{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BUGAF7HSOMKARNPU3MRMMVED4U","short_pith_number":"pith:BUGAF7HS","schema_version":"1.0","canonical_sha256":"0d0c02fcf2731408b5f4db22c65483e52ef957464647cbd23e0cc7072d0ffa4c","source":{"kind":"arxiv","id":"2511.19314","version":2},"attestation_state":"computed","paper":{"title":"PRInTS: Reward Modeling for Long-Horizon Information Seeking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Archiki Prasad, Elias Stengel-Eskin, Jaewoo Lee, Justin Chih-Yao Chen, Mohit Bansal, Zaid Khan","submitted_at":"2025-11-24T17:09:43Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2511.19314","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-11-24T17:09:43Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"275e963954bdf57e971afd12360858e34d0ac4c7b53693bd5e538f47435a3741","abstract_canon_sha256":"417c9f116a33bdf2b58e65a8e995e35d1513461bd541e8a4b9fc34d73cd8a86b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T00:08:11.834040Z","signature_b64":"6GML3w8Y1c38eTOoqD7MsICtOZAWVvhIj3uZtWbPN7PjOjguJVsc91aeYsKDxREwkSdb7KhuTovvA9pH0zSrAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d0c02fcf2731408b5f4db22c65483e52ef957464647cbd23e0cc7072d0ffa4c","last_reissued_at":"2026-06-11T00:08:11.832880Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T00:08:11.832880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PRInTS: Reward Modeling for Long-Horizon Information Seeking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Archiki Prasad, Elias Stengel-Eskin, Jaewoo Lee, Justin Chih-Yao Chen, Mohit Bansal, Zaid Khan","submitted_at":"2025-11-24T17:09:43Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.19314","kind":"arxiv","version":2},"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/2511.19314/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2511.19314","created_at":"2026-06-11T00:08:11.833027+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.19314v2","created_at":"2026-06-11T00:08:11.833027+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.19314","created_at":"2026-06-11T00:08:11.833027+00:00"},{"alias_kind":"pith_short_12","alias_value":"BUGAF7HSOMKA","created_at":"2026-06-11T00:08:11.833027+00:00"},{"alias_kind":"pith_short_16","alias_value":"BUGAF7HSOMKARNPU","created_at":"2026-06-11T00:08:11.833027+00:00"},{"alias_kind":"pith_short_8","alias_value":"BUGAF7HS","created_at":"2026-06-11T00:08:11.833027+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.02572","citing_title":"On Training Large Language Models for Long-Horizon Tasks: An Empirical Study of Horizon Length","ref_index":59,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BUGAF7HSOMKARNPU3MRMMVED4U","json":"https://pith.science/pith/BUGAF7HSOMKARNPU3MRMMVED4U.json","graph_json":"https://pith.science/api/pith-number/BUGAF7HSOMKARNPU3MRMMVED4U/graph.json","events_json":"https://pith.science/api/pith-number/BUGAF7HSOMKARNPU3MRMMVED4U/events.json","paper":"https://pith.science/paper/BUGAF7HS"},"agent_actions":{"view_html":"https://pith.science/pith/BUGAF7HSOMKARNPU3MRMMVED4U","download_json":"https://pith.science/pith/BUGAF7HSOMKARNPU3MRMMVED4U.json","view_paper":"https://pith.science/paper/BUGAF7HS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.19314&json=true","fetch_graph":"https://pith.science/api/pith-number/BUGAF7HSOMKARNPU3MRMMVED4U/graph.json","fetch_events":"https://pith.science/api/pith-number/BUGAF7HSOMKARNPU3MRMMVED4U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BUGAF7HSOMKARNPU3MRMMVED4U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BUGAF7HSOMKARNPU3MRMMVED4U/action/storage_attestation","attest_author":"https://pith.science/pith/BUGAF7HSOMKARNPU3MRMMVED4U/action/author_attestation","sign_citation":"https://pith.science/pith/BUGAF7HSOMKARNPU3MRMMVED4U/action/citation_signature","submit_replication":"https://pith.science/pith/BUGAF7HSOMKARNPU3MRMMVED4U/action/replication_record"}},"created_at":"2026-06-11T00:08:11.833027+00:00","updated_at":"2026-06-11T00:08:11.833027+00:00"}