{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DR3DM65NH4CPZGC6GLGXKFYQCR","short_pith_number":"pith:DR3DM65N","schema_version":"1.0","canonical_sha256":"1c76367bad3f04fc985e32cd751710147e8f3f5ba073814c43cfee7c7be0822a","source":{"kind":"arxiv","id":"2505.05970","version":1},"attestation_state":"computed","paper":{"title":"Towards Developmentally Plausible Rewards: Communicative Success as a Learning Signal for Interactive Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alex Warstadt, Lennart St\\\"opler, Mitja Nikolaus, Rufat Asadli, Ryan Cotterell","submitted_at":"2025-05-09T11:48:36Z","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 "},"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":"2505.05970","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-09T11:48:36Z","cross_cats_sorted":[],"title_canon_sha256":"4c6e4c66d9a74fc40a220ee0db8b119ef4b9b267e378102f5096ea28dbf7e376","abstract_canon_sha256":"30a63afd4898a60c7c33292ab277334dd5c34af53362e36d27c2fe643db431f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:00:51.041324Z","signature_b64":"TEF3kWq5Duf7KkcoO75ARIoWkpFLQ/6LqJWvL2qlBGH6zIDsVxRLXekvzRpuDUvlKXmvI1P1WqqGB2lwbA7dDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c76367bad3f04fc985e32cd751710147e8f3f5ba073814c43cfee7c7be0822a","last_reissued_at":"2026-07-05T11:00:51.040758Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:00:51.040758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Developmentally Plausible Rewards: Communicative Success as a Learning Signal for Interactive Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alex Warstadt, Lennart St\\\"opler, Mitja Nikolaus, Rufat Asadli, Ryan Cotterell","submitted_at":"2025-05-09T11:48:36Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.05970","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/2505.05970/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":"2505.05970","created_at":"2026-07-05T11:00:51.040817+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.05970v1","created_at":"2026-07-05T11:00:51.040817+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05970","created_at":"2026-07-05T11:00:51.040817+00:00"},{"alias_kind":"pith_short_12","alias_value":"DR3DM65NH4CP","created_at":"2026-07-05T11:00:51.040817+00:00"},{"alias_kind":"pith_short_16","alias_value":"DR3DM65NH4CPZGC6","created_at":"2026-07-05T11:00:51.040817+00:00"},{"alias_kind":"pith_short_8","alias_value":"DR3DM65N","created_at":"2026-07-05T11:00:51.040817+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/DR3DM65NH4CPZGC6GLGXKFYQCR","json":"https://pith.science/pith/DR3DM65NH4CPZGC6GLGXKFYQCR.json","graph_json":"https://pith.science/api/pith-number/DR3DM65NH4CPZGC6GLGXKFYQCR/graph.json","events_json":"https://pith.science/api/pith-number/DR3DM65NH4CPZGC6GLGXKFYQCR/events.json","paper":"https://pith.science/paper/DR3DM65N"},"agent_actions":{"view_html":"https://pith.science/pith/DR3DM65NH4CPZGC6GLGXKFYQCR","download_json":"https://pith.science/pith/DR3DM65NH4CPZGC6GLGXKFYQCR.json","view_paper":"https://pith.science/paper/DR3DM65N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.05970&json=true","fetch_graph":"https://pith.science/api/pith-number/DR3DM65NH4CPZGC6GLGXKFYQCR/graph.json","fetch_events":"https://pith.science/api/pith-number/DR3DM65NH4CPZGC6GLGXKFYQCR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DR3DM65NH4CPZGC6GLGXKFYQCR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DR3DM65NH4CPZGC6GLGXKFYQCR/action/storage_attestation","attest_author":"https://pith.science/pith/DR3DM65NH4CPZGC6GLGXKFYQCR/action/author_attestation","sign_citation":"https://pith.science/pith/DR3DM65NH4CPZGC6GLGXKFYQCR/action/citation_signature","submit_replication":"https://pith.science/pith/DR3DM65NH4CPZGC6GLGXKFYQCR/action/replication_record"}},"created_at":"2026-07-05T11:00:51.040817+00:00","updated_at":"2026-07-05T11:00:51.040817+00:00"}