{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ETFQBEYVGIJ7EEYSUPRY76EZDK","short_pith_number":"pith:ETFQBEYV","canonical_record":{"source":{"id":"2507.06615","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-09T07:36:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1c0a1a0d6086b130a0ed1ff849a16a5611d7dd679f476b82a162f9b162c8d318","abstract_canon_sha256":"8a65651fae63d216b5eb31b1fd1bdf68c5e29f8dfe822535ed3f86d914ce8c3d"},"schema_version":"1.0"},"canonical_sha256":"24cb0093153213f21312a3e38ff8991abb96e5e4cf49ed3643fa1892e250cd6d","source":{"kind":"arxiv","id":"2507.06615","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.06615","created_at":"2026-07-05T11:34:19Z"},{"alias_kind":"arxiv_version","alias_value":"2507.06615v1","created_at":"2026-07-05T11:34:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06615","created_at":"2026-07-05T11:34:19Z"},{"alias_kind":"pith_short_12","alias_value":"ETFQBEYVGIJ7","created_at":"2026-07-05T11:34:19Z"},{"alias_kind":"pith_short_16","alias_value":"ETFQBEYVGIJ7EEYS","created_at":"2026-07-05T11:34:19Z"},{"alias_kind":"pith_short_8","alias_value":"ETFQBEYV","created_at":"2026-07-05T11:34:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ETFQBEYVGIJ7EEYSUPRY76EZDK","target":"record","payload":{"canonical_record":{"source":{"id":"2507.06615","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-09T07:36:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1c0a1a0d6086b130a0ed1ff849a16a5611d7dd679f476b82a162f9b162c8d318","abstract_canon_sha256":"8a65651fae63d216b5eb31b1fd1bdf68c5e29f8dfe822535ed3f86d914ce8c3d"},"schema_version":"1.0"},"canonical_sha256":"24cb0093153213f21312a3e38ff8991abb96e5e4cf49ed3643fa1892e250cd6d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:19.404340Z","signature_b64":"jW21w4PXJqqO3sUV3AN71I69ss4WUENLnKpygGVFoj/B6c7aYLfo2s3Vhadf/tJw0QsNcIICmv6xvTOwnpzcDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24cb0093153213f21312a3e38ff8991abb96e5e4cf49ed3643fa1892e250cd6d","last_reissued_at":"2026-07-05T11:34:19.403845Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:19.403845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.06615","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":"2026-07-05T11:34:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HcQoHkN2d8DUGb5D0XoUKtzZTMydkvEaPqwhaIDcZSWAPPoHZH/X1N0lZdCJV17IUGwbYmVc3S3U+38G0zQbCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T10:22:32.814908Z"},"content_sha256":"a787c4255b57de66b9c9e9e37cd78ecf2e50f2d248247abd0c0272720c5b9f6d","schema_version":"1.0","event_id":"sha256:a787c4255b57de66b9c9e9e37cd78ecf2e50f2d248247abd0c0272720c5b9f6d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ETFQBEYVGIJ7EEYSUPRY76EZDK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Multi-Task Reinforcement Learning with Cross-Task Policy Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haobo Fu, Jian Cheng, Jinmin He, Junliang Xing, Kai Li, Qiang Fu, Yifan Zang","submitted_at":"2025-07-09T07:36:28Z","abstract_excerpt":"Multi-task reinforcement learning endeavors to efficiently leverage shared information across various tasks, facilitating the simultaneous learning of multiple tasks. Existing approaches primarily focus on parameter sharing with carefully designed network structures or tailored optimization procedures. However, they overlook a direct and complementary way to exploit cross-task similarities: the control policies of tasks already proficient in some skills can provide explicit guidance for unmastered tasks to accelerate skills acquisition. To this end, we present a novel framework called Cross-Ta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06615","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/2507.06615/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":"2026-07-05T11:34:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AONMCkRNuYqStq/U+NQxL56yswc3iCJLB/awx523lyz/0TM4LTzeqVPqG5NY8ZP9o/ve3VTOmYBk58xC5mQEBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T10:22:32.815387Z"},"content_sha256":"71fde5619c664d584fa7a34067a4400db5ffb9ac1d8d5fc89c364d04968e380a","schema_version":"1.0","event_id":"sha256:71fde5619c664d584fa7a34067a4400db5ffb9ac1d8d5fc89c364d04968e380a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ETFQBEYVGIJ7EEYSUPRY76EZDK/bundle.json","state_url":"https://pith.science