{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3L4KJBNPCOBRO244YDL5AGTQB3","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":"51c2162cb4fa3b0309c8413aa404134c6fb6a585f1d8a5474f3249eb9652e5f3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-04T07:15:43Z","title_canon_sha256":"bce9c072befc312de843e855dc8ee0b7d4884c32219f361155070e1eb00d7ab2"},"schema_version":"1.0","source":{"id":"2606.05784","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05784","created_at":"2026-06-05T01:15:03Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05784v1","created_at":"2026-06-05T01:15:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05784","created_at":"2026-06-05T01:15:03Z"},{"alias_kind":"pith_short_12","alias_value":"3L4KJBNPCOBR","created_at":"2026-06-05T01:15:03Z"},{"alias_kind":"pith_short_16","alias_value":"3L4KJBNPCOBRO244","created_at":"2026-06-05T01:15:03Z"},{"alias_kind":"pith_short_8","alias_value":"3L4KJBNP","created_at":"2026-06-05T01:15:03Z"}],"graph_snapshots":[{"event_id":"sha256:72ac97c3f8e2bb4fbda362b160c05498064ec33f18b65a8f67f4a43bed3b6417","target":"graph","created_at":"2026-06-05T01:15:03Z","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/2606.05784/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We identify and formally characterize credit misassignment as a systematic failure mode of GRPO in tool-augmented multimodal search agents: its uniform broadcast of trajectory-level advantages to all tokens causes valuable tool-use steps in failing trajectories to be penalized no differently from valueless ones. We further empirically quantify the scale of this phenomenon. Over half of failing trajectories and failing tool-use actions exhibit correctable credit misassignment, demonstrating that the wasted training signal is both substantial and structurally exploitable. Building on this insigh","authors_text":"Chengqi Dong, Chuhuai Yue, Fenghe Tang, Guojun Yin, Hang He, Jiajun Chai, S Kevin Zhou, Xiaohan Wang, Yandong Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-04T07:15:43Z","title":"TAPO: Tool-Aware Policy Optimization via Credit Transfer for Multimodal Search Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05784","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":"sha256:41cd3d0534d32de480b51603c27b5e7d60a04907ead7d25044a835f93182678f","target":"record","created_at":"2026-06-05T01:15:03Z","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":"51c2162cb4fa3b0309c8413aa404134c6fb6a585f1d8a5474f3249eb9652e5f3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-04T07:15:43Z","title_canon_sha256":"bce9c072befc312de843e855dc8ee0b7d4884c32219f361155070e1eb00d7ab2"},"schema_version":"1.0","source":{"id":"2606.05784","kind":"arxiv","version":1}},"canonical_sha256":"daf8a485af1383176b9cc0d7d01a700ef64a8af0696cdc5d98fe937a3a1bf5ba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"daf8a485af1383176b9cc0d7d01a700ef64a8af0696cdc5d98fe937a3a1bf5ba","first_computed_at":"2026-06-05T01:15:03.107453Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:15:03.107453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1XDb2ZumfBzfTkXScoDaNJV8TSmRkPmO4u3LIRb45C6/kgkozLfJpzkp+igpO3B/9/sG3CU2Eib5LqRKruhbDg==","signature_status":"signed_v1","signed_at":"2026-06-05T01:15:03.107874Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05784","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41cd3d0534d32de480b51603c27b5e7d60a04907ead7d25044a835f93182678f","sha256:72ac97c3f8e2bb4fbda362b160c05498064ec33f18b65a8f67f4a43bed3b6417"],"state_sha256":"40b421b8b97fc606dd72f9b0b348324f7c8a6510c2049ea849402bb81946fc88"}