{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5VPLR6JJUSLXHZRRSDM24A6NF2","short_pith_number":"pith:5VPLR6JJ","schema_version":"1.0","canonical_sha256":"ed5eb8f929a49773e63190d9ae03cd2ea12ad2778cb655245385084830cbe8de","source":{"kind":"arxiv","id":"2606.02204","version":1},"attestation_state":"computed","paper":{"title":"Cross-Environment Neural Reranking for Sample-Efficient Action Selection in Text-Based Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kan Shao","submitted_at":"2026-06-01T13:00:58Z","abstract_excerpt":"Large language model agents achieve strong performance on text-based benchmarks but incur prohibitive inference costs, motivating the use of compact neural rerankers for action selection. We investigate whether a single lightweight model can perform action selection across multiple diverse environments, a capability that would eliminate per-environment model maintenance. Training DeBERTa-v3 (184M-434M parameters) jointly on ALFWorld, WebShop, and ScienceWorld with minority-class upsampling, we find that rebalanced two-environment joint training substantially improves over single-environment AL"},"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":"2606.02204","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-01T13:00:58Z","cross_cats_sorted":[],"title_canon_sha256":"bd2c91260d1ef10fbee0773a3d89a74b2430c4db83b75df1b5d6e3a494a062f8","abstract_canon_sha256":"59bbe74a930a671fa3fab001a0eac5882520d15806de261033bd51f8e98052c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T03:04:53.059549Z","signature_b64":"N8T1zSUjO3yZqwSVeCLNxkO8ytJw20XxWkhxmwEYpSErOAX0UyVj/FDEUEpAOigX4QXynFh0V3k7I8okJrfRBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed5eb8f929a49773e63190d9ae03cd2ea12ad2778cb655245385084830cbe8de","last_reissued_at":"2026-06-02T03:04:53.059116Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T03:04:53.059116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-Environment Neural Reranking for Sample-Efficient Action Selection in Text-Based Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kan Shao","submitted_at":"2026-06-01T13:00:58Z","abstract_excerpt":"Large language model agents achieve strong performance on text-based benchmarks but incur prohibitive inference costs, motivating the use of compact neural rerankers for action selection. We investigate whether a single lightweight model can perform action selection across multiple diverse environments, a capability that would eliminate per-environment model maintenance. Training DeBERTa-v3 (184M-434M parameters) jointly on ALFWorld, WebShop, and ScienceWorld with minority-class upsampling, we find that rebalanced two-environment joint training substantially improves over single-environment AL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02204","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/2606.02204/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":"2606.02204","created_at":"2026-06-02T03:04:53.059175+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.02204v1","created_at":"2026-06-02T03:04:53.059175+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02204","created_at":"2026-06-02T03:04:53.059175+00:00"},{"alias_kind":"pith_short_12","alias_value":"5VPLR6JJUSLX","created_at":"2026-06-02T03:04:53.059175+00:00"},{"alias_kind":"pith_short_16","alias_value":"5VPLR6JJUSLXHZRR","created_at":"2026-06-02T03:04:53.059175+00:00"},{"alias_kind":"pith_short_8","alias_value":"5VPLR6JJ","created_at":"2026-06-02T03:04:53.059175+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/5VPLR6JJUSLXHZRRSDM24A6NF2","json":"https://pith.science/pith/5VPLR6JJUSLXHZRRSDM24A6NF2.json","graph_json":"https://pith.science/api/pith-number/5VPLR6JJUSLXHZRRSDM24A6NF2/graph.json","events_json":"https://pith.science/api/pith-number/5VPLR6JJUSLXHZRRSDM24A6NF2/events.json","paper":"https://pith.science/paper/5VPLR6JJ"},"agent_actions":{"view_html":"https://pith.science/pith/5VPLR6JJUSLXHZRRSDM24A6NF2","download_json":"https://pith.science/pith/5VPLR6JJUSLXHZRRSDM24A6NF2.json","view_paper":"https://pith.science/paper/5VPLR6JJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.02204&json=true","fetch_graph":"https://pith.science/api/pith-number/5VPLR6JJUSLXHZRRSDM24A6NF2/graph.json","fetch_events":"https://pith.science/api/pith-number/5VPLR6JJUSLXHZRRSDM24A6NF2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5VPLR6JJUSLXHZRRSDM24A6NF2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5VPLR6JJUSLXHZRRSDM24A6NF2/action/storage_attestation","attest_author":"https://pith.science/pith/5VPLR6JJUSLXHZRRSDM24A6NF2/action/author_attestation","sign_citation":"https://pith.science/pith/5VPLR6JJUSLXHZRRSDM24A6NF2/action/citation_signature","submit_replication":"https://pith.science/pith/5VPLR6JJUSLXHZRRSDM24A6NF2/action/replication_record"}},"created_at":"2026-06-02T03:04:53.059175+00:00","updated_at":"2026-06-02T03:04:53.059175+00:00"}