{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JV7MQWMUU62ANEFYQBRGFPETTJ","short_pith_number":"pith:JV7MQWMU","canonical_record":{"source":{"id":"2602.05547","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-05T11:06:37Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d06168a7770c6c93cd7f564637ffbb85c24d457a46e277f96e6c409dc9df6427","abstract_canon_sha256":"2409e1b19b4180fa51ae26ee86f0f8612b3986d000feebc5974b9c93f0107f3c"},"schema_version":"1.0"},"canonical_sha256":"4d7ec85994a7b40690b8806262bc939a45c946bc8b082d923270f767823394e9","source":{"kind":"arxiv","id":"2602.05547","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.05547","created_at":"2026-07-28T02:23:25Z"},{"alias_kind":"arxiv_version","alias_value":"2602.05547v2","created_at":"2026-07-28T02:23:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.05547","created_at":"2026-07-28T02:23:25Z"},{"alias_kind":"pith_short_12","alias_value":"JV7MQWMUU62A","created_at":"2026-07-28T02:23:25Z"},{"alias_kind":"pith_short_16","alias_value":"JV7MQWMUU62ANEFY","created_at":"2026-07-28T02:23:25Z"},{"alias_kind":"pith_short_8","alias_value":"JV7MQWMU","created_at":"2026-07-28T02:23:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JV7MQWMUU62ANEFYQBRGFPETTJ","target":"record","payload":{"canonical_record":{"source":{"id":"2602.05547","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-05T11:06:37Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d06168a7770c6c93cd7f564637ffbb85c24d457a46e277f96e6c409dc9df6427","abstract_canon_sha256":"2409e1b19b4180fa51ae26ee86f0f8612b3986d000feebc5974b9c93f0107f3c"},"schema_version":"1.0"},"canonical_sha256":"4d7ec85994a7b40690b8806262bc939a45c946bc8b082d923270f767823394e9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T02:23:25.403732Z","signature_b64":"AwxvlfQMq5JyZLxExBZeEBnpKr5/03HEUe53skqlqNM4EAjGUsf+SabbSRf8wp68bpTJ1CNfuNfuXkYv0CqwBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d7ec85994a7b40690b8806262bc939a45c946bc8b082d923270f767823394e9","last_reissued_at":"2026-07-28T02:23:25.402767Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T02:23:25.402767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.05547","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":"2026-07-28T02:23:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xC1oybDRAPwPOwTlWT1Tli4pMSCtbGUfPMEFqTX0oEiOq8RtwPdWbtHxC6EKPfAa4yo1avuEzzUVg428CJuvAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T01:11:48.356901Z"},"content_sha256":"9134464bb1e49b8fa1ffc84b181d3a4a92a55b11fec4bc35f9172c8337382277","schema_version":"1.0","event_id":"sha256:9134464bb1e49b8fa1ffc84b181d3a4a92a55b11fec4bc35f9172c8337382277"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JV7MQWMUU62ANEFYQBRGFPETTJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Task GRPO: Reliable LLM Reasoning Across Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aurelien Lucchi, Haitham Bou Ammar, Ilija Bogunovic, Matthieu Zimmer, Sangwoong Yoon, Shyam Sundhar Ramesh, Xiaotong Ji, Zhiyong Wang","submitted_at":"2026-02-05T11:06:37Z","abstract_excerpt":"RL-based post-training with GRPO is widely used to improve large language models on individual reasoning tasks. However, real-world deployment requires reliable performance across diverse tasks. A straightforward multi-task adaptation of GRPO often leads to imbalanced outcomes, with some tasks dominating optimization while others stagnate. Moreover, tasks can vary widely in how frequently prompts yield zero advantages (and thus zero gradients), which further distorts their effective contribution to the optimization signal. To address these issues, we propose a novel Multi-Task GRPO (MT-GRPO) a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.05547","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/2602.05547/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":"2026-07-28T02:23:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MhywFpK4fpz0vkBWC/cGH9T0II3xRrtm84NnTcrcoUkml47PpIB0pOAXLU2vjYdunCCeTmYSyizKT8w08qQ0BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T01:11:48.358934Z"},"content_sha256":"6e487c5930efb555b6bc581c61ca9b141317d34d455f78a78b8eed3cb0154380","schema_version":"1.0","event_id":"sha256:6e487c5930efb555b6bc581c61ca9b141317d34d455f78a78b8eed3cb0154380"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JV7MQWMUU62ANEFYQBRGFPETTJ/bundle.json","state_url":"https://pith