{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:IFKGFBYRA5GOTYQPMDXAKDSJXX","short_pith_number":"pith:IFKGFBYR","schema_version":"1.0","canonical_sha256":"4154628711074ce9e20f60ee050e49bded919cc7fa09ad759a75bbeb66fbf78f","source":{"kind":"arxiv","id":"2003.10925","version":1},"attestation_state":"computed","paper":{"title":"Learning Compact Reward for Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Nannan Li, Zhenzhong Chen","submitted_at":"2020-03-24T15:31:05Z","abstract_excerpt":"Adversarial learning has shown its advances in generating natural and diverse descriptions in image captioning. However, the learned reward of existing adversarial methods is vague and ill-defined due to the reward ambiguity problem. In this paper, we propose a refined Adversarial Inverse Reinforcement Learning (rAIRL) method to handle the reward ambiguity problem by disentangling reward for each word in a sentence, as well as achieve stable adversarial training by refining the loss function to shift the generator towards Nash equilibrium. In addition, we introduce a conditional term in the lo"},"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":"2003.10925","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-03-24T15:31:05Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d0bf56ec79abc9da4468a2f205961bb604e273e675c6053ffb2a31af79306349","abstract_canon_sha256":"e2d8f63b9d8d25ffb5fe35a4a05bd76d6d702e50dc312237af69b5f940326c80"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:50:21.934798Z","signature_b64":"rc/pRoZzHoLWh31gwr1GOJv5lj9aYTEGnXzyy3Vest/ulAXZP1nD3z5oDBBeMrPiBbkCIlkW9C6Ub/SoYQG6Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4154628711074ce9e20f60ee050e49bded919cc7fa09ad759a75bbeb66fbf78f","last_reissued_at":"2026-07-05T00:50:21.934362Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:50:21.934362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Compact Reward for Image Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Nannan Li, Zhenzhong Chen","submitted_at":"2020-03-24T15:31:05Z","abstract_excerpt":"Adversarial learning has shown its advances in generating natural and diverse descriptions in image captioning. However, the learned reward of existing adversarial methods is vague and ill-defined due to the reward ambiguity problem. In this paper, we propose a refined Adversarial Inverse Reinforcement Learning (rAIRL) method to handle the reward ambiguity problem by disentangling reward for each word in a sentence, as well as achieve stable adversarial training by refining the loss function to shift the generator towards Nash equilibrium. In addition, we introduce a conditional term in the lo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.10925","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/2003.10925/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":"2003.10925","created_at":"2026-07-05T00:50:21.934427+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.10925v1","created_at":"2026-07-05T00:50:21.934427+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.10925","created_at":"2026-07-05T00:50:21.934427+00:00"},{"alias_kind":"pith_short_12","alias_value":"IFKGFBYRA5GO","created_at":"2026-07-05T00:50:21.934427+00:00"},{"alias_kind":"pith_short_16","alias_value":"IFKGFBYRA5GOTYQP","created_at":"2026-07-05T00:50:21.934427+00:00"},{"alias_kind":"pith_short_8","alias_value":"IFKGFBYR","created_at":"2026-07-05T00:50:21.934427+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/IFKGFBYRA5GOTYQPMDXAKDSJXX","json":"https://pith.science/pith/IFKGFBYRA5GOTYQPMDXAKDSJXX.json","graph_json":"https://pith.science/api/pith-number/IFKGFBYRA5GOTYQPMDXAKDSJXX/graph.json","events_json":"https://pith.science/api/pith-number/IFKGFBYRA5GOTYQPMDXAKDSJXX/events.json","paper":"https://pith.science/paper/IFKGFBYR"},"agent_actions":{"view_html":"https://pith.science/pith/IFKGFBYRA5GOTYQPMDXAKDSJXX","download_json":"https://pith.science/pith/IFKGFBYRA5GOTYQPMDXAKDSJXX.json","view_paper":"https://pith.science/paper/IFKGFBYR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.10925&json=true","fetch_graph":"https://pith.science/api/pith-number/IFKGFBYRA5GOTYQPMDXAKDSJXX/graph.json","fetch_events":"https://pith.science/api/pith-number/IFKGFBYRA5GOTYQPMDXAKDSJXX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IFKGFBYRA5GOTYQPMDXAKDSJXX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IFKGFBYRA5GOTYQPMDXAKDSJXX/action/storage_attestation","attest_author":"https://pith.science/pith/IFKGFBYRA5GOTYQPMDXAKDSJXX/action/author_attestation","sign_citation":"https://pith.science/pith/IFKGFBYRA5GOTYQPMDXAKDSJXX/action/citation_signature","submit_replication":"https://pith.science/pith/IFKGFBYRA5GOTYQPMDXAKDSJXX/action/replication_record"}},"created_at":"2026-07-05T00:50:21.934427+00:00","updated_at":"2026-07-05T00:50:21.934427+00:00"}