{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:U6RNDZT5ZBNNJ2N6DNONU2CXEM","short_pith_number":"pith:U6RNDZT5","schema_version":"1.0","canonical_sha256":"a7a2d1e67dc85ad4e9be1b5cda6857233701937690eaa33c45f32cee435aefa9","source":{"kind":"arxiv","id":"2605.29697","version":1},"attestation_state":"computed","paper":{"title":"Beyond Trajectory Rewards: Step-level Credit Assignment for Agentic Search via Graph Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jianing Yu, Jiasi Chen, Lixiong Qin, Sheng Gao, Sheng Yang, Weiran Xu, Yingjie Feng, Yuchen Liu","submitted_at":"2026-05-28T09:57:12Z","abstract_excerpt":"In Agentic Search, trajectory-level outcome rewards fail to quantify the behavioral contributions of individual steps, while existing step-level reward methods typically rely on costly tree sampling. We view world knowledge as a latent world graph and each IS task as search within a latent task graph, where effective steps should make graph progress toward the answer node. Based on this prior, we propose Graph-Distance Contribution Reward (GDCR), a step-level process reward that scores newly-retrieved and newly-cited entities by their distance to the answer node in a training-time Entity-Relat"},"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":"2605.29697","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T09:57:12Z","cross_cats_sorted":[],"title_canon_sha256":"768071e2c8aff7edde7122404f19f1a62b5ca96f09a48b3a75cc5b03e4275bce","abstract_canon_sha256":"dd40f470c74954cb1c2404d760e5cdfaf2d002b7cd5c0aef34a33568e1be9a48"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:56.113364Z","signature_b64":"pFdzyLmUu0JA7oPOek2wlZTwVVNazarE2BTKMoKHeQ3soo6va/XMYsHMprrlaC23R/qLrPhM4+1cl1oSCbw/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7a2d1e67dc85ad4e9be1b5cda6857233701937690eaa33c45f32cee435aefa9","last_reissued_at":"2026-05-29T01:05:56.112838Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:56.112838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Trajectory Rewards: Step-level Credit Assignment for Agentic Search via Graph Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jianing Yu, Jiasi Chen, Lixiong Qin, Sheng Gao, Sheng Yang, Weiran Xu, Yingjie Feng, Yuchen Liu","submitted_at":"2026-05-28T09:57:12Z","abstract_excerpt":"In Agentic Search, trajectory-level outcome rewards fail to quantify the behavioral contributions of individual steps, while existing step-level reward methods typically rely on costly tree sampling. We view world knowledge as a latent world graph and each IS task as search within a latent task graph, where effective steps should make graph progress toward the answer node. Based on this prior, we propose Graph-Distance Contribution Reward (GDCR), a step-level process reward that scores newly-retrieved and newly-cited entities by their distance to the answer node in a training-time Entity-Relat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29697","kind":"arxiv","version":1},"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/2605.29697/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":"2605.29697","created_at":"2026-05-29T01:05:56.112912+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29697v1","created_at":"2026-05-29T01:05:56.112912+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29697","created_at":"2026-05-29T01:05:56.112912+00:00"},{"alias_kind":"pith_short_12","alias_value":"U6RNDZT5ZBNN","created_at":"2026-05-29T01:05:56.112912+00:00"},{"alias_kind":"pith_short_16","alias_value":"U6RNDZT5ZBNNJ2N6","created_at":"2026-05-29T01:05:56.112912+00:00"},{"alias_kind":"pith_short_8","alias_value":"U6RNDZT5","created_at":"2026-05-29T01:05:56.112912+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U6RNDZT5ZBNNJ2N6DNONU2CXEM","json":"https://pith.science/pith/U6RNDZT5ZBNNJ2N6DNONU2CXEM.json","graph_json":"https://pith.science/api/pith-number/U6RNDZT5ZBNNJ2N6DNONU2CXEM/graph.json","events_json":"https://pith.science/api/pith-number/U6RNDZT5ZBNNJ2N6DNONU2CXEM/events.json","paper":"https://pith.science/paper/U6RNDZT5"},"agent_actions":{"view_html":"https://pith.science/pith/U6RNDZT5ZBNNJ2N6DNONU2CXEM","download_json":"https://pith.science/pith/U6RNDZT5ZBNNJ2N6DNONU2CXEM.json","view_paper":"https://pith.science/paper/U6RNDZT5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29697&json=true","fetch_graph":"https://pith.science/api/pith-number/U6RNDZT5ZBNNJ2N6DNONU2CXEM/graph.json","fetch_events":"https://pith.science/api/pith-number/U6RNDZT5ZBNNJ2N6DNONU2CXEM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U6RNDZT5ZBNNJ2N6DNONU2CXEM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U6RNDZT5ZBNNJ2N6DNONU2CXEM/action/storage_attestation","attest_author":"https://pith.science/pith/U6RNDZT5ZBNNJ2N6DNONU2CXEM/action/author_attestation","sign_citation":"https://pith.science/pith/U6RNDZT5ZBNNJ2N6DNONU2CXEM/action/citation_signature","submit_replication":"https://pith.science/pith/U6RNDZT5ZBNNJ2N6DNONU2CXEM/action/replication_record"}},"created_at":"2026-05-29T01:05:56.112912+00:00","updated_at":"2026-05-29T01:05:56.112912+00:00"}