{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:UVSCDZYJQA5LZ4XXC7DFLCL6Y6","short_pith_number":"pith:UVSCDZYJ","canonical_record":{"source":{"id":"1911.09753","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-11-21T21:26:28Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c2605eab885ebf2ba4c416576184e6eb71bbcd77aea10b7f5a975a1501a324f2","abstract_canon_sha256":"186fbb22041abb261ba1c9e647dc285338de92e91af4963aa8cebae43cca6632"},"schema_version":"1.0"},"canonical_sha256":"a56421e709803abcf2f717c655897ec7b74483b429b1c19748a8aac7df2ab2b7","source":{"kind":"arxiv","id":"1911.09753","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.09753","created_at":"2026-07-05T00:21:17Z"},{"alias_kind":"arxiv_version","alias_value":"1911.09753v1","created_at":"2026-07-05T00:21:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.09753","created_at":"2026-07-05T00:21:17Z"},{"alias_kind":"pith_short_12","alias_value":"UVSCDZYJQA5L","created_at":"2026-07-05T00:21:17Z"},{"alias_kind":"pith_short_16","alias_value":"UVSCDZYJQA5LZ4XX","created_at":"2026-07-05T00:21:17Z"},{"alias_kind":"pith_short_8","alias_value":"UVSCDZYJ","created_at":"2026-07-05T00:21:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:UVSCDZYJQA5LZ4XXC7DFLCL6Y6","target":"record","payload":{"canonical_record":{"source":{"id":"1911.09753","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-11-21T21:26:28Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c2605eab885ebf2ba4c416576184e6eb71bbcd77aea10b7f5a975a1501a324f2","abstract_canon_sha256":"186fbb22041abb261ba1c9e647dc285338de92e91af4963aa8cebae43cca6632"},"schema_version":"1.0"},"canonical_sha256":"a56421e709803abcf2f717c655897ec7b74483b429b1c19748a8aac7df2ab2b7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:21:17.382989Z","signature_b64":"Es7bly2eA2L9YWD5KuH4yRA0NkQkTlshQzkiUH90cT+4IGCl6TIswokXySLBTwRnwjMGgUXZ7OKKdn9tz7tDDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a56421e709803abcf2f717c655897ec7b74483b429b1c19748a8aac7df2ab2b7","last_reissued_at":"2026-07-05T00:21:17.382583Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:21:17.382583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1911.09753","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:21:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vgdLPY70saELyD/uE8TNDEWnl2Dy9x4MBzsifNQpMkLV0tMw0WTXEp60UQXQ1niqX64n1CFaLdjq3Dz1ZRFSCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T11:13:13.613723Z"},"content_sha256":"3ce0df76d120a6cf8405195f213e3f0d113aee951260b204c650c81ef3db4bd3","schema_version":"1.0","event_id":"sha256:3ce0df76d120a6cf8405195f213e3f0d113aee951260b204c650c81ef3db4bd3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:UVSCDZYJQA5LZ4XXC7DFLCL6Y6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcing an Image Caption Generator Using Off-Line Human Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Bohyung Han, Paul Hongsuck Seo, Piyush Sharma, Radu Soricut, Tomer Levinboim","submitted_at":"2019-11-21T21:26:28Z","abstract_excerpt":"Human ratings are currently the most accurate way to assess the quality of an image captioning model, yet most often the only used outcome of an expensive human rating evaluation is a few overall statistics over the evaluation dataset. In this paper, we show that the signal from instance-level human caption ratings can be leveraged to improve captioning models, even when the amount of caption ratings is several orders of magnitude less than the caption training data. We employ a policy gradient method to maximize the human ratings as rewards in an off-policy reinforcement learning setting, whe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.09753","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/1911.09753/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:21:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2OunlcqlkSRLkPrX92uXp+4M5jA0MpR0hKF9QEadOtWg6jJNDYyQzWNB5dCdHTGYnXz7hNC41YFnefjUWpr0DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T11:13:13.614827Z"},"content_sha256":"9e9c53d7ce564acef361ddd393f3bb032bedc477839256f573d97f7a03c80222","schema_version":"1.0","event_id":"sha256:9e9c53d7ce564acef361ddd393f3bb032bedc477839256f573d97f7a03c80222"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UVSCDZYJQA5LZ4XXC7DFLCL6Y6/bundle.json","state_url":"https://pith.science/pith/UVSCDZYJQA5LZ4XXC7DFLCL6Y6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UVSCDZYJQA5LZ4XXC7DFLCL6Y6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-14T11:13:13Z","links":{"resolver":"https://pith.science/pith/UVSCDZYJQA5LZ4XXC7DFLCL6Y6","bundle":"https://pith.science/pith/UVSCDZYJQA5LZ4XXC7DFLCL6Y6/bundle.json","state":"https://pith.science/pith/UVSCDZYJQA5LZ4XXC7DFLCL6Y6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UVSCDZYJQA5LZ4XXC7DFLCL6Y6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:UVSCDZYJQA5LZ4XXC7DFLCL6Y6","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":"186fbb22041abb261ba1c9e647dc285338de92e91af4963aa8cebae43cca6632","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-11-21T21:26:28Z","title_canon_sha256":"c2605eab885ebf2ba4c416576184e6eb71bbcd77aea10b7f5a975a1501a324f2"},"schema_version":"1.0","source":{"id":"1911.09753","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.09753","created_at":"2026-07-05T00:21:17Z"},{"alias_kind":"arxiv_version","alias_value":"1911.09753v1","created_at":"2026-07-05T00:21:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.09753","created_at":"2026-07-05T00:21:17Z"},{"alias_kind":"pith_short_12","alias_value":"UVSCDZYJQA5L","created_at":"2026-07-05T00:21:17Z"},{"alias_kind":"pith_short_16","alias_value":"UVSCDZYJQA5LZ4XX","created_at":"2026-07-05T00:21:17Z"},{"alias_kind":"pith_short_8","alias_value":"UVSCDZYJ","created_at":"2026-07-05T00:21:17Z"}],"graph_snapshots":[{"event_id":"sha256:9e9c53d7ce564acef361ddd393f3bb032bedc477839256f573d97f7a03c80222","target":"graph","created_at":"2026-07-05T00:21:17Z","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/1911.09753/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Human ratings are currently the most accurate way to assess the quality of an image captioning model, yet most often the only used outcome of an expensive human rating evaluation is a few overall statistics over the evaluation dataset. In this paper, we show that the signal from instance-level human caption ratings can be leveraged to improve captioning models, even when the amount of caption ratings is several orders of magnitude less than the caption training data. We employ a policy gradient method to maximize the human ratings as rewards in an off-policy reinforcement learning setting, whe","authors_text":"Bohyung Han, Paul Hongsuck Seo, Piyush Sharma, Radu Soricut, Tomer Levinboim","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-11-21T21:26:28Z","title":"Reinforcing an Image Caption Generator Using Off-Line Human Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.09753","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":"sha256:3ce0df76d120a6cf8405195f213e3f0d113aee951260b204c650c81ef3db4bd3","target":"record","created_at":"2026-07-05T00:21:17Z","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":"186fbb22041abb261ba1c9e647dc285338de92e91af4963aa8cebae43cca6632","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-11-21T21:26:28Z","title_canon_sha256":"c2605eab885ebf2ba4c416576184e6eb71bbcd77aea10b7f5a975a1501a324f2"},"schema_version":"1.0","source":{"id":"1911.09753","kind":"arxiv","version":1}},"canonical_sha256":"a56421e709803abcf2f717c655897ec7b74483b429b1c19748a8aac7df2ab2b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a56421e709803abcf2f717c655897ec7b74483b429b1c19748a8aac7df2ab2b7","first_computed_at":"2026-07-05T00:21:17.382583Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:21:17.382583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Es7bly2eA2L9YWD5KuH4yRA0NkQkTlshQzkiUH90cT+4IGCl6TIswokXySLBTwRnwjMGgUXZ7OKKdn9tz7tDDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:21:17.382989Z","signed_message":"canonical_sha256_bytes"},"source_id":"1911.09753","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ce0df76d120a6cf8405195f213e3f0d113aee951260b204c650c81ef3db4bd3","sha256:9e9c53d7ce564acef361ddd393f3bb032bedc477839256f573d97f7a03c80222"],"state_sha256":"2479172e7e1a25146c42256b41096d1ca688c78049b2d4a2a7a17242a499a2ab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oyL7N4H9oPq353XdYfDAfXhhv/3rxU1Bahijxhby4YbkN6/UaKYorrJWJTS4Y4Os7+UcKEWAQ01Sg9UF8ZgXCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T11:13:13.631504Z","bundle_sha256":"e72f480de8a0929fea46d1d441b771204862ce70b6820e0ab6f31fffdf253093"}}