{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:TDHLWLXT7PUBA4HHE7K75MMK4I","short_pith_number":"pith:TDHLWLXT","canonical_record":{"source":{"id":"1909.13794","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-09-30T15:43:49Z","cross_cats_sorted":[],"title_canon_sha256":"421bfaab90fe641eb5720cb5054bff63d324382900705d34be59d848f2470f9a","abstract_canon_sha256":"4844332d8a296439b799d79fab3db71d8c59aeca7759285a727eb94fee7978c6"},"schema_version":"1.0"},"canonical_sha256":"98cebb2ef3fbe81070e727d5feb18ae2228cf88de17d9a2d2126f63c64caa55d","source":{"kind":"arxiv","id":"1909.13794","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.13794","created_at":"2026-07-05T00:08:14Z"},{"alias_kind":"arxiv_version","alias_value":"1909.13794v1","created_at":"2026-07-05T00:08:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.13794","created_at":"2026-07-05T00:08:14Z"},{"alias_kind":"pith_short_12","alias_value":"TDHLWLXT7PUB","created_at":"2026-07-05T00:08:14Z"},{"alias_kind":"pith_short_16","alias_value":"TDHLWLXT7PUBA4HH","created_at":"2026-07-05T00:08:14Z"},{"alias_kind":"pith_short_8","alias_value":"TDHLWLXT","created_at":"2026-07-05T00:08:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:TDHLWLXT7PUBA4HHE7K75MMK4I","target":"record","payload":{"canonical_record":{"source":{"id":"1909.13794","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-09-30T15:43:49Z","cross_cats_sorted":[],"title_canon_sha256":"421bfaab90fe641eb5720cb5054bff63d324382900705d34be59d848f2470f9a","abstract_canon_sha256":"4844332d8a296439b799d79fab3db71d8c59aeca7759285a727eb94fee7978c6"},"schema_version":"1.0"},"canonical_sha256":"98cebb2ef3fbe81070e727d5feb18ae2228cf88de17d9a2d2126f63c64caa55d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:08:14.062395Z","signature_b64":"fmBnApAInoaSwj6NOt2EhrEhxdvpeXlVkhoy5wics7ol5ztUvdQka3UwlqgM//vnXW89kHq09hpjbEwR4OfkAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98cebb2ef3fbe81070e727d5feb18ae2228cf88de17d9a2d2126f63c64caa55d","last_reissued_at":"2026-07-05T00:08:14.061978Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:08:14.061978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1909.13794","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":"2026-07-05T00:08:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4ZlO0MxdB5Fk2EI1ImJzBBh7rY+s0VTUZHz1Ok46ooZzfC26uTDmncsVO59aNDCZYw+vjZ9UMZRtx1qTp3lqDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:52:23.767129Z"},"content_sha256":"b699fa9f5d698784cd0e7423b928f0d27c37b81ea58b235b99da73ef26881aaa","schema_version":"1.0","event_id":"sha256:b699fa9f5d698784cd0e7423b928f0d27c37b81ea58b235b99da73ef26881aaa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:TDHLWLXT7PUBA4HHE7K75MMK4I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-agent Collaboration for Feasible Collaborative Behavior Construction and Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Rong Xiong, Shenhan Jia, Yunkai Wang, Zexi Chen, Zheyuan Huang","submitted_at":"2019-09-30T15:43:49Z","abstract_excerpt":"In the case of the two-person zero-sum stochastic game with a central controller, this paper proposes a best collaborative behavior search and selection algorithm based on reinforcement learning, in response to how to choose the best collaborative object and action for the central controller. In view of the existing multi-agent collaboration and confrontation reinforcement learning methods, the methods of traversing all actions in a certain state leads to the problem of long calculation time and unsafe policy exploration. This paper proposes to construct a feasible collaborative behavior set b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.13794","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/1909.13794/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":"2026-07-05T00:08:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mpZc9wPb7fcsAb8PIlPb1kikeeTCTP8VeG4UxvpackInqWzKVtIr4br3wj/XX7PnmQxpAEBqHuIkROptaGseBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:52:23.767520Z"},"content_sha256":"e10e55bd8f52b7775b503c0b55da26082c467e82b9295f9e849f40125597b7d7","schema_version":"1.0","event_id":"sha256:e10e55bd8f52b7775b503c0b55da26082c467e82b9295f9e849f40125597b7d7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TDHLWLXT7PUBA4HHE7K75MMK4I/bundle.json","state_url":"https://