/pith/ETFQBEYVGIJ7EEYSUPRY76EZDK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ETFQBEYVGIJ7EEYSUPRY76EZDK/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":"2026-08-08T10:22:32Z","links":{"resolver":"https://pith.science/pith/ETFQBEYVGIJ7EEYSUPRY76EZDK","bundle":"https://pith.science/pith/ETFQBEYVGIJ7EEYSUPRY76EZDK/bundle.json","state":"https://pith.science/pith/ETFQBEYVGIJ7EEYSUPRY76EZDK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ETFQBEYVGIJ7EEYSUPRY76EZDK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ETFQBEYVGIJ7EEYSUPRY76EZDK","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":"8a65651fae63d216b5eb31b1fd1bdf68c5e29f8dfe822535ed3f86d914ce8c3d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-09T07:36:28Z","title_canon_sha256":"1c0a1a0d6086b130a0ed1ff849a16a5611d7dd679f476b82a162f9b162c8d318"},"schema_version":"1.0","source":{"id":"2507.06615","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.06615","created_at":"2026-07-05T11:34:19Z"},{"alias_kind":"arxiv_version","alias_value":"2507.06615v1","created_at":"2026-07-05T11:34:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06615","created_at":"2026-07-05T11:34:19Z"},{"alias_kind":"pith_short_12","alias_value":"ETFQBEYVGIJ7","created_at":"2026-07-05T11:34:19Z"},{"alias_kind":"pith_short_16","alias_value":"ETFQBEYVGIJ7EEYS","created_at":"2026-07-05T11:34:19Z"},{"alias_kind":"pith_short_8","alias_value":"ETFQBEYV","created_at":"2026-07-05T11:34:19Z"}],"graph_snapshots":[{"event_id":"sha256:71fde5619c664d584fa7a34067a4400db5ffb9ac1d8d5fc89c364d04968e380a","target":"graph","created_at":"2026-07-05T11:34:19Z","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/2507.06615/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-task reinforcement learning endeavors to efficiently leverage shared information across various tasks, facilitating the simultaneous learning of multiple tasks. Existing approaches primarily focus on parameter sharing with carefully designed network structures or tailored optimization procedures. However, they overlook a direct and complementary way to exploit cross-task similarities: the control policies of tasks already proficient in some skills can provide explicit guidance for unmastered tasks to accelerate skills acquisition. To this end, we present a novel framework called Cross-Ta","authors_text":"Haobo Fu, Jian Cheng, Jinmin He, Junliang Xing, Kai Li, Qiang Fu, Yifan Zang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-09T07:36:28Z","title":"Efficient Multi-Task Reinforcement Learning with Cross-Task Policy Guidance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06615","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:a787c4255b57de66b9c9e9e37cd78ecf2e50f2d248247abd0c0272720c5b9f6d","target":"record","created_at":"2026-07-05T11:34:19Z","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":"8a65651fae63d216b5eb31b1fd1bdf68c5e29f8dfe822535ed3f86d914ce8c3d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-09T07:36:28Z","title_canon_sha256":"1c0a1a0d6086b130a0ed1ff849a16a5611d7dd679f476b82a162f9b162c8d318"},"schema_version":"1.0","source":{"id":"2507.06615","kind":"arxiv","version":1}},"canonical_sha256":"24cb0093153213f21312a3e38ff8991abb96e5e4cf49ed3643fa1892e250cd6d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24cb0093153213f21312a3e38ff8991abb96e5e4cf49ed3643fa1892e250cd6d","first_computed_at":"2026-07-05T11:34:19.403845Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:34:19.403845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jW21w4PXJqqO3sUV3AN71I69ss4WUENLnKpygGVFoj/B6c7aYLfo2s3Vhadf/tJw0QsNcIICmv6xvTOwnpzcDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:34:19.404340Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.06615","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a787c4255b57de66b9c9e9e37cd78ecf2e50f2d248247abd0c0272720c5b9f6d","sha256:71fde5619c664d584fa7a34067a4400db5ffb9ac1d8d5fc89c364d04968e380a"],"state_sha256":"5813de2d4d6733232f57ec93571f6ebb21ea43f01424ea8b9375588babbd55c6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X6rc5wWRY9EZe+S7MpEMqsoQPnIvC4yrmTWSLNBihAcZskeC+EF1K6+KVW9PCulEvtg21g7Z/nu63Ki+vdwgBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T10:22:32.818806Z","bundle_sha256":"d3aff997b41c79516414249a9efd35e188e813057a1fc818ebc9d6be06023476"}}