{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BULDWIQO3XR2LJRGSWPPQD64TW","short_pith_number":"pith:BULDWIQO","canonical_record":{"source":{"id":"2405.18080","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T11:41:41Z","cross_cats_sorted":[],"title_canon_sha256":"d9e56acc946044c2f56697331e274404354bc50c14302f9be7291f378f94c391","abstract_canon_sha256":"db30905d31ebf6f0cabb587b2ba802fee815857298341c812d04ebb6cac2c548"},"schema_version":"1.0"},"canonical_sha256":"0d163b220edde3a5a626959ef80fdc9da4e66eb36c28e26fcb82ea0d06e5c6cc","source":{"kind":"arxiv","id":"2405.18080","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.18080","created_at":"2026-07-05T08:24:15Z"},{"alias_kind":"arxiv_version","alias_value":"2405.18080v1","created_at":"2026-07-05T08:24:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18080","created_at":"2026-07-05T08:24:15Z"},{"alias_kind":"pith_short_12","alias_value":"BULDWIQO3XR2","created_at":"2026-07-05T08:24:15Z"},{"alias_kind":"pith_short_16","alias_value":"BULDWIQO3XR2LJRG","created_at":"2026-07-05T08:24:15Z"},{"alias_kind":"pith_short_8","alias_value":"BULDWIQO","created_at":"2026-07-05T08:24:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BULDWIQO3XR2LJRGSWPPQD64TW","target":"record","payload":{"canonical_record":{"source":{"id":"2405.18080","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T11:41:41Z","cross_cats_sorted":[],"title_canon_sha256":"d9e56acc946044c2f56697331e274404354bc50c14302f9be7291f378f94c391","abstract_canon_sha256":"db30905d31ebf6f0cabb587b2ba802fee815857298341c812d04ebb6cac2c548"},"schema_version":"1.0"},"canonical_sha256":"0d163b220edde3a5a626959ef80fdc9da4e66eb36c28e26fcb82ea0d06e5c6cc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:15.461774Z","signature_b64":"1SimcwxZ/UHYN6a9BTFQaGo+7ZSit9FB809nvZfM2P4Ii0CqZL0m5kifnkSwofztdfiOrRnMvdxsOmo5u/EaCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d163b220edde3a5a626959ef80fdc9da4e66eb36c28e26fcb82ea0d06e5c6cc","last_reissued_at":"2026-07-05T08:24:15.461297Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:15.461297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.18080","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":"2026-07-05T08:24:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hUH1bW2PWCblMI1TdFM6/4WOE3vABLgq/k+BCO68NRMSr/VI4imofUl795OZRZIDq370whAVhhs6FoFIAiZvBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:51:46.645231Z"},"content_sha256":"09e89751b89996bebb42f66fc910660da9e71aca42e6b1df01b65f8366df373e","schema_version":"1.0","event_id":"sha256:09e89751b89996bebb42f66fc910660da9e71aca42e6b1df01b65f8366df373e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BULDWIQO3XR2LJRGSWPPQD64TW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HarmoDT: Harmony Multi-Task Decision Transformer for Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dacheng Tao, Li Shen, Shengchao Hu, Yanfeng Wang, Ya Zhang, Ziqing Fan","submitted_at":"2024-05-28T11:41:41Z","abstract_excerpt":"The purpose of offline multi-task reinforcement learning (MTRL) is to develop a unified policy applicable to diverse tasks without the need for online environmental interaction. Recent advancements approach this through sequence modeling, leveraging the Transformer architecture's scalability and the benefits of parameter sharing to exploit task similarities. However, variations in task content and complexity pose significant challenges in policy formulation, necessitating judicious parameter sharing and management of conflicting gradients for optimal policy performance. In this work, we introd"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18080","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/2405.18080/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":"2026-07-05T08:24:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ph+FtDKquJJYoOYw6S4sv8u3aHnHT/R/Hb2/u281mqloJ0osqpOIPMOvv6gX1nGfKhwvi08raFNvgR25c6VhCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:51:46.645726Z"},"content_sha256":"97981143f074c1f1d2674de21cc5a6679d6a4162828f4f07225c153ab20c722b","schema_version":"1.0","event_id":"sha256:97981143f074c1f1d2674de21cc5a6679d6a4162828f4f07225c153ab20c722b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BULDWIQO3XR2LJRGSWPPQD64TW/bundle.json","state_url":"https://pith.science