{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BUGAF7HSOMKARNPU3MRMMVED4U","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":"417c9f116a33bdf2b58e65a8e995e35d1513461bd541e8a4b9fc34d73cd8a86b","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-11-24T17:09:43Z","title_canon_sha256":"275e963954bdf57e971afd12360858e34d0ac4c7b53693bd5e538f47435a3741"},"schema_version":"1.0","source":{"id":"2511.19314","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.19314","created_at":"2026-06-11T00:08:11Z"},{"alias_kind":"arxiv_version","alias_value":"2511.19314v2","created_at":"2026-06-11T00:08:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.19314","created_at":"2026-06-11T00:08:11Z"},{"alias_kind":"pith_short_12","alias_value":"BUGAF7HSOMKA","created_at":"2026-06-11T00:08:11Z"},{"alias_kind":"pith_short_16","alias_value":"BUGAF7HSOMKARNPU","created_at":"2026-06-11T00:08:11Z"},{"alias_kind":"pith_short_8","alias_value":"BUGAF7HS","created_at":"2026-06-11T00:08:11Z"}],"graph_snapshots":[{"event_id":"sha256:8c59a1551c88f2f4f1f9d1ede2f34e65ff64558acfd675c9e1c9ca82a4d4582b","target":"graph","created_at":"2026-06-11T00:08:11Z","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/2511.19314/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Information-seeking is a core capability for AI agents, requiring them to gather and reason over tool-generated information across long trajectories. However, such multi-step information-seeking tasks remain challenging for agents backed by language models. While process reward models (PRMs) can guide agents by ranking candidate steps at test-time, existing PRMs - designed for short reasoning with binary judgment - cannot capture richer dimensions of information-seeking steps, such as tool interactions and reasoning over tool outputs, nor handle the rapidly growing context in long-horizon task","authors_text":"Archiki Prasad, Elias Stengel-Eskin, Jaewoo Lee, Justin Chih-Yao Chen, Mohit Bansal, Zaid Khan","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-11-24T17:09:43Z","title":"PRInTS: Reward Modeling for Long-Horizon Information Seeking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.19314","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":"sha256:5783966dde945217db091b0002f31360d0cd4abbbb62bfde40165bcc26dcbd9f","target":"record","created_at":"2026-06-11T00:08:11Z","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":"417c9f116a33bdf2b58e65a8e995e35d1513461bd541e8a4b9fc34d73cd8a86b","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-11-24T17:09:43Z","title_canon_sha256":"275e963954bdf57e971afd12360858e34d0ac4c7b53693bd5e538f47435a3741"},"schema_version":"1.0","source":{"id":"2511.19314","kind":"arxiv","version":2}},"canonical_sha256":"0d0c02fcf2731408b5f4db22c65483e52ef957464647cbd23e0cc7072d0ffa4c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d0c02fcf2731408b5f4db22c65483e52ef957464647cbd23e0cc7072d0ffa4c","first_computed_at":"2026-06-11T00:08:11.832880Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T00:08:11.832880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6GML3w8Y1c38eTOoqD7MsICtOZAWVvhIj3uZtWbPN7PjOjguJVsc91aeYsKDxREwkSdb7KhuTovvA9pH0zSrAA==","signature_status":"signed_v1","signed_at":"2026-06-11T00:08:11.834040Z","signed_message":"canonical_sha256_bytes"},"source_id":"2511.19314","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5783966dde945217db091b0002f31360d0cd4abbbb62bfde40165bcc26dcbd9f","sha256:8c59a1551c88f2f4f1f9d1ede2f34e65ff64558acfd675c9e1c9ca82a4d4582b"],"state_sha256":"e193adc42f6c0a74b659074b2d3b0316b247cfeaa2a3111c2730fe5a68dfdd32"}