pith.science/pith/TDHLWLXT7PUBA4HHE7K75MMK4I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TDHLWLXT7PUBA4HHE7K75MMK4I/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":"2026-07-07T06:52:23Z","links":{"resolver":"https://pith.science/pith/TDHLWLXT7PUBA4HHE7K75MMK4I","bundle":"https://pith.science/pith/TDHLWLXT7PUBA4HHE7K75MMK4I/bundle.json","state":"https://pith.science/pith/TDHLWLXT7PUBA4HHE7K75MMK4I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TDHLWLXT7PUBA4HHE7K75MMK4I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:TDHLWLXT7PUBA4HHE7K75MMK4I","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":"4844332d8a296439b799d79fab3db71d8c59aeca7759285a727eb94fee7978c6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-09-30T15:43:49Z","title_canon_sha256":"421bfaab90fe641eb5720cb5054bff63d324382900705d34be59d848f2470f9a"},"schema_version":"1.0","source":{"id":"1909.13794","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.13794","created_at":"2026-07-05T00:08:14Z"},{"alias_kind":"arxiv_version","alias_value":"1909.13794v1","created_at":"2026-07-05T00:08:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.13794","created_at":"2026-07-05T00:08:14Z"},{"alias_kind":"pith_short_12","alias_value":"TDHLWLXT7PUB","created_at":"2026-07-05T00:08:14Z"},{"alias_kind":"pith_short_16","alias_value":"TDHLWLXT7PUBA4HH","created_at":"2026-07-05T00:08:14Z"},{"alias_kind":"pith_short_8","alias_value":"TDHLWLXT","created_at":"2026-07-05T00:08:14Z"}],"graph_snapshots":[{"event_id":"sha256:e10e55bd8f52b7775b503c0b55da26082c467e82b9295f9e849f40125597b7d7","target":"graph","created_at":"2026-07-05T00:08:14Z","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/1909.13794/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the case of the two-person zero-sum stochastic game with a central controller, this paper proposes a best collaborative behavior search and selection algorithm based on reinforcement learning, in response to how to choose the best collaborative object and action for the central controller. In view of the existing multi-agent collaboration and confrontation reinforcement learning methods, the methods of traversing all actions in a certain state leads to the problem of long calculation time and unsafe policy exploration. This paper proposes to construct a feasible collaborative behavior set b","authors_text":"Rong Xiong, Shenhan Jia, Yunkai Wang, Zexi Chen, Zheyuan Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-09-30T15:43:49Z","title":"Multi-agent Collaboration for Feasible Collaborative Behavior Construction and Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.13794","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:b699fa9f5d698784cd0e7423b928f0d27c37b81ea58b235b99da73ef26881aaa","target":"record","created_at":"2026-07-05T00:08:14Z","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":"4844332d8a296439b799d79fab3db71d8c59aeca7759285a727eb94fee7978c6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-09-30T15:43:49Z","title_canon_sha256":"421bfaab90fe641eb5720cb5054bff63d324382900705d34be59d848f2470f9a"},"schema_version":"1.0","source":{"id":"1909.13794","kind":"arxiv","version":1}},"canonical_sha256":"98cebb2ef3fbe81070e727d5feb18ae2228cf88de17d9a2d2126f63c64caa55d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"98cebb2ef3fbe81070e727d5feb18ae2228cf88de17d9a2d2126f63c64caa55d","first_computed_at":"2026-07-05T00:08:14.061978Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:08:14.061978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fmBnApAInoaSwj6NOt2EhrEhxdvpeXlVkhoy5wics7ol5ztUvdQka3UwlqgM//vnXW89kHq09hpjbEwR4OfkAg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:08:14.062395Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.13794","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b699fa9f5d698784cd0e7423b928f0d27c37b81ea58b235b99da73ef26881aaa","sha256:e10e55bd8f52b7775b503c0b55da26082c467e82b9295f9e849f40125597b7d7"],"state_sha256":"b8422ca21af40ac8936eeec702cc4a8b16907e1d652d0afd90b22d11a25df074"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y1dlVYkZCmCvutbthKfES4vCMgaTdSWO5OCiVlfrvUjp+/G8GGC7eeadIwYb7Klifa1cbOazt6mIdZ0rvmL1Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T06:52:23.769782Z","bundle_sha256":"5d17249a979e53874ff256e9cff8a6268f50dd34d52cc1502942a4d41d86cc38"}}