{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:YUGH3AB62VAKZRPJITX5EMA6PH","short_pith_number":"pith:YUGH3AB6","canonical_record":{"source":{"id":"2305.18444","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-29T03:36:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1434152b6a566608c574e63ace27b895cefbc1449a9b98197570c8293e36ad2c","abstract_canon_sha256":"e45264fb08c45879bb1620e461e3ed0060a17cead3d8aae1721605c661c55546"},"schema_version":"1.0"},"canonical_sha256":"c50c7d803ed540acc5e944efd2301e79d8532e804dc0f326076c4faa2507d101","source":{"kind":"arxiv","id":"2305.18444","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.18444","created_at":"2026-07-05T06:17:08Z"},{"alias_kind":"arxiv_version","alias_value":"2305.18444v2","created_at":"2026-07-05T06:17:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18444","created_at":"2026-07-05T06:17:08Z"},{"alias_kind":"pith_short_12","alias_value":"YUGH3AB62VAK","created_at":"2026-07-05T06:17:08Z"},{"alias_kind":"pith_short_16","alias_value":"YUGH3AB62VAKZRPJ","created_at":"2026-07-05T06:17:08Z"},{"alias_kind":"pith_short_8","alias_value":"YUGH3AB6","created_at":"2026-07-05T06:17:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:YUGH3AB62VAKZRPJITX5EMA6PH","target":"record","payload":{"canonical_record":{"source":{"id":"2305.18444","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-29T03:36:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1434152b6a566608c574e63ace27b895cefbc1449a9b98197570c8293e36ad2c","abstract_canon_sha256":"e45264fb08c45879bb1620e461e3ed0060a17cead3d8aae1721605c661c55546"},"schema_version":"1.0"},"canonical_sha256":"c50c7d803ed540acc5e944efd2301e79d8532e804dc0f326076c4faa2507d101","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:08.078853Z","signature_b64":"6hxnIg3omV2pm9XILmj7hL6JMyg6xHM8o6xe4BCGEIbKJeJsLDuY9uVrrd638CVyJNptAarUb4C4U1X3ZgBlBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c50c7d803ed540acc5e944efd2301e79d8532e804dc0f326076c4faa2507d101","last_reissued_at":"2026-07-05T06:17:08.078514Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:08.078514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.18444","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":"2026-07-05T06:17:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K7Svb0xt426sTN4IJOc9gBY3cNyGoZXlSPGsQCzHHHnN/Y/O1rDPdv8BjSmn8r6heYA5a01C7jB/Y5cReu6RCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T00:01:07.536639Z"},"content_sha256":"3091830b6528fb9c342706423d83187f25a9908ca501d71c4b7b9249e21fad9f","schema_version":"1.0","event_id":"sha256:3091830b6528fb9c342706423d83187f25a9908ca501d71c4b7b9249e21fad9f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:YUGH3AB62VAKZRPJITX5EMA6PH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Continual Task Allocation in Meta-Policy Network via Sparse Prompting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Guodong Long, Jing Jiang, Tianyi Zhou, Yijun Yang, Yuhui Shi","submitted_at":"2023-05-29T03:36:32Z","abstract_excerpt":"How to train a generalizable meta-policy by continually learning a sequence of tasks? It is a natural human skill yet challenging to achieve by current reinforcement learning: the agent is expected to quickly adapt to new tasks (plasticity) meanwhile retaining the common knowledge from previous tasks (stability). We address it by \"Continual Task Allocation via Sparse Prompting (CoTASP)\", which learns over-complete dictionaries to produce sparse masks as prompts extracting a sub-network for each task from a meta-policy network. CoTASP trains a policy for each task by optimizing the prompts and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18444","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/2305.18444/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":"2026-07-05T06:17:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dfC4IwvLXA1HmW5V9TszORyqwQ1dtGGDdiLQleswxmGC4bhmjAxL+Tc9DZT7lwrhR0b93JUW0GMuGp2C/vZWDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T00:01:07.537217Z"},"content_sha256":"d8056e8e2c4dcc5976083ae67f66b3d4fede2912225eeefefef0b53c979361f2","schema_version":"1.0","event_id":"sha256:d8056e8e2c4dcc5976083ae67f66b3d4fede2912225eeefefef0b53c979361f2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YUGH3AB62VAKZRPJITX5EMA6PH/bundle.json","state_url":"https://pith.science