{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CRINC73ZCKQC5K33MPSM73OWKQ","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":"6248ba6f4094793fb571a9247d87839310569af4b3cf50a08ede1791ed5e646f","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-26T23:00:43Z","title_canon_sha256":"d9f06b95c7d9bc044966a9faffd97dd74aa6f57eb4b0ace7e4a0644ebff6b3d0"},"schema_version":"1.0","source":{"id":"2507.20077","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.20077","created_at":"2026-07-05T11:56:59Z"},{"alias_kind":"arxiv_version","alias_value":"2507.20077v2","created_at":"2026-07-05T11:56:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.20077","created_at":"2026-07-05T11:56:59Z"},{"alias_kind":"pith_short_12","alias_value":"CRINC73ZCKQC","created_at":"2026-07-05T11:56:59Z"},{"alias_kind":"pith_short_16","alias_value":"CRINC73ZCKQC5K33","created_at":"2026-07-05T11:56:59Z"},{"alias_kind":"pith_short_8","alias_value":"CRINC73Z","created_at":"2026-07-05T11:56:59Z"}],"graph_snapshots":[{"event_id":"sha256:f9f34c28ad29a8ff35016f995abbf847e3146692a1f0f02cacdb12371bc55ecf","target":"graph","created_at":"2026-07-05T11:56:59Z","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/2507.20077/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite significant advances in vision-language models (VLMs), image captioning often suffers from a lack of detail, with base models producing short, generic captions. This limitation persists even though VLMs are equipped with strong vision and language backbones. While supervised data and complex reward functions have been proposed to improve detailed image captioning, we identify a simpler underlying issue: a bias towards the end-of-sequence (EOS) token, which is introduced during cross-entropy training. We propose an unsupervised method to debias the model's tendency to predict the EOS to","authors_text":"Abdelrahman Mohamed, Yova Kementchedjhieva","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-26T23:00:43Z","title":"The Devil is in the EOS: Sequence Training for Detailed Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.20077","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:baf3e94201d5df115c25ff0039afaad5bb97d835ed7e9e6de793daf226376fab","target":"record","created_at":"2026-07-05T11:56:59Z","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":"6248ba6f4094793fb571a9247d87839310569af4b3cf50a08ede1791ed5e646f","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-26T23:00:43Z","title_canon_sha256":"d9f06b95c7d9bc044966a9faffd97dd74aa6f57eb4b0ace7e4a0644ebff6b3d0"},"schema_version":"1.0","source":{"id":"2507.20077","kind":"arxiv","version":2}},"canonical_sha256":"1450d17f7912a02eab7b63e4cfedd65439192a352d94797f9fb3b929391cdbc6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1450d17f7912a02eab7b63e4cfedd65439192a352d94797f9fb3b929391cdbc6","first_computed_at":"2026-07-05T11:56:59.624532Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:56:59.624532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rWw7y8g0Tyhb/v4jcWVespMH57sZi7D5KtU88IDSjPayy0PTNqDYmEEdID0DMsGeMfSL4GEIaEqSwkiW9OdGAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:56:59.625005Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.20077","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:baf3e94201d5df115c25ff0039afaad5bb97d835ed7e9e6de793daf226376fab","sha256:f9f34c28ad29a8ff35016f995abbf847e3146692a1f0f02cacdb12371bc55ecf"],"state_sha256":"aeae0813dbecd03306e37d0e69963e92ff05d895f4f9703c1ff1dfdb30f977a3"}