{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:77XBYIICMBP5HT6BR4SCTQJOXZ","short_pith_number":"pith:77XBYIIC","canonical_record":{"source":{"id":"2607.07178","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-08T09:13:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3fd1413e9122e35967252e7214ce5f7e67be70612bad3f99e6c5ff3a280e7e33","abstract_canon_sha256":"120f39f4293054ad460ff346b25a1093e5ce6e705021546630e2e17fa0635314"},"schema_version":"1.0"},"canonical_sha256":"ffee1c2102605fd3cfc18f2429c12ebe58ba0f92047d0a08fa83f05f3384da4f","source":{"kind":"arxiv","id":"2607.07178","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.07178","created_at":"2026-07-09T01:20:16Z"},{"alias_kind":"arxiv_version","alias_value":"2607.07178v1","created_at":"2026-07-09T01:20:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.07178","created_at":"2026-07-09T01:20:16Z"},{"alias_kind":"pith_short_12","alias_value":"77XBYIICMBP5","created_at":"2026-07-09T01:20:16Z"},{"alias_kind":"pith_short_16","alias_value":"77XBYIICMBP5HT6B","created_at":"2026-07-09T01:20:16Z"},{"alias_kind":"pith_short_8","alias_value":"77XBYIIC","created_at":"2026-07-09T01:20:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:77XBYIICMBP5HT6BR4SCTQJOXZ","target":"record","payload":{"canonical_record":{"source":{"id":"2607.07178","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-08T09:13:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3fd1413e9122e35967252e7214ce5f7e67be70612bad3f99e6c5ff3a280e7e33","abstract_canon_sha256":"120f39f4293054ad460ff346b25a1093e5ce6e705021546630e2e17fa0635314"},"schema_version":"1.0"},"canonical_sha256":"ffee1c2102605fd3cfc18f2429c12ebe58ba0f92047d0a08fa83f05f3384da4f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-09T01:20:16.623866Z","signature_b64":"dN8jn3GTSNcJCt5VY+06cl9pRSt7ksbd8vPVUjbWTbhedmzw3QpiBPoEEpEtFRvSCbhj7FvK/V7DuBuiReamDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ffee1c2102605fd3cfc18f2429c12ebe58ba0f92047d0a08fa83f05f3384da4f","last_reissued_at":"2026-07-09T01:20:16.623454Z","signature_status":"signed_v1","first_computed_at":"2026-07-09T01:20:16.623454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.07178","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":"2026-07-09T01:20:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LQIfuED8xXqtNHv1+Lo79o127cdySnPhmIyljl8eXfbEci/pu7h9d3hpYyd+GHD66aLm5diGdU/YVuADfoSBAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T06:41:54.464639Z"},"content_sha256":"88b384b1c0365d5cf7d55f82e06e362bd8745e20beccbe8c67467e335380bb1f","schema_version":"1.0","event_id":"sha256:88b384b1c0365d5cf7d55f82e06e362bd8745e20beccbe8c67467e335380bb1f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:77XBYIICMBP5HT6BR4SCTQJOXZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Entropy Pacing Policy Optimization for Multi-Task Agentic Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dacheng Tao, Junjie Zhang, Shunyu Liu, Ting-En Lin, Yongbin Li, Yongcheng Jing, Zetian Hu","submitted_at":"2026-07-08T09:13:05Z","abstract_excerpt":"Recent breakthroughs of Reinforcement Learning (RL) have highlighted its potential for complex agentic Large Language Model (LLM) tasks. However, existing efforts largely focus on single-task settings, whereas real-world deployment necessitates a generalist agent capable of solving multiple tasks simultaneously. In this work, we identify a critical yet underexplored phenomenon in multi-task agentic RL: different tasks can exhibit exploration-exploitation pace mismatch. Specifically, easier tasks may converge early to low-entropy policies that hinder learning on harder tasks, while harder tasks"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.07178","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/2607.07178/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":"2026-07-09T01:20:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OS/d/5iE6+A2Z/5kdY+FCNgCCud+st4FQ7muDK65jWv9RMFxbk/bFZGX5DXlYi1OncDlokXHuQo0Ff3/8JnWBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T06:41:54.465301Z"},"content_sha256":"9e260d85dfce3dd5000486f69b33558be83ff5cb031a089cba9c54e7ad6be43a","schema_version":"1.0","event_id":"sha256:9e260d85dfce3dd5000486f69b33558be83ff5cb031a089cba9c54e7ad6be43a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/77XBYIICMBP5HT6BR4SCTQJOXZ/bundle.json","state_url":"https://pith.science/pith/77XBYIICMBP5HT6BR4SCTQJOXZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/77XBYIICMBP5HT6BR4SCTQJOXZ/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":"2026-07-11T06:41:54Z","links":{"resolver":"https://pith.science/pith/77XBYIICMBP5HT6BR4SCTQJOXZ","bundle":"https://pith.science/pith/77XBYIICMBP5HT6BR4SCTQJOXZ/bundle.json","state":"https://pith.science/pith/77XBYIICMBP5HT6BR4SCTQJOXZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/77XBYIICMBP5HT6BR4SCTQJOXZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:77XBYIICMBP5HT6BR4SCTQJOXZ","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":"120f39f4293054ad460ff346b25a1093e5ce6e705021546630e2e17fa0635314","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-08T09:13:05Z","title_canon_sha256":"3fd1413e9122e35967252e7214ce5f7e67be70612bad3f99e6c5ff3a280e7e33"},"schema_version":"1.0","source":{"id":"2607.07178","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.07178","created_at":"2026-07-09T01:20:16Z"},{"alias_kind":"arxiv_version","alias_value":"2607.07178v1","created_at":"2026-07-09T01:20:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.07178","created_at":"2026-07-09T01:20:16Z"},{"alias_kind":"pith_short_12","alias_value":"77XBYIICMBP5","created_at":"2026-07-09T01:20:16Z"},{"alias_kind":"pith_short_16","alias_value":"77XBYIICMBP5HT6B","created_at":"2026-07-09T01:20:16Z"},{"alias_kind":"pith_short_8","alias_value":"77XBYIIC","created_at":"2026-07-09T01:20:16Z"}],"graph_snapshots":[{"event_id":"sha256:9e260d85dfce3dd5000486f69b33558be83ff5cb031a089cba9c54e7ad6be43a","target":"graph","created_at":"2026-07-09T01:20:16Z","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/2607.07178/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent breakthroughs of Reinforcement Learning (RL) have highlighted its potential for complex agentic Large Language Model (LLM) tasks. However, existing efforts largely focus on single-task settings, whereas real-world deployment necessitates a generalist agent capable of solving multiple tasks simultaneously. In this work, we identify a critical yet underexplored phenomenon in multi-task agentic RL: different tasks can exhibit exploration-exploitation pace mismatch. Specifically, easier tasks may converge early to low-entropy policies that hinder learning on harder tasks, while harder tasks","authors_text":"Dacheng Tao, Junjie Zhang, Shunyu Liu, Ting-En Lin, Yongbin Li, Yongcheng Jing, Zetian Hu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-08T09:13:05Z","title":"Entropy Pacing Policy Optimization for Multi-Task Agentic Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.07178","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":"sha256:88b384b1c0365d5cf7d55f82e06e362bd8745e20beccbe8c67467e335380bb1f","target":"record","created_at":"2026-07-09T01:20:16Z","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":"120f39f4293054ad460ff346b25a1093e5ce6e705021546630e2e17fa0635314","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-08T09:13:05Z","title_canon_sha256":"3fd1413e9122e35967252e7214ce5f7e67be70612bad3f99e6c5ff3a280e7e33"},"schema_version":"1.0","source":{"id":"2607.07178","kind":"arxiv","version":1}},"canonical_sha256":"ffee1c2102605fd3cfc18f2429c12ebe58ba0f92047d0a08fa83f05f3384da4f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ffee1c2102605fd3cfc18f2429c12ebe58ba0f92047d0a08fa83f05f3384da4f","first_computed_at":"2026-07-09T01:20:16.623454Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-09T01:20:16.623454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dN8jn3GTSNcJCt5VY+06cl9pRSt7ksbd8vPVUjbWTbhedmzw3QpiBPoEEpEtFRvSCbhj7FvK/V7DuBuiReamDQ==","signature_status":"signed_v1","signed_at":"2026-07-09T01:20:16.623866Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.07178","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:88b384b1c0365d5cf7d55f82e06e362bd8745e20beccbe8c67467e335380bb1f","sha256:9e260d85dfce3dd5000486f69b33558be83ff5cb031a089cba9c54e7ad6be43a"],"state_sha256":"6f3a55f0ab212f6f906fd25584ce020a66cd6204ae8d65d81fc5230dd4e1d12e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EELdoXFoMne6091Wc8jDOJG+KcZOLP9gUHUzwfoOz/RtROhuTF9d4VS8s6Pmd8FNynU8h9fADscFhl95fD0uCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-11T06:41:54.468958Z","bundle_sha256":"313f80b9c79fc1aeee84f7259e0596ad8abf19ef0fdc1e7d36ac888372c13e2e"}}