/pith/YUGH3AB62VAKZRPJITX5EMA6PH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YUGH3AB62VAKZRPJITX5EMA6PH/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":"2026-08-05T00:01:07Z","links":{"resolver":"https://pith.science/pith/YUGH3AB62VAKZRPJITX5EMA6PH","bundle":"https://pith.science/pith/YUGH3AB62VAKZRPJITX5EMA6PH/bundle.json","state":"https://pith.science/pith/YUGH3AB62VAKZRPJITX5EMA6PH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YUGH3AB62VAKZRPJITX5EMA6PH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YUGH3AB62VAKZRPJITX5EMA6PH","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":"e45264fb08c45879bb1620e461e3ed0060a17cead3d8aae1721605c661c55546","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-29T03:36:32Z","title_canon_sha256":"1434152b6a566608c574e63ace27b895cefbc1449a9b98197570c8293e36ad2c"},"schema_version":"1.0","source":{"id":"2305.18444","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.18444","created_at":"2026-07-05T06:17:08Z"},{"alias_kind":"arxiv_version","alias_value":"2305.18444v2","created_at":"2026-07-05T06:17:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18444","created_at":"2026-07-05T06:17:08Z"},{"alias_kind":"pith_short_12","alias_value":"YUGH3AB62VAK","created_at":"2026-07-05T06:17:08Z"},{"alias_kind":"pith_short_16","alias_value":"YUGH3AB62VAKZRPJ","created_at":"2026-07-05T06:17:08Z"},{"alias_kind":"pith_short_8","alias_value":"YUGH3AB6","created_at":"2026-07-05T06:17:08Z"}],"graph_snapshots":[{"event_id":"sha256:d8056e8e2c4dcc5976083ae67f66b3d4fede2912225eeefefef0b53c979361f2","target":"graph","created_at":"2026-07-05T06:17:08Z","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/2305.18444/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"How to train a generalizable meta-policy by continually learning a sequence of tasks? It is a natural human skill yet challenging to achieve by current reinforcement learning: the agent is expected to quickly adapt to new tasks (plasticity) meanwhile retaining the common knowledge from previous tasks (stability). We address it by \"Continual Task Allocation via Sparse Prompting (CoTASP)\", which learns over-complete dictionaries to produce sparse masks as prompts extracting a sub-network for each task from a meta-policy network. CoTASP trains a policy for each task by optimizing the prompts and ","authors_text":"Guodong Long, Jing Jiang, Tianyi Zhou, Yijun Yang, Yuhui Shi","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-29T03:36:32Z","title":"Continual Task Allocation in Meta-Policy Network via Sparse Prompting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18444","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":"sha256:3091830b6528fb9c342706423d83187f25a9908ca501d71c4b7b9249e21fad9f","target":"record","created_at":"2026-07-05T06:17:08Z","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":"e45264fb08c45879bb1620e461e3ed0060a17cead3d8aae1721605c661c55546","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-29T03:36:32Z","title_canon_sha256":"1434152b6a566608c574e63ace27b895cefbc1449a9b98197570c8293e36ad2c"},"schema_version":"1.0","source":{"id":"2305.18444","kind":"arxiv","version":2}},"canonical_sha256":"c50c7d803ed540acc5e944efd2301e79d8532e804dc0f326076c4faa2507d101","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c50c7d803ed540acc5e944efd2301e79d8532e804dc0f326076c4faa2507d101","first_computed_at":"2026-07-05T06:17:08.078514Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:17:08.078514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6hxnIg3omV2pm9XILmj7hL6JMyg6xHM8o6xe4BCGEIbKJeJsLDuY9uVrrd638CVyJNptAarUb4C4U1X3ZgBlBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:17:08.078853Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.18444","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3091830b6528fb9c342706423d83187f25a9908ca501d71c4b7b9249e21fad9f","sha256:d8056e8e2c4dcc5976083ae67f66b3d4fede2912225eeefefef0b53c979361f2"],"state_sha256":"a1fe33b33fd66e5c16b69d14ced4c0b22021c4dc520eb9c4656b75db7f6d17d2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"170QGit/hoI6GDySOQMCswpTRtKHKTboJ0NviLLWSWMQS2LdTfe433N+R5zE0PO5X+DQIKNuk/DZUW2+HRmcDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T00:01:07.542038Z","bundle_sha256":"9c5abe896e96df5c8294173e11f1074780333cf862a6cf90c9b1ac031f79e0ab"}}