{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:BHD4S2YZ7EVA6KOBYT27MGUO5J","short_pith_number":"pith:BHD4S2YZ","canonical_record":{"source":{"id":"2111.05992","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-10T23:45:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"627c890bf648ee0c93faac6ee4594185d12e54f6c31d495db31e554f3b172514","abstract_canon_sha256":"95adf96c016f903ab636951ce3a917028fca3dd52c3bed177352e06cb55e4657"},"schema_version":"1.0"},"canonical_sha256":"09c7c96b19f92a0f29c1c4f5f61a8eea79582d74ceba00df69618056b0de2bf8","source":{"kind":"arxiv","id":"2111.05992","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.05992","created_at":"2026-07-05T04:29:27Z"},{"alias_kind":"arxiv_version","alias_value":"2111.05992v2","created_at":"2026-07-05T04:29:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.05992","created_at":"2026-07-05T04:29:27Z"},{"alias_kind":"pith_short_12","alias_value":"BHD4S2YZ7EVA","created_at":"2026-07-05T04:29:27Z"},{"alias_kind":"pith_short_16","alias_value":"BHD4S2YZ7EVA6KOB","created_at":"2026-07-05T04:29:27Z"},{"alias_kind":"pith_short_8","alias_value":"BHD4S2YZ","created_at":"2026-07-05T04:29:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:BHD4S2YZ7EVA6KOBYT27MGUO5J","target":"record","payload":{"canonical_record":{"source":{"id":"2111.05992","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-10T23:45:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"627c890bf648ee0c93faac6ee4594185d12e54f6c31d495db31e554f3b172514","abstract_canon_sha256":"95adf96c016f903ab636951ce3a917028fca3dd52c3bed177352e06cb55e4657"},"schema_version":"1.0"},"canonical_sha256":"09c7c96b19f92a0f29c1c4f5f61a8eea79582d74ceba00df69618056b0de2bf8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:29:27.136860Z","signature_b64":"eU9fp45Ed9bEZKU0KKQ6JqGXyWzj3Q9uIDiRW8EbsRdfTDN82N1g0zFiCZUZHraaAxJvCJwy3WSNR8NtiQSNAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09c7c96b19f92a0f29c1c4f5f61a8eea79582d74ceba00df69618056b0de2bf8","last_reissued_at":"2026-07-05T04:29:27.136362Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:29:27.136362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.05992","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":"2026-07-05T04:29:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CaFCQQ8ULApjvjlKSmftvXjRWIAq3iz+UFL3lt7bwNoIl+k3/A1W5yAuclElcg0wudGvYhxviicfjd8uXjoNBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T19:35:11.018032Z"},"content_sha256":"44b2d8197bad81072990e15536e46c86d44b1c20f74cc0756e150c28e4caf1e5","schema_version":"1.0","event_id":"sha256:44b2d8197bad81072990e15536e46c86d44b1c20f74cc0756e150c28e4caf1e5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:BHD4S2YZ7EVA6KOBYT27MGUO5J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Use and Misuse of Absorbing States in Multi-agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alexander Zook, Andrew Cohen, Ervin Teng, Hunter Henry, Marwan Mattar, Ruo-Ping Dong, Sujoy Ganguly, Vincent-Pierre Berges","submitted_at":"2021-11-10T23:45:08Z","abstract_excerpt":"The creation and destruction of agents in cooperative multi-agent reinforcement learning (MARL) is a critically under-explored area of research. Current MARL algorithms often assume that the number of agents within a group remains fixed throughout an experiment. However, in many practical problems, an agent may terminate before their teammates. This early termination issue presents a challenge: the terminated agent must learn from the group's success or failure which occurs beyond its own existence. We refer to propagating value from rewards earned by remaining teammates to terminated agents a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.05992","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/2111.05992/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":"2026-07-05T04:29:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pFYs9aHlS5zkZiuWXvWxQEYUi4gWXN7XqntwkjgVPwPyi/eT++aqglCDWo9qd2h+d1vlpvp/wz3U7P9lMw5nAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T19:35:11.018382Z"},"content_sha256":"9d4402f607d859d6243bccaa88e83901494dd174845a59c860441a5dfe85fb20","schema_version":"1.0","event_id":"sha256:9d4402f607d859d6243bccaa88e83901494dd174845a59c860441a5dfe85fb20"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BHD4S2YZ7EVA6KOBYT27MGUO5J/bundle.json","state_url":"https://pith.science