/pith/BULDWIQO3XR2LJRGSWPPQD64TW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BULDWIQO3XR2LJRGSWPPQD64TW/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":"2026-08-08T11:51:46Z","links":{"resolver":"https://pith.science/pith/BULDWIQO3XR2LJRGSWPPQD64TW","bundle":"https://pith.science/pith/BULDWIQO3XR2LJRGSWPPQD64TW/bundle.json","state":"https://pith.science/pith/BULDWIQO3XR2LJRGSWPPQD64TW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BULDWIQO3XR2LJRGSWPPQD64TW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BULDWIQO3XR2LJRGSWPPQD64TW","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":"db30905d31ebf6f0cabb587b2ba802fee815857298341c812d04ebb6cac2c548","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T11:41:41Z","title_canon_sha256":"d9e56acc946044c2f56697331e274404354bc50c14302f9be7291f378f94c391"},"schema_version":"1.0","source":{"id":"2405.18080","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.18080","created_at":"2026-07-05T08:24:15Z"},{"alias_kind":"arxiv_version","alias_value":"2405.18080v1","created_at":"2026-07-05T08:24:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18080","created_at":"2026-07-05T08:24:15Z"},{"alias_kind":"pith_short_12","alias_value":"BULDWIQO3XR2","created_at":"2026-07-05T08:24:15Z"},{"alias_kind":"pith_short_16","alias_value":"BULDWIQO3XR2LJRG","created_at":"2026-07-05T08:24:15Z"},{"alias_kind":"pith_short_8","alias_value":"BULDWIQO","created_at":"2026-07-05T08:24:15Z"}],"graph_snapshots":[{"event_id":"sha256:97981143f074c1f1d2674de21cc5a6679d6a4162828f4f07225c153ab20c722b","target":"graph","created_at":"2026-07-05T08:24:15Z","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/2405.18080/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The purpose of offline multi-task reinforcement learning (MTRL) is to develop a unified policy applicable to diverse tasks without the need for online environmental interaction. Recent advancements approach this through sequence modeling, leveraging the Transformer architecture's scalability and the benefits of parameter sharing to exploit task similarities. However, variations in task content and complexity pose significant challenges in policy formulation, necessitating judicious parameter sharing and management of conflicting gradients for optimal policy performance. In this work, we introd","authors_text":"Dacheng Tao, Li Shen, Shengchao Hu, Yanfeng Wang, Ya Zhang, Ziqing Fan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T11:41:41Z","title":"HarmoDT: Harmony Multi-Task Decision Transformer for Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18080","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":"sha256:09e89751b89996bebb42f66fc910660da9e71aca42e6b1df01b65f8366df373e","target":"record","created_at":"2026-07-05T08:24:15Z","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":"db30905d31ebf6f0cabb587b2ba802fee815857298341c812d04ebb6cac2c548","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T11:41:41Z","title_canon_sha256":"d9e56acc946044c2f56697331e274404354bc50c14302f9be7291f378f94c391"},"schema_version":"1.0","source":{"id":"2405.18080","kind":"arxiv","version":1}},"canonical_sha256":"0d163b220edde3a5a626959ef80fdc9da4e66eb36c28e26fcb82ea0d06e5c6cc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d163b220edde3a5a626959ef80fdc9da4e66eb36c28e26fcb82ea0d06e5c6cc","first_computed_at":"2026-07-05T08:24:15.461297Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:24:15.461297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1SimcwxZ/UHYN6a9BTFQaGo+7ZSit9FB809nvZfM2P4Ii0CqZL0m5kifnkSwofztdfiOrRnMvdxsOmo5u/EaCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:24:15.461774Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.18080","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09e89751b89996bebb42f66fc910660da9e71aca42e6b1df01b65f8366df373e","sha256:97981143f074c1f1d2674de21cc5a6679d6a4162828f4f07225c153ab20c722b"],"state_sha256":"6d7cd1514f073e94dea9795ffc595aee1607c625dc13a00bb38e7188a685f4a2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mcCZ9ONEqfpxmBdCBAfMBKk+kxsoVbDA0Cclz7y2Y9I2F8MmPRcn8hgaf48Tv890oUhCTdOs5TCBXI+kD9K9Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:51:46.648989Z","bundle_sha256":"a57c1deddeedcc20eff2ac5b1fe34fc325adf402580d7f488e735cb9dbf00c6b"}}