{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZCMT7GW5BDOK5Q63FTI4NMGATG","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":"fe15f98a87556bcc425d997dca362c7f7b837734165da3a753d414be7e51b8eb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-12T17:23:34Z","title_canon_sha256":"2a6c3dcfd1ce1ac75f768aa109db9618d58ca8349001ce39b6355e92950efd51"},"schema_version":"1.0","source":{"id":"2505.07773","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.07773","created_at":"2026-07-05T11:56:19Z"},{"alias_kind":"arxiv_version","alias_value":"2505.07773v4","created_at":"2026-07-05T11:56:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07773","created_at":"2026-07-05T11:56:19Z"},{"alias_kind":"pith_short_12","alias_value":"ZCMT7GW5BDOK","created_at":"2026-07-05T11:56:19Z"},{"alias_kind":"pith_short_16","alias_value":"ZCMT7GW5BDOK5Q63","created_at":"2026-07-05T11:56:19Z"},{"alias_kind":"pith_short_8","alias_value":"ZCMT7GW5","created_at":"2026-07-05T11:56:19Z"}],"graph_snapshots":[{"event_id":"sha256:1bb485ee98aca8bb00fee85a7021f9738d587ef6e0e605da6e878f0e4496ac40","target":"graph","created_at":"2026-07-05T11:56:19Z","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/2505.07773/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) often struggle with mathematical reasoning tasks requiring precise, verifiable computation. While Reinforcement Learning (RL) from outcome-based rewards enhances text-based reasoning, understanding how agents autonomously learn to leverage external tools like code execution remains crucial. We investigate RL from outcome-based rewards for Tool-Integrated Reasoning, ZeroTIR, training base LLMs to spontaneously generate and execute Python code for mathematical problems without supervised tool-use examples. Our central contribution is we demonstrate that as RL trainin","authors_text":"Haotian Xu, Jian Hu, Weinong Wang, Wenqiang Zhang, Xing W, Xinji Mai, Yingying Zhang, Zhong-Zhi Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-12T17:23:34Z","title":"Agent RL Scaling Law: Agent RL with Spontaneous Code Execution for Mathematical Problem Solving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07773","kind":"arxiv","version":4},"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":"sha256:58d39ebba14e503f360ef631d8a41ed7c7df613926474854cd69b74020226794","target":"record","created_at":"2026-07-05T11:56:19Z","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":"fe15f98a87556bcc425d997dca362c7f7b837734165da3a753d414be7e51b8eb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-12T17:23:34Z","title_canon_sha256":"2a6c3dcfd1ce1ac75f768aa109db9618d58ca8349001ce39b6355e92950efd51"},"schema_version":"1.0","source":{"id":"2505.07773","kind":"arxiv","version":4}},"canonical_sha256":"c8993f9add08dcaec3db2cd1c6b0c099b14ba68d11e92d0d8b997cd404f1695a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c8993f9add08dcaec3db2cd1c6b0c099b14ba68d11e92d0d8b997cd404f1695a","first_computed_at":"2026-07-05T11:56:19.555718Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:56:19.555718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Qs3JKQW2QzXev0Mmk2x9ipr7tEAHYXpZSOG+xJ2xeATIMzNWVroDWc3TGUK7gpj8D9LWP/X+s4rlYC1pl/tpAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:56:19.556205Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.07773","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:58d39ebba14e503f360ef631d8a41ed7c7df613926474854cd69b74020226794","sha256:1bb485ee98aca8bb00fee85a7021f9738d587ef6e0e605da6e878f0e4496ac40"],"state_sha256":"aced95a93eaeda55f74971efca71638fbf65f0fd33bc33aad903453f6bf26ce8"}