{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Y6R5YAJGUGKOXMHNNROYLEOI3Q","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":"4f2eff9a0678b8f57d4584804b90d960cd317ba2f72b3a665f42742f2755c6e6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T04:30:37Z","title_canon_sha256":"dc59a7556dd44e2a2a3d2e442866753f1373051c94e546e2109b1114e9f99ad9"},"schema_version":"1.0","source":{"id":"2606.11652","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.11652","created_at":"2026-06-11T01:10:01Z"},{"alias_kind":"arxiv_version","alias_value":"2606.11652v1","created_at":"2026-06-11T01:10:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11652","created_at":"2026-06-11T01:10:01Z"},{"alias_kind":"pith_short_12","alias_value":"Y6R5YAJGUGKO","created_at":"2026-06-11T01:10:01Z"},{"alias_kind":"pith_short_16","alias_value":"Y6R5YAJGUGKOXMHN","created_at":"2026-06-11T01:10:01Z"},{"alias_kind":"pith_short_8","alias_value":"Y6R5YAJG","created_at":"2026-06-11T01:10:01Z"}],"graph_snapshots":[{"event_id":"sha256:2120507dcafc0c1a6d04b0de1e03fa069c008f680a995cdd76826d6f683d6139","target":"graph","created_at":"2026-06-11T01:10:01Z","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/2606.11652/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper investigates reinforcement learning (RL) methods for improving tool-calling capabilities in multimodal small language model (SLM) agents. While existing works have explored various reward designs to improve agentic tool-calling ability, these approaches face inherent limitations for SLM training, especially under multimodal scenarios. First, many existing methods evaluate tool use correctness through exact matching against certain ground-truth or predefined formats. However, this assumption is often unsuitable for multimodal tasks, where multiple tool use paths may be valid and anno","authors_text":"Jiayi Tian, Liyan Tan, Yifan Yang, Zheng Zhang, Zhen Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T04:30:37Z","title":"IAPO: Input Attribution-Aware Policy Optimization for Tool Use in Small Multimodal Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11652","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:ed78373e2662e83a8789b0c1d33050d4e521b29993ae401abac4fd94cfdcc6e9","target":"record","created_at":"2026-06-11T01:10:01Z","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":"4f2eff9a0678b8f57d4584804b90d960cd317ba2f72b3a665f42742f2755c6e6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T04:30:37Z","title_canon_sha256":"dc59a7556dd44e2a2a3d2e442866753f1373051c94e546e2109b1114e9f99ad9"},"schema_version":"1.0","source":{"id":"2606.11652","kind":"arxiv","version":1}},"canonical_sha256":"c7a3dc0126a194ebb0ed6c5d8591c8dc3823605f8095b5819ec447639d3d1abb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c7a3dc0126a194ebb0ed6c5d8591c8dc3823605f8095b5819ec447639d3d1abb","first_computed_at":"2026-06-11T01:10:01.090448Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T01:10:01.090448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JLvGjIouyPfUSwxRQsbsJ3wbQaHU+NBZmG1AdR+CdvLWIsXURZ0VgPaZf8xv9+ukK/lq7KeKQp1dRBL8XFNHBQ==","signature_status":"signed_v1","signed_at":"2026-06-11T01:10:01.091181Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.11652","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed78373e2662e83a8789b0c1d33050d4e521b29993ae401abac4fd94cfdcc6e9","sha256:2120507dcafc0c1a6d04b0de1e03fa069c008f680a995cdd76826d6f683d6139"],"state_sha256":"cd90b59dde6bc61bcc9f4f5e4183bc400f47e37f9b5b1fab657ba0f7c1d9bde1"}