{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QAI6DK6LNVGOMZMYBKZS6LQEL7","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":"8da6cbd440fa57e9dffd1acf29dc3624fc175c9303eb8d7f24126b576eb1abd4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-05T17:41:31Z","title_canon_sha256":"d83d5cf5cae9647d887f19e606cf9dd50ef4dbb9749a8f63c54c5b5da0d426a8"},"schema_version":"1.0","source":{"id":"2608.05102","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.05102","created_at":"2026-08-06T01:49:12Z"},{"alias_kind":"arxiv_version","alias_value":"2608.05102v1","created_at":"2026-08-06T01:49:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05102","created_at":"2026-08-06T01:49:12Z"},{"alias_kind":"pith_short_12","alias_value":"QAI6DK6LNVGO","created_at":"2026-08-06T01:49:12Z"},{"alias_kind":"pith_short_16","alias_value":"QAI6DK6LNVGOMZMY","created_at":"2026-08-06T01:49:12Z"},{"alias_kind":"pith_short_8","alias_value":"QAI6DK6L","created_at":"2026-08-06T01:49:12Z"}],"graph_snapshots":[{"event_id":"sha256:b7b7f802c861d43f9548720c9b8295f10e7069a6f2327aed1c9c090243de3024","target":"graph","created_at":"2026-08-06T01:49:12Z","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/2608.05102/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Long-horizon search agents must make multiple sequential actions (steps) to search, retrieve, verify, and integrate evidence to reach a final answer. However, existing methods for training these agents typically treat all steps within a trajectory uniformly during both supervised fine-tuning (SFT) and reinforcement learning (RL), failing to distinguish useful actions from erroneous or redundant ones. In this paper, we propose Answer-Backtracked Credit Assignment (ABC), a fine-grained credit assignment framework for training long-horizon search agents by converting sparse trajectory-level outco","authors_text":"Jiajun Wang, Rui Ye, Siheng Chen, Songhua Liu, Tian Jin, Yijun Lu, Yuwen Du","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-05T17:41:31Z","title":"ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05102","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":"sha256:979dbb11dfd1ea265c0a66ae1e8d2f1a597432b1f07089e8f82d10ff931f4a63","target":"record","created_at":"2026-08-06T01:49:12Z","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":"8da6cbd440fa57e9dffd1acf29dc3624fc175c9303eb8d7f24126b576eb1abd4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-05T17:41:31Z","title_canon_sha256":"d83d5cf5cae9647d887f19e606cf9dd50ef4dbb9749a8f63c54c5b5da0d426a8"},"schema_version":"1.0","source":{"id":"2608.05102","kind":"arxiv","version":1}},"canonical_sha256":"8011e1abcb6d4ce665980ab32f2e045ff1930d10e01f16691d7e23563ed33807","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8011e1abcb6d4ce665980ab32f2e045ff1930d10e01f16691d7e23563ed33807","first_computed_at":"2026-08-06T01:49:12.090737Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-06T01:49:12.090737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7J6NubRHbSErE85tih+RYZlQd66oTEptCuyc+Wv7hwcLU9OQQ9vCl4Te706lSlla4YIEWoE4d7u+WSA0YoXiBg==","signature_status":"signed_v1","signed_at":"2026-08-06T01:49:12.092189Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.05102","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:979dbb11dfd1ea265c0a66ae1e8d2f1a597432b1f07089e8f82d10ff931f4a63","sha256:b7b7f802c861d43f9548720c9b8295f10e7069a6f2327aed1c9c090243de3024"],"state_sha256":"677c55f9a0b995b35f1123ccfd6ab8c3235720f3ae7d51e65d80bb833dbfea74"}