{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TPTDA2G63H2SBLVXVTQML5SV7C","short_pith_number":"pith:TPTDA2G6","canonical_record":{"source":{"id":"2508.06871","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-09T07:44:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"49636632eac67226c62979e357884875b5314e842b12b8e24d25291f7b14df08","abstract_canon_sha256":"019ded8b2f804cccb1be3b0e3769c5131c2d98bb661746170d20362794ef6832"},"schema_version":"1.0"},"canonical_sha256":"9be63068ded9f520aeb7ace0c5f655f89936882b5cfa2045f8a8bdf68dfa888f","source":{"kind":"arxiv","id":"2508.06871","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.06871","created_at":"2026-06-26T01:15:45Z"},{"alias_kind":"arxiv_version","alias_value":"2508.06871v1","created_at":"2026-06-26T01:15:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.06871","created_at":"2026-06-26T01:15:45Z"},{"alias_kind":"pith_short_12","alias_value":"TPTDA2G63H2S","created_at":"2026-06-26T01:15:45Z"},{"alias_kind":"pith_short_16","alias_value":"TPTDA2G63H2SBLVX","created_at":"2026-06-26T01:15:45Z"},{"alias_kind":"pith_short_8","alias_value":"TPTDA2G6","created_at":"2026-06-26T01:15:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TPTDA2G63H2SBLVXVTQML5SV7C","target":"record","payload":{"canonical_record":{"source":{"id":"2508.06871","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-09T07:44:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"49636632eac67226c62979e357884875b5314e842b12b8e24d25291f7b14df08","abstract_canon_sha256":"019ded8b2f804cccb1be3b0e3769c5131c2d98bb661746170d20362794ef6832"},"schema_version":"1.0"},"canonical_sha256":"9be63068ded9f520aeb7ace0c5f655f89936882b5cfa2045f8a8bdf68dfa888f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T01:15:45.307943Z","signature_b64":"U58m+Q0iXT82869rWp5X7gn379hUFDMhwvSV3Lgcyws86t3czhoSWExg+IsYCvDeSUXZBny0XUtwyO2601PeAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9be63068ded9f520aeb7ace0c5f655f89936882b5cfa2045f8a8bdf68dfa888f","last_reissued_at":"2026-06-26T01:15:45.307408Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T01:15:45.307408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.06871","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":"2026-06-26T01:15:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FgUJEwjhQ0lwQ3UDySzwJBSLrUS+KZos/aHmOjUN2/2NPVfzwS1HVk80WlTxh9ShinjIxkI8aXmQqOvcI4o5Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T05:47:21.627147Z"},"content_sha256":"51c3023f82fefe4aeead397ddb1e3e6d33c41f8f536766026387f610090cc192","schema_version":"1.0","event_id":"sha256:51c3023f82fefe4aeead397ddb1e3e6d33c41f8f536766026387f610090cc192"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TPTDA2G63H2SBLVXVTQML5SV7C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sparsity-Driven Plasticity in Multi-Task Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aleksandar Todorov, Juan Cardenas-Cartagena, Marco Zullich, Matthia Sabatelli, Rafael F. Cunha","submitted_at":"2025-08-09T07:44:44Z","abstract_excerpt":"Plasticity loss, a diminishing capacity to adapt as training progresses, is a critical challenge in deep reinforcement learning. We examine this issue in multi-task reinforcement learning (MTRL), where higher representational flexibility is crucial for managing diverse and potentially conflicting task demands. We systematically explore how sparsification methods, particularly Gradual Magnitude Pruning (GMP) and Sparse Evolutionary Training (SET), enhance plasticity and consequently improve performance in MTRL agents. We evaluate these approaches across distinct MTRL architectures (shared backb"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.06871","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/2508.06871/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":"2026-06-26T01:15:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D+t92s3JAF8Xc1WT05zytWkROYDDKLfW79vlhqrXWkroVtuNfbZSi2Dy7WllyAfhbrJMkVM01SsKQCzm2fcAAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T05:47:21.627532Z"},"content_sha256":"0772d81d465bedd3121020f8025995a3e976c908ceee9fb8152a304596be60d0","schema_version":"1.0","event_id":"sha256:0772d81d465bedd3121020f8025995a3e976c908ceee9fb8152a304596be60d0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TPTDA2G63H2SBLVXVTQML5SV7C/bundle.json","state_url":"https://pith.science