{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ULWF5RXVSW4IEG4SKIQDDH2BCA","short_pith_number":"pith:ULWF5RXV","canonical_record":{"source":{"id":"2501.12061","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-21T11:31:01Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"539b3aa611e57bcc2000b3355dbc445397ecc3f20b2ba0739f9a8bab98cd2ed3","abstract_canon_sha256":"56761678b7a23fd0db73329ff988ce5f9692880cb4975485cdc0b331511bde0b"},"schema_version":"1.0"},"canonical_sha256":"a2ec5ec6f595b8821b925220319f41102e993a45192b0a40bb5978b6085418dc","source":{"kind":"arxiv","id":"2501.12061","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.12061","created_at":"2026-07-05T10:03:31Z"},{"alias_kind":"arxiv_version","alias_value":"2501.12061v1","created_at":"2026-07-05T10:03:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12061","created_at":"2026-07-05T10:03:31Z"},{"alias_kind":"pith_short_12","alias_value":"ULWF5RXVSW4I","created_at":"2026-07-05T10:03:31Z"},{"alias_kind":"pith_short_16","alias_value":"ULWF5RXVSW4IEG4S","created_at":"2026-07-05T10:03:31Z"},{"alias_kind":"pith_short_8","alias_value":"ULWF5RXV","created_at":"2026-07-05T10:03:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ULWF5RXVSW4IEG4SKIQDDH2BCA","target":"record","payload":{"canonical_record":{"source":{"id":"2501.12061","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-21T11:31:01Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"539b3aa611e57bcc2000b3355dbc445397ecc3f20b2ba0739f9a8bab98cd2ed3","abstract_canon_sha256":"56761678b7a23fd0db73329ff988ce5f9692880cb4975485cdc0b331511bde0b"},"schema_version":"1.0"},"canonical_sha256":"a2ec5ec6f595b8821b925220319f41102e993a45192b0a40bb5978b6085418dc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:03:31.266532Z","signature_b64":"4kqCbkRNpWJkpEwmMiz5RX2Vhlmvw12rspT+me+p2w5Wg6ojy6grlqMLI2MgyFQKPAQKqiM8wi5Vq3+dC8/NCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2ec5ec6f595b8821b925220319f41102e993a45192b0a40bb5978b6085418dc","last_reissued_at":"2026-07-05T10:03:31.266139Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:03:31.266139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.12061","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":"2026-07-05T10:03:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IguiPNS5s0goQBROn3ZEuiwKF77EtukYNEZLLkHTr8n8FL7ynnqUkW4xcKSUaBj8MLiM3oTtBi248EVGXQLrAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T09:45:08.725009Z"},"content_sha256":"6cd7613df68945fdbe5a248167a23077180267fd4e7420e691a747673c750077","schema_version":"1.0","event_id":"sha256:6cd7613df68945fdbe5a248167a23077180267fd4e7420e691a747673c750077"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ULWF5RXVSW4IEG4SKIQDDH2BCA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tackling Uncertainties in Multi-Agent Reinforcement Learning through Integration of Agent Termination Dynamics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Pallab Dasgupta, Somnath Hazra, Soumyajit Dey","submitted_at":"2025-01-21T11:31:01Z","abstract_excerpt":"Multi-Agent Reinforcement Learning (MARL) has gained significant traction for solving complex real-world tasks, but the inherent stochasticity and uncertainty in these environments pose substantial challenges to efficient and robust policy learning. While Distributional Reinforcement Learning has been successfully applied in single-agent settings to address risk and uncertainty, its application in MARL is substantially limited. In this work, we propose a novel approach that integrates distributional learning with a safety-focused loss function to improve convergence in cooperative MARL tasks. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12061","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/2501.12061/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":"2026-07-05T10:03:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"30jsI7x2+EaHHy8G831iqbzbsThRHoWU2OYPjyN9EPAYN0v0Ya8ShUsylb51ltkBUd2hyFVDESy1wKJVT4GsCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T09:45:08.725542Z"},"content_sha256":"1ecf0bad4009cb1924a8cc0ea8827631c759714af84e946d1006f200747050c2","schema_version":"1.0","event_id":"sha256:1ecf0bad4009cb1924a8cc0ea8827631c759714af84e946d1006f200747050c2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ULWF5RXVSW4IEG4SKIQDDH2BCA/bundle.json","state_url":"https://pith.science