{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:TAMHXFKGSFDY3BJXZKPKHQH2AU","short_pith_number":"pith:TAMHXFKG","canonical_record":{"source":{"id":"2205.14495","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-28T17:59:00Z","cross_cats_sorted":[],"title_canon_sha256":"bc196c21a3a28ae8e39c0eebe04aea7b8dc1ca4fc3e02650546194847fa74343","abstract_canon_sha256":"97192f23d136fd9986a3df27efd8046ffab3a615fab8bd1a7d9268f7ca7fc87a"},"schema_version":"1.0"},"canonical_sha256":"98187b954691478d8537ca9ea3c0fa053890db21d9d7109ce20259d491dc878f","source":{"kind":"arxiv","id":"2205.14495","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.14495","created_at":"2026-07-05T06:11:16Z"},{"alias_kind":"arxiv_version","alias_value":"2205.14495v3","created_at":"2026-07-05T06:11:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.14495","created_at":"2026-07-05T06:11:16Z"},{"alias_kind":"pith_short_12","alias_value":"TAMHXFKGSFDY","created_at":"2026-07-05T06:11:16Z"},{"alias_kind":"pith_short_16","alias_value":"TAMHXFKGSFDY3BJX","created_at":"2026-07-05T06:11:16Z"},{"alias_kind":"pith_short_8","alias_value":"TAMHXFKG","created_at":"2026-07-05T06:11:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:TAMHXFKGSFDY3BJXZKPKHQH2AU","target":"record","payload":{"canonical_record":{"source":{"id":"2205.14495","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-28T17:59:00Z","cross_cats_sorted":[],"title_canon_sha256":"bc196c21a3a28ae8e39c0eebe04aea7b8dc1ca4fc3e02650546194847fa74343","abstract_canon_sha256":"97192f23d136fd9986a3df27efd8046ffab3a615fab8bd1a7d9268f7ca7fc87a"},"schema_version":"1.0"},"canonical_sha256":"98187b954691478d8537ca9ea3c0fa053890db21d9d7109ce20259d491dc878f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:11:16.103662Z","signature_b64":"A1ij0XRFpjNmJ2IAyqNmRTk08Y+8rLtHANVZ2ht1HBOTjEU3h2j5XNIgdSmJN5G8bHSLYuQ3qKA/lT/D4zjsAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98187b954691478d8537ca9ea3c0fa053890db21d9d7109ce20259d491dc878f","last_reissued_at":"2026-07-05T06:11:16.103273Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:11:16.103273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.14495","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:11:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w3zX5nvsKvxv6YXDZtdQSX+jkKNI4iVqMu+8s9pPEa1Dzw/b3UwKjOsUjmABfgL8llJVFMnOCKyB75kOmg2gDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:06:32.775459Z"},"content_sha256":"30b14712d5591f2588fd75a6b515a92f6153a62e0c7f61d84296e14c94d1788a","schema_version":"1.0","event_id":"sha256:30b14712d5591f2588fd75a6b515a92f6153a62e0c7f61d84296e14c94d1788a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:TAMHXFKGSFDY3BJXZKPKHQH2AU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Task-Agnostic Continual Reinforcement Learning: Gaining Insights and Overcoming Challenges","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jonas Mueller, Laurent Charlin, Massimo Caccia, Rasool Fakoor, Taesup Kim","submitted_at":"2022-05-28T17:59:00Z","abstract_excerpt":"Continual learning (CL) enables the development of models and agents that learn from a sequence of tasks while addressing the limitations of standard deep learning approaches, such as catastrophic forgetting. In this work, we investigate the factors that contribute to the performance differences between task-agnostic CL and multi-task (MTL) agents. We pose two hypotheses: (1) task-agnostic methods might provide advantages in settings with limited data, computation, or high dimensionality, and (2) faster adaptation may be particularly beneficial in continual learning settings, helping to mitiga"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.14495","kind":"arxiv","version":3},"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/2205.14495/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":"2026-07-05T06:11:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jLN2K+KEze5e5KKOvoePEAUyrcg+0qu6JcVeO68lgcPOIy2vDAJzn/9J69PglubTsSjNRysGN5ulaI/FF+anAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:06:32.775833Z"},"content_sha256":"f29efcf951b211dfdcf01e84fbd6cf4a667f3c06b6fd1f547575ecf96a68c395","schema_version":"1.0","event_id":"sha256:f29efcf951b211dfdcf01e84fbd6cf4a667f3c06b6fd1f547575ecf96a68c395"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TAMHXFKGSFDY3BJXZKPKHQH2AU/bundle.json","state_url":"https://pith.science/pith