/pith/TPTDA2G63H2SBLVXVTQML5SV7C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TPTDA2G63H2SBLVXVTQML5SV7C/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":"2026-06-26T05:47:21Z","links":{"resolver":"https://pith.science/pith/TPTDA2G63H2SBLVXVTQML5SV7C","bundle":"https://pith.science/pith/TPTDA2G63H2SBLVXVTQML5SV7C/bundle.json","state":"https://pith.science/pith/TPTDA2G63H2SBLVXVTQML5SV7C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TPTDA2G63H2SBLVXVTQML5SV7C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TPTDA2G63H2SBLVXVTQML5SV7C","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":"019ded8b2f804cccb1be3b0e3769c5131c2d98bb661746170d20362794ef6832","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-09T07:44:44Z","title_canon_sha256":"49636632eac67226c62979e357884875b5314e842b12b8e24d25291f7b14df08"},"schema_version":"1.0","source":{"id":"2508.06871","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.06871","created_at":"2026-06-26T01:15:45Z"},{"alias_kind":"arxiv_version","alias_value":"2508.06871v1","created_at":"2026-06-26T01:15:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.06871","created_at":"2026-06-26T01:15:45Z"},{"alias_kind":"pith_short_12","alias_value":"TPTDA2G63H2S","created_at":"2026-06-26T01:15:45Z"},{"alias_kind":"pith_short_16","alias_value":"TPTDA2G63H2SBLVX","created_at":"2026-06-26T01:15:45Z"},{"alias_kind":"pith_short_8","alias_value":"TPTDA2G6","created_at":"2026-06-26T01:15:45Z"}],"graph_snapshots":[{"event_id":"sha256:0772d81d465bedd3121020f8025995a3e976c908ceee9fb8152a304596be60d0","target":"graph","created_at":"2026-06-26T01:15:45Z","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/2508.06871/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Plasticity loss, a diminishing capacity to adapt as training progresses, is a critical challenge in deep reinforcement learning. We examine this issue in multi-task reinforcement learning (MTRL), where higher representational flexibility is crucial for managing diverse and potentially conflicting task demands. We systematically explore how sparsification methods, particularly Gradual Magnitude Pruning (GMP) and Sparse Evolutionary Training (SET), enhance plasticity and consequently improve performance in MTRL agents. We evaluate these approaches across distinct MTRL architectures (shared backb","authors_text":"Aleksandar Todorov, Juan Cardenas-Cartagena, Marco Zullich, Matthia Sabatelli, Rafael F. Cunha","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-09T07:44:44Z","title":"Sparsity-Driven Plasticity in Multi-Task Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.06871","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":"sha256:51c3023f82fefe4aeead397ddb1e3e6d33c41f8f536766026387f610090cc192","target":"record","created_at":"2026-06-26T01:15:45Z","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":"019ded8b2f804cccb1be3b0e3769c5131c2d98bb661746170d20362794ef6832","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-09T07:44:44Z","title_canon_sha256":"49636632eac67226c62979e357884875b5314e842b12b8e24d25291f7b14df08"},"schema_version":"1.0","source":{"id":"2508.06871","kind":"arxiv","version":1}},"canonical_sha256":"9be63068ded9f520aeb7ace0c5f655f89936882b5cfa2045f8a8bdf68dfa888f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9be63068ded9f520aeb7ace0c5f655f89936882b5cfa2045f8a8bdf68dfa888f","first_computed_at":"2026-06-26T01:15:45.307408Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-26T01:15:45.307408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U58m+Q0iXT82869rWp5X7gn379hUFDMhwvSV3Lgcyws86t3czhoSWExg+IsYCvDeSUXZBny0XUtwyO2601PeAQ==","signature_status":"signed_v1","signed_at":"2026-06-26T01:15:45.307943Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.06871","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:51c3023f82fefe4aeead397ddb1e3e6d33c41f8f536766026387f610090cc192","sha256:0772d81d465bedd3121020f8025995a3e976c908ceee9fb8152a304596be60d0"],"state_sha256":"0f38f065570dfbcd3230716ccf55b0bacb9368d394b5dd483ec4364d2f32b008"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mAEabnf8jl1WoiQAKDacSzaoXW9T1uX6FmUkOBhtbbEhjoUlLc0XdFjZghfuC+WYjo4IpD85fjzHCS/PBZ3OAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-26T05:47:21.629659Z","bundle_sha256":"5fcbf78fe3e4c6d3d09dd593f667855a413cfafe50f2d5bbf77f2db409f2c0f7"}}