCYNKP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:YCX5FCYE3OUM77GNMDOKGCYNKP","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":"d7663f90a9e9e84f6ac48f6f796b677a36804835e1ed83793eee61afbd81c536","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-21T08:23:33Z","title_canon_sha256":"a901ad8abeb37915904a9b944ed50803b1d230f2095edff3bd00a45aed38d251"},"schema_version":"1.0","source":{"id":"2008.09369","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.09369","created_at":"2026-07-05T01:31:30Z"},{"alias_kind":"arxiv_version","alias_value":"2008.09369v2","created_at":"2026-07-05T01:31:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.09369","created_at":"2026-07-05T01:31:30Z"},{"alias_kind":"pith_short_12","alias_value":"YCX5FCYE3OUM","created_at":"2026-07-05T01:31:30Z"},{"alias_kind":"pith_short_16","alias_value":"YCX5FCYE3OUM77GN","created_at":"2026-07-05T01:31:30Z"},{"alias_kind":"pith_short_8","alias_value":"YCX5FCYE","created_at":"2026-07-05T01:31:30Z"}],"graph_snapshots":[{"event_id":"sha256:94306db83bbdc02a2b4d5e6963e5532451dac39a99313fe564faa5f63cc010e0","target":"graph","created_at":"2026-07-05T01:31:30Z","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/2008.09369/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the rise of online e-commerce platforms, more and more customers prefer to shop online. To sell more products, online platforms introduce various modules to recommend items with different properties such as huge discounts. A web page often consists of different independent modules. The ranking policies of these modules are decided by different teams and optimized individually without cooperation, which might result in competition between modules. Thus, the global policy of the whole page could be sub-optimal. In this paper, we propose a novel multi-agent cooperative reinforcement learning","authors_text":"Bo An, Haikai Chen, Rundong Wang, Runsheng Yu, Xin Li, Xinrun Wang, Xu He, Yanghua Li, Zhirong Wang","cross_cats":["cs.AI","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-21T08:23:33Z","title":"Learning to Collaborate in Multi-Module Recommendation via Multi-Agent Reinforcement Learning without Communication"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.09369","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:eff4acc85a7b7ba0cb77a5adfc381de116fc40d3d53ecc34d705f0b130bad36a","target":"record","created_at":"2026-07-05T01:31:30Z","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":"d7663f90a9e9e84f6ac48f6f796b677a36804835e1ed83793eee61afbd81c536","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-21T08:23:33Z","title_canon_sha256":"a901ad8abeb37915904a9b944ed50803b1d230f2095edff3bd00a45aed38d251"},"schema_version":"1.0","source":{"id":"2008.09369","kind":"arxiv","version":2}},"canonical_sha256":"c0afd28b04dba8cffccd60dca30b0d53c613576dac3da9deaaf160610d1cd4e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c0afd28b04dba8cffccd60dca30b0d53c613576dac3da9deaaf160610d1cd4e2","first_computed_at":"2026-07-05T01:31:30.467236Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:31:30.467236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bwDnsfRu5CD3o7vjbBvtnhPp1kZSXUO1+JqZiz6Fot+n3O2iLB/No57VuFTyappRdq47s6k23VZEG5soKBrmAg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:31:30.467581Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.09369","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eff4acc85a7b7ba0cb77a5adfc381de116fc40d3d53ecc34d705f0b130bad36a","sha256:94306db83bbdc02a2b4d5e6963e5532451dac39a99313fe564faa5f63cc010e0"],"state_sha256":"f64fef135ddfd3430444cb970d83577a95d47b1d2a5895b972c45191553bcefb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KWdyP8ObW8XIH73ZFgo524WTS2kIEP5PaP08hc9NNO0kDZ33cM67HFTbMlZxM62hae/e7vA1pDi0XkQggbgdBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T00:21:13.352331Z","bundle_sha256":"a523b857124f8c4a83f43d6e3e7a6dac4cea7beeaa5e513af4590a0dbac319c1"}}