/TAMHXFKGSFDY3BJXZKPKHQH2AU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TAMHXFKGSFDY3BJXZKPKHQH2AU/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":"2026-08-06T01:06:32Z","links":{"resolver":"https://pith.science/pith/TAMHXFKGSFDY3BJXZKPKHQH2AU","bundle":"https://pith.science/pith/TAMHXFKGSFDY3BJXZKPKHQH2AU/bundle.json","state":"https://pith.science/pith/TAMHXFKGSFDY3BJXZKPKHQH2AU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TAMHXFKGSFDY3BJXZKPKHQH2AU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:TAMHXFKGSFDY3BJXZKPKHQH2AU","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":"97192f23d136fd9986a3df27efd8046ffab3a615fab8bd1a7d9268f7ca7fc87a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-28T17:59:00Z","title_canon_sha256":"bc196c21a3a28ae8e39c0eebe04aea7b8dc1ca4fc3e02650546194847fa74343"},"schema_version":"1.0","source":{"id":"2205.14495","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.14495","created_at":"2026-07-05T06:11:16Z"},{"alias_kind":"arxiv_version","alias_value":"2205.14495v3","created_at":"2026-07-05T06:11:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.14495","created_at":"2026-07-05T06:11:16Z"},{"alias_kind":"pith_short_12","alias_value":"TAMHXFKGSFDY","created_at":"2026-07-05T06:11:16Z"},{"alias_kind":"pith_short_16","alias_value":"TAMHXFKGSFDY3BJX","created_at":"2026-07-05T06:11:16Z"},{"alias_kind":"pith_short_8","alias_value":"TAMHXFKG","created_at":"2026-07-05T06:11:16Z"}],"graph_snapshots":[{"event_id":"sha256:f29efcf951b211dfdcf01e84fbd6cf4a667f3c06b6fd1f547575ecf96a68c395","target":"graph","created_at":"2026-07-05T06:11:16Z","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/2205.14495/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Continual learning (CL) enables the development of models and agents that learn from a sequence of tasks while addressing the limitations of standard deep learning approaches, such as catastrophic forgetting. In this work, we investigate the factors that contribute to the performance differences between task-agnostic CL and multi-task (MTL) agents. We pose two hypotheses: (1) task-agnostic methods might provide advantages in settings with limited data, computation, or high dimensionality, and (2) faster adaptation may be particularly beneficial in continual learning settings, helping to mitiga","authors_text":"Jonas Mueller, Laurent Charlin, Massimo Caccia, Rasool Fakoor, Taesup Kim","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-28T17:59:00Z","title":"Task-Agnostic Continual Reinforcement Learning: Gaining Insights and Overcoming Challenges"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.14495","kind":"arxiv","version":3},"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":"sha256:30b14712d5591f2588fd75a6b515a92f6153a62e0c7f61d84296e14c94d1788a","target":"record","created_at":"2026-07-05T06:11:16Z","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":"97192f23d136fd9986a3df27efd8046ffab3a615fab8bd1a7d9268f7ca7fc87a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-28T17:59:00Z","title_canon_sha256":"bc196c21a3a28ae8e39c0eebe04aea7b8dc1ca4fc3e02650546194847fa74343"},"schema_version":"1.0","source":{"id":"2205.14495","kind":"arxiv","version":3}},"canonical_sha256":"98187b954691478d8537ca9ea3c0fa053890db21d9d7109ce20259d491dc878f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"98187b954691478d8537ca9ea3c0fa053890db21d9d7109ce20259d491dc878f","first_computed_at":"2026-07-05T06:11:16.103273Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:11:16.103273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A1ij0XRFpjNmJ2IAyqNmRTk08Y+8rLtHANVZ2ht1HBOTjEU3h2j5XNIgdSmJN5G8bHSLYuQ3qKA/lT/D4zjsAw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:11:16.103662Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.14495","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:30b14712d5591f2588fd75a6b515a92f6153a62e0c7f61d84296e14c94d1788a","sha256:f29efcf951b211dfdcf01e84fbd6cf4a667f3c06b6fd1f547575ecf96a68c395"],"state_sha256":"923961c49cd04c67acce724c1921f61374ee5928c0b8bffd0ddc7b2ce1fbb90d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9zgCXbSf5uMbZSF/JxMaJp0qtHUwLBlEhX+3VEpZ0/J2VqlSfWGq/gAiMmcKMK6TNfOcgu9HzWwCcQAgLWrIAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T01:06:32.778519Z","bundle_sha256":"d0d815e3a1b31d7ed49bc0ba9457df5d63b6c8f9f9ce8276689a2d136c05c1bf"}}