.science/pith/JV7MQWMUU62ANEFYQBRGFPETTJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JV7MQWMUU62ANEFYQBRGFPETTJ/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":"2026-08-11T01:11:48Z","links":{"resolver":"https://pith.science/pith/JV7MQWMUU62ANEFYQBRGFPETTJ","bundle":"https://pith.science/pith/JV7MQWMUU62ANEFYQBRGFPETTJ/bundle.json","state":"https://pith.science/pith/JV7MQWMUU62ANEFYQBRGFPETTJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JV7MQWMUU62ANEFYQBRGFPETTJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JV7MQWMUU62ANEFYQBRGFPETTJ","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":"2409e1b19b4180fa51ae26ee86f0f8612b3986d000feebc5974b9c93f0107f3c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-05T11:06:37Z","title_canon_sha256":"d06168a7770c6c93cd7f564637ffbb85c24d457a46e277f96e6c409dc9df6427"},"schema_version":"1.0","source":{"id":"2602.05547","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.05547","created_at":"2026-07-28T02:23:25Z"},{"alias_kind":"arxiv_version","alias_value":"2602.05547v2","created_at":"2026-07-28T02:23:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.05547","created_at":"2026-07-28T02:23:25Z"},{"alias_kind":"pith_short_12","alias_value":"JV7MQWMUU62A","created_at":"2026-07-28T02:23:25Z"},{"alias_kind":"pith_short_16","alias_value":"JV7MQWMUU62ANEFY","created_at":"2026-07-28T02:23:25Z"},{"alias_kind":"pith_short_8","alias_value":"JV7MQWMU","created_at":"2026-07-28T02:23:25Z"}],"graph_snapshots":[{"event_id":"sha256:6e487c5930efb555b6bc581c61ca9b141317d34d455f78a78b8eed3cb0154380","target":"graph","created_at":"2026-07-28T02:23:25Z","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/2602.05547/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"RL-based post-training with GRPO is widely used to improve large language models on individual reasoning tasks. However, real-world deployment requires reliable performance across diverse tasks. A straightforward multi-task adaptation of GRPO often leads to imbalanced outcomes, with some tasks dominating optimization while others stagnate. Moreover, tasks can vary widely in how frequently prompts yield zero advantages (and thus zero gradients), which further distorts their effective contribution to the optimization signal. To address these issues, we propose a novel Multi-Task GRPO (MT-GRPO) a","authors_text":"Aurelien Lucchi, Haitham Bou Ammar, Ilija Bogunovic, Matthieu Zimmer, Sangwoong Yoon, Shyam Sundhar Ramesh, Xiaotong Ji, Zhiyong Wang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-05T11:06:37Z","title":"Multi-Task GRPO: Reliable LLM Reasoning Across Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.05547","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":"sha256:9134464bb1e49b8fa1ffc84b181d3a4a92a55b11fec4bc35f9172c8337382277","target":"record","created_at":"2026-07-28T02:23:25Z","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":"2409e1b19b4180fa51ae26ee86f0f8612b3986d000feebc5974b9c93f0107f3c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-05T11:06:37Z","title_canon_sha256":"d06168a7770c6c93cd7f564637ffbb85c24d457a46e277f96e6c409dc9df6427"},"schema_version":"1.0","source":{"id":"2602.05547","kind":"arxiv","version":2}},"canonical_sha256":"4d7ec85994a7b40690b8806262bc939a45c946bc8b082d923270f767823394e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d7ec85994a7b40690b8806262bc939a45c946bc8b082d923270f767823394e9","first_computed_at":"2026-07-28T02:23:25.402767Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T02:23:25.402767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AwxvlfQMq5JyZLxExBZeEBnpKr5/03HEUe53skqlqNM4EAjGUsf+SabbSRf8wp68bpTJ1CNfuNfuXkYv0CqwBQ==","signature_status":"signed_v1","signed_at":"2026-07-28T02:23:25.403732Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.05547","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9134464bb1e49b8fa1ffc84b181d3a4a92a55b11fec4bc35f9172c8337382277","sha256:6e487c5930efb555b6bc581c61ca9b141317d34d455f78a78b8eed3cb0154380"],"state_sha256":"63690ed61b553bca8205b0f46a0ae9f753376cf860bfca777917c5df6201bcd4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DDKET9ANMUBWeFfwerf0aXceTU46vbAqc03l3bfxXwaU0ofHCau0DSALimxI1Y+C+p9weDETjXmmSZekLal2Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T01:11:48.395150Z","bundle_sha256":"3788ffdf07f2b604af178c7c919a9d67eb007982c50fa9da8a3c6648fc593459"}}