{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HV6AVDMXVUOZGG5UFDBBPRQEXZ","short_pith_number":"pith:HV6AVDMX","schema_version":"1.0","canonical_sha256":"3d7c0a8d97ad1d931bb428c217c604be7749e47426955d1835631084ddfe155b","source":{"kind":"arxiv","id":"2606.00593","version":1},"attestation_state":"computed","paper":{"title":"SPADER: Step-wise Peer Advantage with Diversity-Aware Exploration Rewards for Multi-Answer Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Di Weng, Qiming Shi, Yingcai Wu, Yunfan Zhou, Zhaolu Kang","submitted_at":"2026-05-30T07:47:42Z","abstract_excerpt":"Large language models are increasingly deployed as tool-augmented agents to acquire information beyond parametric knowledge. While recent work has improved long-horizon tool-use reasoning, most approaches focus on tasks with a single correct answer. In contrast, many real-world queries require discovering a comprehensive set of valid answers, a setting known as Multi-Answer QA. This setting raises two challenges: fine-grained credit assignment over long search trajectories and reward alignment for sustained exploration beyond easy high-frequency entities. We propose SPADER, a reinforcement lea"},"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":"2606.00593","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-30T07:47:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d576f7eb58f6d9ca5268551f94f11f7710de925bc8d71bfad38d6b8b4629fb2e","abstract_canon_sha256":"a4e6abd48a8aefabafc34abf234a6a71ce79e98cff1b95cfe0e12be41d383109"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:59.124498Z","signature_b64":"L1jy7NiCPkvjZswGdIzn39lf0rc1dTvSAbuIlXoGGtvb+4gjS4LvxK61yWeZCj41uhy1ktW64M7VsGhw2/2+Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d7c0a8d97ad1d931bb428c217c604be7749e47426955d1835631084ddfe155b","last_reissued_at":"2026-06-02T01:03:59.124088Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:59.124088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPADER: Step-wise Peer Advantage with Diversity-Aware Exploration Rewards for Multi-Answer Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Di Weng, Qiming Shi, Yingcai Wu, Yunfan Zhou, Zhaolu Kang","submitted_at":"2026-05-30T07:47:42Z","abstract_excerpt":"Large language models are increasingly deployed as tool-augmented agents to acquire information beyond parametric knowledge. While recent work has improved long-horizon tool-use reasoning, most approaches focus on tasks with a single correct answer. In contrast, many real-world queries require discovering a comprehensive set of valid answers, a setting known as Multi-Answer QA. This setting raises two challenges: fine-grained credit assignment over long search trajectories and reward alignment for sustained exploration beyond easy high-frequency entities. We propose SPADER, a reinforcement lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00593","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/2606.00593/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":"2606.00593","created_at":"2026-06-02T01:03:59.124148+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.00593v1","created_at":"2026-06-02T01:03:59.124148+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00593","created_at":"2026-06-02T01:03:59.124148+00:00"},{"alias_kind":"pith_short_12","alias_value":"HV6AVDMXVUOZ","created_at":"2026-06-02T01:03:59.124148+00:00"},{"alias_kind":"pith_short_16","alias_value":"HV6AVDMXVUOZGG5U","created_at":"2026-06-02T01:03:59.124148+00:00"},{"alias_kind":"pith_short_8","alias_value":"HV6AVDMX","created_at":"2026-06-02T01:03:59.124148+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/HV6AVDMXVUOZGG5UFDBBPRQEXZ","json":"https://pith.science/pith/HV6AVDMXVUOZGG5UFDBBPRQEXZ.json","graph_json":"https://pith.science/api/pith-number/HV6AVDMXVUOZGG5UFDBBPRQEXZ/graph.json","events_json":"https://pith.science/api/pith-number/HV6AVDMXVUOZGG5UFDBBPRQEXZ/events.json","paper":"https://pith.science/paper/HV6AVDMX"},"agent_actions":{"view_html":"https://pith.science/pith/HV6AVDMXVUOZGG5UFDBBPRQEXZ","download_json":"https://pith.science/pith/HV6AVDMXVUOZGG5UFDBBPRQEXZ.json","view_paper":"https://pith.science/paper/HV6AVDMX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.00593&json=true","fetch_graph":"https://pith.science/api/pith-number/HV6AVDMXVUOZGG5UFDBBPRQEXZ/graph.json","fetch_events":"https://pith.science/api/pith-number/HV6AVDMXVUOZGG5UFDBBPRQEXZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HV6AVDMXVUOZGG5UFDBBPRQEXZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HV6AVDMXVUOZGG5UFDBBPRQEXZ/action/storage_attestation","attest_author":"https://pith.science/pith/HV6AVDMXVUOZGG5UFDBBPRQEXZ/action/author_attestation","sign_citation":"https://pith.science/pith/HV6AVDMXVUOZGG5UFDBBPRQEXZ/action/citation_signature","submit_replication":"https://pith.science/pith/HV6AVDMXVUOZGG5UFDBBPRQEXZ/action/replication_record"}},"created_at":"2026-06-02T01:03:59.124148+00:00","updated_at":"2026-06-02T01:03:59.124148+00:00"}