/pith/ULWF5RXVSW4IEG4SKIQDDH2BCA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ULWF5RXVSW4IEG4SKIQDDH2BCA/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":"2026-08-11T09:45:08Z","links":{"resolver":"https://pith.science/pith/ULWF5RXVSW4IEG4SKIQDDH2BCA","bundle":"https://pith.science/pith/ULWF5RXVSW4IEG4SKIQDDH2BCA/bundle.json","state":"https://pith.science/pith/ULWF5RXVSW4IEG4SKIQDDH2BCA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ULWF5RXVSW4IEG4SKIQDDH2BCA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ULWF5RXVSW4IEG4SKIQDDH2BCA","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":"56761678b7a23fd0db73329ff988ce5f9692880cb4975485cdc0b331511bde0b","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-21T11:31:01Z","title_canon_sha256":"539b3aa611e57bcc2000b3355dbc445397ecc3f20b2ba0739f9a8bab98cd2ed3"},"schema_version":"1.0","source":{"id":"2501.12061","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.12061","created_at":"2026-07-05T10:03:31Z"},{"alias_kind":"arxiv_version","alias_value":"2501.12061v1","created_at":"2026-07-05T10:03:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12061","created_at":"2026-07-05T10:03:31Z"},{"alias_kind":"pith_short_12","alias_value":"ULWF5RXVSW4I","created_at":"2026-07-05T10:03:31Z"},{"alias_kind":"pith_short_16","alias_value":"ULWF5RXVSW4IEG4S","created_at":"2026-07-05T10:03:31Z"},{"alias_kind":"pith_short_8","alias_value":"ULWF5RXV","created_at":"2026-07-05T10:03:31Z"}],"graph_snapshots":[{"event_id":"sha256:1ecf0bad4009cb1924a8cc0ea8827631c759714af84e946d1006f200747050c2","target":"graph","created_at":"2026-07-05T10:03:31Z","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/2501.12061/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-Agent Reinforcement Learning (MARL) has gained significant traction for solving complex real-world tasks, but the inherent stochasticity and uncertainty in these environments pose substantial challenges to efficient and robust policy learning. While Distributional Reinforcement Learning has been successfully applied in single-agent settings to address risk and uncertainty, its application in MARL is substantially limited. In this work, we propose a novel approach that integrates distributional learning with a safety-focused loss function to improve convergence in cooperative MARL tasks. ","authors_text":"Pallab Dasgupta, Somnath Hazra, Soumyajit Dey","cross_cats":["cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-21T11:31:01Z","title":"Tackling Uncertainties in Multi-Agent Reinforcement Learning through Integration of Agent Termination Dynamics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12061","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":"sha256:6cd7613df68945fdbe5a248167a23077180267fd4e7420e691a747673c750077","target":"record","created_at":"2026-07-05T10:03:31Z","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":"56761678b7a23fd0db73329ff988ce5f9692880cb4975485cdc0b331511bde0b","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-21T11:31:01Z","title_canon_sha256":"539b3aa611e57bcc2000b3355dbc445397ecc3f20b2ba0739f9a8bab98cd2ed3"},"schema_version":"1.0","source":{"id":"2501.12061","kind":"arxiv","version":1}},"canonical_sha256":"a2ec5ec6f595b8821b925220319f41102e993a45192b0a40bb5978b6085418dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a2ec5ec6f595b8821b925220319f41102e993a45192b0a40bb5978b6085418dc","first_computed_at":"2026-07-05T10:03:31.266139Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:03:31.266139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4kqCbkRNpWJkpEwmMiz5RX2Vhlmvw12rspT+me+p2w5Wg6ojy6grlqMLI2MgyFQKPAQKqiM8wi5Vq3+dC8/NCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:03:31.266532Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.12061","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6cd7613df68945fdbe5a248167a23077180267fd4e7420e691a747673c750077","sha256:1ecf0bad4009cb1924a8cc0ea8827631c759714af84e946d1006f200747050c2"],"state_sha256":"0fdb57e7bdc08f5bb12f8c929db5cc48ca06c364d58a543f5a2accd40fc1fc46"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B7zJEzzrHPZR5MCo4Pp03nHf6NJYvI11i3mV8h17sp5Q+noMUv5el0+obyeYSMPSh/f5NOvuFNrHcZiNm7HDCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T09:45:08.729420Z","bundle_sha256":"604e64f622d1a49eb9830d62626e5fdbeaf0345769a17715c8aa304ca45189e8"}}