{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:X52UKHPH7MQRL53DXL6NOR4MG5","short_pith_number":"pith:X52UKHPH","schema_version":"1.0","canonical_sha256":"bf75451de7fb2115f763bafcd7478c375dd560a67c6292eaafffd67bcf529e38","source":{"kind":"arxiv","id":"1907.11565","version":1},"attestation_state":"computed","paper":{"title":"Cooperative image captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gal Chechik, Gal Oren, Gilad Vered, Yuval Atzmon","submitted_at":"2019-07-26T13:18:56Z","abstract_excerpt":"When describing images with natural language, the descriptions can be made more informative if tuned using downstream tasks. This is often achieved by training two networks: a \"speaker network\" that generates sentences given an image, and a \"listener network\" that uses them to perform a task. Unfortunately, training multiple networks jointly to communicate to achieve a joint task, faces two major challenges. First, the descriptions generated by a speaker network are discrete and stochastic, making optimization very hard and inefficient. Second, joint training usually causes the vocabulary used"},"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":"1907.11565","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-26T13:18:56Z","cross_cats_sorted":[],"title_canon_sha256":"97f1e2863cd07679ac169799965d8810f63063c1b1ad9b4983103569031b896f","abstract_canon_sha256":"ff4a98f111fe6fe948987b57186fbf89a2d835beca3c3857c8fba5ec1f4a78a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:28.667515Z","signature_b64":"Yh3XY76gNGGjbtaGzcjSOL1Nt0Y2dVp08QBdSz+S6vYlaxSBo9n0serW8R2YMECWDP9MyaI4YHx3DyeBdma0BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf75451de7fb2115f763bafcd7478c375dd560a67c6292eaafffd67bcf529e38","last_reissued_at":"2026-05-17T23:39:28.666763Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:28.666763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cooperative image captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gal Chechik, Gal Oren, Gilad Vered, Yuval Atzmon","submitted_at":"2019-07-26T13:18:56Z","abstract_excerpt":"When describing images with natural language, the descriptions can be made more informative if tuned using downstream tasks. This is often achieved by training two networks: a \"speaker network\" that generates sentences given an image, and a \"listener network\" that uses them to perform a task. Unfortunately, training multiple networks jointly to communicate to achieve a joint task, faces two major challenges. First, the descriptions generated by a speaker network are discrete and stochastic, making optimization very hard and inefficient. Second, joint training usually causes the vocabulary used"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.11565","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":""},"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":"1907.11565","created_at":"2026-05-17T23:39:28.666879+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.11565v1","created_at":"2026-05-17T23:39:28.666879+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.11565","created_at":"2026-05-17T23:39:28.666879+00:00"},{"alias_kind":"pith_short_12","alias_value":"X52UKHPH7MQR","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"X52UKHPH7MQRL53D","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"X52UKHPH","created_at":"2026-05-18T12:33:33.725879+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/X52UKHPH7MQRL53DXL6NOR4MG5","json":"https://pith.science/pith/X52UKHPH7MQRL53DXL6NOR4MG5.json","graph_json":"https://pith.science/api/pith-number/X52UKHPH7MQRL53DXL6NOR4MG5/graph.json","events_json":"https://pith.science/api/pith-number/X52UKHPH7MQRL53DXL6NOR4MG5/events.json","paper":"https://pith.science/paper/X52UKHPH"},"agent_actions":{"view_html":"https://pith.science/pith/X52UKHPH7MQRL53DXL6NOR4MG5","download_json":"https://pith.science/pith/X52UKHPH7MQRL53DXL6NOR4MG5.json","view_paper":"https://pith.science/paper/X52UKHPH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.11565&json=true","fetch_graph":"https://pith.science/api/pith-number/X52UKHPH7MQRL53DXL6NOR4MG5/graph.json","fetch_events":"https://pith.science/api/pith-number/X52UKHPH7MQRL53DXL6NOR4MG5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X52UKHPH7MQRL53DXL6NOR4MG5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X52UKHPH7MQRL53DXL6NOR4MG5/action/storage_attestation","attest_author":"https://pith.science/pith/X52UKHPH7MQRL53DXL6NOR4MG5/action/author_attestation","sign_citation":"https://pith.science/pith/X52UKHPH7MQRL53DXL6NOR4MG5/action/citation_signature","submit_replication":"https://pith.science/pith/X52UKHPH7MQRL53DXL6NOR4MG5/action/replication_record"}},"created_at":"2026-05-17T23:39:28.666879+00:00","updated_at":"2026-05-17T23:39:28.666879+00:00"}