{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:7DGPR6DZFTNYDMGIKKEHZ3M3PH","short_pith_number":"pith:7DGPR6DZ","canonical_record":{"source":{"id":"2310.08746","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-12T22:19:36Z","cross_cats_sorted":[],"title_canon_sha256":"cd061c2c8c836d462c606b835a65587e128a52e6e987d87165cbae6b9049d358","abstract_canon_sha256":"f31fe7f3a99d911a5c4586ac13e5ec54bb7dd7a7621ba28300e35c43566ec381"},"schema_version":"1.0"},"canonical_sha256":"f8ccf8f8792cdb81b0c852887ced9b79c8a8a0509d7edd08e41efed5fd9dc0b8","source":{"kind":"arxiv","id":"2310.08746","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.08746","created_at":"2026-07-05T07:00:34Z"},{"alias_kind":"arxiv_version","alias_value":"2310.08746v1","created_at":"2026-07-05T07:00:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08746","created_at":"2026-07-05T07:00:34Z"},{"alias_kind":"pith_short_12","alias_value":"7DGPR6DZFTNY","created_at":"2026-07-05T07:00:34Z"},{"alias_kind":"pith_short_16","alias_value":"7DGPR6DZFTNYDMGI","created_at":"2026-07-05T07:00:34Z"},{"alias_kind":"pith_short_8","alias_value":"7DGPR6DZ","created_at":"2026-07-05T07:00:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:7DGPR6DZFTNYDMGIKKEHZ3M3PH","target":"record","payload":{"canonical_record":{"source":{"id":"2310.08746","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-12T22:19:36Z","cross_cats_sorted":[],"title_canon_sha256":"cd061c2c8c836d462c606b835a65587e128a52e6e987d87165cbae6b9049d358","abstract_canon_sha256":"f31fe7f3a99d911a5c4586ac13e5ec54bb7dd7a7621ba28300e35c43566ec381"},"schema_version":"1.0"},"canonical_sha256":"f8ccf8f8792cdb81b0c852887ced9b79c8a8a0509d7edd08e41efed5fd9dc0b8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:00:34.250857Z","signature_b64":"zRuXJ1lCW1Qu5fl9Tr4xjhjinXY3xvJPXW6wqDoC194VwGKi+p1Fz8iA15yDoRIlbbG3oXbqluW0FPDhKrXUDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8ccf8f8792cdb81b0c852887ced9b79c8a8a0509d7edd08e41efed5fd9dc0b8","last_reissued_at":"2026-07-05T07:00:34.250352Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:00:34.250352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.08746","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":"2026-07-05T07:00:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1BkKmEh2RcMMG2N6W2h+VpHWVoHHjqenISXDUqPJZuyk/fYuKqt3vsepAnssT7IpxNszYw0/2bym+rdlLX5yAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:39:06.052757Z"},"content_sha256":"4678d809ff18f013144309af86d5558eeb2ff28a3237121b9c2677e3c976cc78","schema_version":"1.0","event_id":"sha256:4678d809ff18f013144309af86d5558eeb2ff28a3237121b9c2677e3c976cc78"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:7DGPR6DZFTNYDMGIKKEHZ3M3PH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robustness to Multi-Modal Environment Uncertainty in MARL using Curriculum Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aakriti Agrawal, Furong Huang, Rohith Aralikatti, Yanchao Sun","submitted_at":"2023-10-12T22:19:36Z","abstract_excerpt":"Multi-agent reinforcement learning (MARL) plays a pivotal role in tackling real-world challenges. However, the seamless transition of trained policies from simulations to real-world requires it to be robust to various environmental uncertainties. Existing works focus on finding Nash Equilibrium or the optimal policy under uncertainty in one environment variable (i.e. action, state or reward). This is because a multi-agent system itself is highly complex and unstationary. However, in real-world situation uncertainty can occur in multiple environment variables simultaneously. This work is the fi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08746","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/2310.08746/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":"2026-07-05T07:00:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n6b/PfWpVZPrY5UieQ/OD5fuIEEqHHrnlREKo3VYJqon45S1rIcu4OFAG4AJ4gzkxyBMMDPP8aVQXR0CwYWBAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:39:06.053846Z"},"content_sha256":"159030a270981be1019dbf1e81a0b1acfcb6c721aa7db8a6de20f5e3b31fc776","schema_version":"1.0","event_id":"sha256:159030a270981be1019dbf1e81a0b1acfcb6c721aa7db8a6de20f5e3b31fc776"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7DGPR6DZFTNYDMGIKKEHZ3M3PH/bundle.json","state_url":"https://pith.science