/pith/BHD4S2YZ7EVA6KOBYT27MGUO5J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BHD4S2YZ7EVA6KOBYT27MGUO5J/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":"2026-08-11T19:35:11Z","links":{"resolver":"https://pith.science/pith/BHD4S2YZ7EVA6KOBYT27MGUO5J","bundle":"https://pith.science/pith/BHD4S2YZ7EVA6KOBYT27MGUO5J/bundle.json","state":"https://pith.science/pith/BHD4S2YZ7EVA6KOBYT27MGUO5J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BHD4S2YZ7EVA6KOBYT27MGUO5J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:BHD4S2YZ7EVA6KOBYT27MGUO5J","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":"95adf96c016f903ab636951ce3a917028fca3dd52c3bed177352e06cb55e4657","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-10T23:45:08Z","title_canon_sha256":"627c890bf648ee0c93faac6ee4594185d12e54f6c31d495db31e554f3b172514"},"schema_version":"1.0","source":{"id":"2111.05992","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.05992","created_at":"2026-07-05T04:29:27Z"},{"alias_kind":"arxiv_version","alias_value":"2111.05992v2","created_at":"2026-07-05T04:29:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.05992","created_at":"2026-07-05T04:29:27Z"},{"alias_kind":"pith_short_12","alias_value":"BHD4S2YZ7EVA","created_at":"2026-07-05T04:29:27Z"},{"alias_kind":"pith_short_16","alias_value":"BHD4S2YZ7EVA6KOB","created_at":"2026-07-05T04:29:27Z"},{"alias_kind":"pith_short_8","alias_value":"BHD4S2YZ","created_at":"2026-07-05T04:29:27Z"}],"graph_snapshots":[{"event_id":"sha256:9d4402f607d859d6243bccaa88e83901494dd174845a59c860441a5dfe85fb20","target":"graph","created_at":"2026-07-05T04:29:27Z","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/2111.05992/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The creation and destruction of agents in cooperative multi-agent reinforcement learning (MARL) is a critically under-explored area of research. Current MARL algorithms often assume that the number of agents within a group remains fixed throughout an experiment. However, in many practical problems, an agent may terminate before their teammates. This early termination issue presents a challenge: the terminated agent must learn from the group's success or failure which occurs beyond its own existence. We refer to propagating value from rewards earned by remaining teammates to terminated agents a","authors_text":"Alexander Zook, Andrew Cohen, Ervin Teng, Hunter Henry, Marwan Mattar, Ruo-Ping Dong, Sujoy Ganguly, Vincent-Pierre Berges","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-10T23:45:08Z","title":"On the Use and Misuse of Absorbing States in Multi-agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.05992","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":"sha256:44b2d8197bad81072990e15536e46c86d44b1c20f74cc0756e150c28e4caf1e5","target":"record","created_at":"2026-07-05T04:29:27Z","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":"95adf96c016f903ab636951ce3a917028fca3dd52c3bed177352e06cb55e4657","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-10T23:45:08Z","title_canon_sha256":"627c890bf648ee0c93faac6ee4594185d12e54f6c31d495db31e554f3b172514"},"schema_version":"1.0","source":{"id":"2111.05992","kind":"arxiv","version":2}},"canonical_sha256":"09c7c96b19f92a0f29c1c4f5f61a8eea79582d74ceba00df69618056b0de2bf8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"09c7c96b19f92a0f29c1c4f5f61a8eea79582d74ceba00df69618056b0de2bf8","first_computed_at":"2026-07-05T04:29:27.136362Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:29:27.136362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eU9fp45Ed9bEZKU0KKQ6JqGXyWzj3Q9uIDiRW8EbsRdfTDN82N1g0zFiCZUZHraaAxJvCJwy3WSNR8NtiQSNAw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:29:27.136860Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.05992","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:44b2d8197bad81072990e15536e46c86d44b1c20f74cc0756e150c28e4caf1e5","sha256:9d4402f607d859d6243bccaa88e83901494dd174845a59c860441a5dfe85fb20"],"state_sha256":"804413427a3b68b68cdb1ce39f8afde8fd4d6244b5216b47f63347c0e593a5a3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jhm9L3x5PU+oG8PENfX+jMbVKFMehJNsiuEWIS8kRGHdHymXkMABVUtjHTLVDODIkkHmOx2ipv9+DHEpeg5DAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T19:35:11.021486Z","bundle_sha256":"2885fa5429821652706f7f8b16984bf877bf3eb4ee031fd1cbc54d5b3e616393"}}