{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:MLRVJAZCJL72676H2DPLTTWPJ3","short_pith_number":"pith:MLRVJAZC","schema_version":"1.0","canonical_sha256":"62e35483224affaf7fc7d0deb9cecf4ec282b91009266007e3eccb7090531c95","source":{"kind":"arxiv","id":"2006.00418","version":1},"attestation_state":"computed","paper":{"title":"Learning to refer informatively by amortizing pragmatic reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jesse Mu, Julia White, Noah D. Goodman","submitted_at":"2020-05-31T02:52:22Z","abstract_excerpt":"A hallmark of human language is the ability to effectively and efficiently convey contextually relevant information. One theory for how humans reason about language is presented in the Rational Speech Acts (RSA) framework, which captures pragmatic phenomena via a process of recursive social reasoning (Goodman & Frank, 2016). However, RSA represents ideal reasoning in an unconstrained setting. We explore the idea that speakers might learn to amortize the cost of RSA computation over time by directly optimizing for successful communication with an internal listener model. In simulations with gro"},"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":"2006.00418","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-31T02:52:22Z","cross_cats_sorted":[],"title_canon_sha256":"6b8df68d753b55a2f865e4be50864f22553b438f6fb47cf18797cbcd1de49b8f","abstract_canon_sha256":"4af4c62160a47764bad2c1718352089354d19aeaf927f07d76207bd92acb2ee0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:07:01.376677Z","signature_b64":"M96D3lwQYZjw/uUcykCrNy9B87kO+RvD0QCKNbiSl+wSNxlU+gu/ohMoRcQffC10VzSm35i9kX2lSQ5yFgKkBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62e35483224affaf7fc7d0deb9cecf4ec282b91009266007e3eccb7090531c95","last_reissued_at":"2026-07-05T01:07:01.376130Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:07:01.376130Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to refer informatively by amortizing pragmatic reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jesse Mu, Julia White, Noah D. Goodman","submitted_at":"2020-05-31T02:52:22Z","abstract_excerpt":"A hallmark of human language is the ability to effectively and efficiently convey contextually relevant information. One theory for how humans reason about language is presented in the Rational Speech Acts (RSA) framework, which captures pragmatic phenomena via a process of recursive social reasoning (Goodman & Frank, 2016). However, RSA represents ideal reasoning in an unconstrained setting. We explore the idea that speakers might learn to amortize the cost of RSA computation over time by directly optimizing for successful communication with an internal listener model. In simulations with gro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.00418","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/2006.00418/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":"2006.00418","created_at":"2026-07-05T01:07:01.376190+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.00418v1","created_at":"2026-07-05T01:07:01.376190+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.00418","created_at":"2026-07-05T01:07:01.376190+00:00"},{"alias_kind":"pith_short_12","alias_value":"MLRVJAZCJL72","created_at":"2026-07-05T01:07:01.376190+00:00"},{"alias_kind":"pith_short_16","alias_value":"MLRVJAZCJL72676H","created_at":"2026-07-05T01:07:01.376190+00:00"},{"alias_kind":"pith_short_8","alias_value":"MLRVJAZC","created_at":"2026-07-05T01:07:01.376190+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.01474","citing_title":"Integrating Neural and Symbolic Components in a Model of Pragmatic Question-Answering","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MLRVJAZCJL72676H2DPLTTWPJ3","json":"https://pith.science/pith/MLRVJAZCJL72676H2DPLTTWPJ3.json","graph_json":"https://pith.science/api/pith-number/MLRVJAZCJL72676H2DPLTTWPJ3/graph.json","events_json":"https://pith.science/api/pith-number/MLRVJAZCJL72676H2DPLTTWPJ3/events.json","paper":"https://pith.science/paper/MLRVJAZC"},"agent_actions":{"view_html":"https://pith.science/pith/MLRVJAZCJL72676H2DPLTTWPJ3","download_json":"https://pith.science/pith/MLRVJAZCJL72676H2DPLTTWPJ3.json","view_paper":"https://pith.science/paper/MLRVJAZC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.00418&json=true","fetch_graph":"https://pith.science/api/pith-number/MLRVJAZCJL72676H2DPLTTWPJ3/graph.json","fetch_events":"https://pith.science/api/pith-number/MLRVJAZCJL72676H2DPLTTWPJ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MLRVJAZCJL72676H2DPLTTWPJ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MLRVJAZCJL72676H2DPLTTWPJ3/action/storage_attestation","attest_author":"https://pith.science/pith/MLRVJAZCJL72676H2DPLTTWPJ3/action/author_attestation","sign_citation":"https://pith.science/pith/MLRVJAZCJL72676H2DPLTTWPJ3/action/citation_signature","submit_replication":"https://pith.science/pith/MLRVJAZCJL72676H2DPLTTWPJ3/action/replication_record"}},"created_at":"2026-07-05T01:07:01.376190+00:00","updated_at":"2026-07-05T01:07:01.376190+00:00"}