{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DR3DM65NH4CPZGC6GLGXKFYQCR","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":"30a63afd4898a60c7c33292ab277334dd5c34af53362e36d27c2fe643db431f1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-09T11:48:36Z","title_canon_sha256":"4c6e4c66d9a74fc40a220ee0db8b119ef4b9b267e378102f5096ea28dbf7e376"},"schema_version":"1.0","source":{"id":"2505.05970","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.05970","created_at":"2026-07-05T11:00:51Z"},{"alias_kind":"arxiv_version","alias_value":"2505.05970v1","created_at":"2026-07-05T11:00:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05970","created_at":"2026-07-05T11:00:51Z"},{"alias_kind":"pith_short_12","alias_value":"DR3DM65NH4CP","created_at":"2026-07-05T11:00:51Z"},{"alias_kind":"pith_short_16","alias_value":"DR3DM65NH4CPZGC6","created_at":"2026-07-05T11:00:51Z"},{"alias_kind":"pith_short_8","alias_value":"DR3DM65N","created_at":"2026-07-05T11:00:51Z"}],"graph_snapshots":[{"event_id":"sha256:08d3a0725012ce8e9c7b8f794309ce8e7802e71f770bd391c356739b4d089c55","target":"graph","created_at":"2026-07-05T11:00:51Z","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/2505.05970/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a method for training language models in an interactive setting inspired by child language acquisition. In our setting, a speaker attempts to communicate some information to a listener in a single-turn dialogue and receives a reward if communicative success is achieved. Unlike earlier related work using image--caption data for interactive reference games, we operationalize communicative success in a more abstract language-only question--answering setting. First, we present a feasibility study demonstrating that our reward provides an indirect signal about grammaticality. Second, we ","authors_text":"Alex Warstadt, Lennart St\\\"opler, Mitja Nikolaus, Rufat Asadli, Ryan Cotterell","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-09T11:48:36Z","title":"Towards Developmentally Plausible Rewards: Communicative Success as a Learning Signal for Interactive Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.05970","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":"sha256:17cc3b5ed02bd622f45835163ce700866d2a841623c097a2c6c1e01fa1906de1","target":"record","created_at":"2026-07-05T11:00:51Z","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":"30a63afd4898a60c7c33292ab277334dd5c34af53362e36d27c2fe643db431f1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-09T11:48:36Z","title_canon_sha256":"4c6e4c66d9a74fc40a220ee0db8b119ef4b9b267e378102f5096ea28dbf7e376"},"schema_version":"1.0","source":{"id":"2505.05970","kind":"arxiv","version":1}},"canonical_sha256":"1c76367bad3f04fc985e32cd751710147e8f3f5ba073814c43cfee7c7be0822a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1c76367bad3f04fc985e32cd751710147e8f3f5ba073814c43cfee7c7be0822a","first_computed_at":"2026-07-05T11:00:51.040758Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:00:51.040758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TEF3kWq5Duf7KkcoO75ARIoWkpFLQ/6LqJWvL2qlBGH6zIDsVxRLXekvzRpuDUvlKXmvI1P1WqqGB2lwbA7dDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:00:51.041324Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.05970","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:17cc3b5ed02bd622f45835163ce700866d2a841623c097a2c6c1e01fa1906de1","sha256:08d3a0725012ce8e9c7b8f794309ce8e7802e71f770bd391c356739b4d089c55"],"state_sha256":"cf76c83c54d11cfa47090a8162a49a44be2ac1bc4d74cbc6348aaf7b23e6ac2b"}