{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5CKTMWJEE7ZV7LGD5AO3MVZEAE","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":"8e67a05a6fbfc32403f6242edaebe4c51cc323b7f6b6e73e0b89abb7dffe3861","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-01T02:19:41Z","title_canon_sha256":"8cd3c82d0f2bcb07d021aa004e69db6015c908bb5c545ffedd37b4673c099d34"},"schema_version":"1.0","source":{"id":"2309.00215","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.00215","created_at":"2026-07-05T06:46:53Z"},{"alias_kind":"arxiv_version","alias_value":"2309.00215v1","created_at":"2026-07-05T06:46:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.00215","created_at":"2026-07-05T06:46:53Z"},{"alias_kind":"pith_short_12","alias_value":"5CKTMWJEE7ZV","created_at":"2026-07-05T06:46:53Z"},{"alias_kind":"pith_short_16","alias_value":"5CKTMWJEE7ZV7LGD","created_at":"2026-07-05T06:46:53Z"},{"alias_kind":"pith_short_8","alias_value":"5CKTMWJE","created_at":"2026-07-05T06:46:53Z"}],"graph_snapshots":[{"event_id":"sha256:ade488cba1c0212fbd105935dd8c227850486d4fe535a916ad56f9f07aaa414c","target":"graph","created_at":"2026-07-05T06:46:53Z","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/2309.00215/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Object proposal generation serves as a standard pre-processing step in Vision-Language (VL) tasks (image captioning, visual question answering, etc.). The performance of object proposals generated for VL tasks is currently evaluated across all available annotations, a protocol that we show is misaligned - higher scores do not necessarily correspond to improved performance on downstream VL tasks. Our work serves as a study of this phenomenon and explores the effectiveness of semantic grounding to mitigate its effects. To this end, we propose evaluating object proposals against only a subset of ","authors_text":"Joshua Feinglass, Yezhou Yang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-01T02:19:41Z","title":"Towards Addressing the Misalignment of Object Proposal Evaluation for Vision-Language Tasks via Semantic Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.00215","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":"sha256:6edff99a4be7eb7f2b472703696d6074b5cc4f33ee9be9fc4e9664e3d549e681","target":"record","created_at":"2026-07-05T06:46:53Z","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":"8e67a05a6fbfc32403f6242edaebe4c51cc323b7f6b6e73e0b89abb7dffe3861","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-01T02:19:41Z","title_canon_sha256":"8cd3c82d0f2bcb07d021aa004e69db6015c908bb5c545ffedd37b4673c099d34"},"schema_version":"1.0","source":{"id":"2309.00215","kind":"arxiv","version":1}},"canonical_sha256":"e89536592427f35facc3e81db657240115c2e8d60eb9a0034abb25bc0fb65a38","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e89536592427f35facc3e81db657240115c2e8d60eb9a0034abb25bc0fb65a38","first_computed_at":"2026-07-05T06:46:53.856819Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:46:53.856819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gFdPPkR0sxEVx7lC7/hPdBC97JFQ8oOF0l8/if/l75kcVYA+6TyZg5NtaqrJghAcp73vj4yFUF4lSyJKW/SFBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:46:53.857280Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.00215","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6edff99a4be7eb7f2b472703696d6074b5cc4f33ee9be9fc4e9664e3d549e681","sha256:ade488cba1c0212fbd105935dd8c227850486d4fe535a916ad56f9f07aaa414c"],"state_sha256":"9235af5287090112079a04dd5f8203e103271fc6c0ff545b5806014a3eab10c9"}