/pith/7DGPR6DZFTNYDMGIKKEHZ3M3PH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7DGPR6DZFTNYDMGIKKEHZ3M3PH/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":"2026-08-05T15:39:06Z","links":{"resolver":"https://pith.science/pith/7DGPR6DZFTNYDMGIKKEHZ3M3PH","bundle":"https://pith.science/pith/7DGPR6DZFTNYDMGIKKEHZ3M3PH/bundle.json","state":"https://pith.science/pith/7DGPR6DZFTNYDMGIKKEHZ3M3PH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7DGPR6DZFTNYDMGIKKEHZ3M3PH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7DGPR6DZFTNYDMGIKKEHZ3M3PH","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":"f31fe7f3a99d911a5c4586ac13e5ec54bb7dd7a7621ba28300e35c43566ec381","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-12T22:19:36Z","title_canon_sha256":"cd061c2c8c836d462c606b835a65587e128a52e6e987d87165cbae6b9049d358"},"schema_version":"1.0","source":{"id":"2310.08746","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.08746","created_at":"2026-07-05T07:00:34Z"},{"alias_kind":"arxiv_version","alias_value":"2310.08746v1","created_at":"2026-07-05T07:00:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08746","created_at":"2026-07-05T07:00:34Z"},{"alias_kind":"pith_short_12","alias_value":"7DGPR6DZFTNY","created_at":"2026-07-05T07:00:34Z"},{"alias_kind":"pith_short_16","alias_value":"7DGPR6DZFTNYDMGI","created_at":"2026-07-05T07:00:34Z"},{"alias_kind":"pith_short_8","alias_value":"7DGPR6DZ","created_at":"2026-07-05T07:00:34Z"}],"graph_snapshots":[{"event_id":"sha256:159030a270981be1019dbf1e81a0b1acfcb6c721aa7db8a6de20f5e3b31fc776","target":"graph","created_at":"2026-07-05T07:00:34Z","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/2310.08746/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-agent reinforcement learning (MARL) plays a pivotal role in tackling real-world challenges. However, the seamless transition of trained policies from simulations to real-world requires it to be robust to various environmental uncertainties. Existing works focus on finding Nash Equilibrium or the optimal policy under uncertainty in one environment variable (i.e. action, state or reward). This is because a multi-agent system itself is highly complex and unstationary. However, in real-world situation uncertainty can occur in multiple environment variables simultaneously. This work is the fi","authors_text":"Aakriti Agrawal, Furong Huang, Rohith Aralikatti, Yanchao Sun","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-12T22:19:36Z","title":"Robustness to Multi-Modal Environment Uncertainty in MARL using Curriculum Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08746","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":"sha256:4678d809ff18f013144309af86d5558eeb2ff28a3237121b9c2677e3c976cc78","target":"record","created_at":"2026-07-05T07:00:34Z","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":"f31fe7f3a99d911a5c4586ac13e5ec54bb7dd7a7621ba28300e35c43566ec381","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-12T22:19:36Z","title_canon_sha256":"cd061c2c8c836d462c606b835a65587e128a52e6e987d87165cbae6b9049d358"},"schema_version":"1.0","source":{"id":"2310.08746","kind":"arxiv","version":1}},"canonical_sha256":"f8ccf8f8792cdb81b0c852887ced9b79c8a8a0509d7edd08e41efed5fd9dc0b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8ccf8f8792cdb81b0c852887ced9b79c8a8a0509d7edd08e41efed5fd9dc0b8","first_computed_at":"2026-07-05T07:00:34.250352Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:00:34.250352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zRuXJ1lCW1Qu5fl9Tr4xjhjinXY3xvJPXW6wqDoC194VwGKi+p1Fz8iA15yDoRIlbbG3oXbqluW0FPDhKrXUDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:00:34.250857Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.08746","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4678d809ff18f013144309af86d5558eeb2ff28a3237121b9c2677e3c976cc78","sha256:159030a270981be1019dbf1e81a0b1acfcb6c721aa7db8a6de20f5e3b31fc776"],"state_sha256":"b214c20e944f02c65dff2633bac18058f57f98d0f8cbaa4979bef66be77e006a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wsqOoQGwKuBI4JOFTFU0CsnYH/tvEec+xzmhlPBdjeSzB+uPcDWSLu0ogQLgp0QXQ8mknXSGlZnlyz3tD1a2Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T15:39:06.060230Z","bundle_sha256":"331d02915b7a0c0d54985382a049f06fa3dde59580647c7936c7bc20c26684f3"}}