{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5DLWYQR6JAKYUTIBCA7BDPTXUX","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":"01f55e08c98f10a5091429eb0ac87088ba3825e5b1faaf66cb940b78fe10454b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-04T18:32:39Z","title_canon_sha256":"ef7ce293636f37c9dc76515260f848d214b4a099a3b572f5a83b3f8473d3a343"},"schema_version":"1.0","source":{"id":"2409.03025","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.03025","created_at":"2026-07-05T10:46:20Z"},{"alias_kind":"arxiv_version","alias_value":"2409.03025v2","created_at":"2026-07-05T10:46:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.03025","created_at":"2026-07-05T10:46:20Z"},{"alias_kind":"pith_short_12","alias_value":"5DLWYQR6JAKY","created_at":"2026-07-05T10:46:20Z"},{"alias_kind":"pith_short_16","alias_value":"5DLWYQR6JAKYUTIB","created_at":"2026-07-05T10:46:20Z"},{"alias_kind":"pith_short_8","alias_value":"5DLWYQR6","created_at":"2026-07-05T10:46:20Z"}],"graph_snapshots":[{"event_id":"sha256:d75563f9c2ed5b873191b617250d989f3bcadf40134ac80f8c28ef371b015c4c","target":"graph","created_at":"2026-07-05T10:46:20Z","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/2409.03025/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image captioning systems are unable to generate fine-grained captions as they are trained on data that is either noisy (alt-text) or generic (human annotations). This is further exacerbated by maximum likelihood training that encourages generation of frequently occurring phrases. Previous works have tried to address this limitation by fine-tuning captioners with a self-retrieval (SR) reward. However, we find that SR fine-tuning has a tendency to reduce caption faithfulness and even hallucinate. In this work, we circumvent this bottleneck by improving the MLE initialization of the captioning sy","authors_text":"Darshan Singh, Makarand Tapaswi, Manu Gaur","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-04T18:32:39Z","title":"No Detail Left Behind: Revisiting Self-Retrieval for Fine-Grained Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.03025","kind":"arxiv","version":2},"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":"sha256:0967ff588b163ed5bc72c97e5ae6e382b9178d3dccf6ca0d1fe5b8f2c11655f2","target":"record","created_at":"2026-07-05T10:46:20Z","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":"01f55e08c98f10a5091429eb0ac87088ba3825e5b1faaf66cb940b78fe10454b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-04T18:32:39Z","title_canon_sha256":"ef7ce293636f37c9dc76515260f848d214b4a099a3b572f5a83b3f8473d3a343"},"schema_version":"1.0","source":{"id":"2409.03025","kind":"arxiv","version":2}},"canonical_sha256":"e8d76c423e48158a4d01103e11be77a5e8d7b299690affc9b0b85022fdf8a021","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e8d76c423e48158a4d01103e11be77a5e8d7b299690affc9b0b85022fdf8a021","first_computed_at":"2026-07-05T10:46:20.222017Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:46:20.222017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yIOYNYEL3dNdTljKOCL0F63hKeWcRkmDuXWs6jBZ0GsGVpi6XF8eLhzLn1v2Y5C5Bd/5LzLqeuOGfKMxys8+AA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:46:20.222480Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.03025","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0967ff588b163ed5bc72c97e5ae6e382b9178d3dccf6ca0d1fe5b8f2c11655f2","sha256:d75563f9c2ed5b873191b617250d989f3bcadf40134ac80f8c28ef371b015c4c"],"state_sha256":"e049fc550c1cfc8a69c6dc9193888889533d1562fc265224de194f8738670c66"}