{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:4P5NS3UOXO4E7BAKZUDOGLFMSA","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":"047215f3b36f0171a30c57633f3ff4eac56dcb0b70b2e568f5437fececdfdde3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-17T19:45:05Z","title_canon_sha256":"9c19758b0d5ac08215c6c1adb9c6baec776c82d4ec2c10c84201fcd14e984282"},"schema_version":"1.0","source":{"id":"1811.07212","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.07212","created_at":"2026-07-05T01:42:11Z"},{"alias_kind":"arxiv_version","alias_value":"1811.07212v3","created_at":"2026-07-05T01:42:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.07212","created_at":"2026-07-05T01:42:11Z"},{"alias_kind":"pith_short_12","alias_value":"4P5NS3UOXO4E","created_at":"2026-07-05T01:42:11Z"},{"alias_kind":"pith_short_16","alias_value":"4P5NS3UOXO4E7BAK","created_at":"2026-07-05T01:42:11Z"},{"alias_kind":"pith_short_8","alias_value":"4P5NS3UO","created_at":"2026-07-05T01:42:11Z"}],"graph_snapshots":[{"event_id":"sha256:5034aa112e1c5c119ab94a64af359f9ecabe1aecbac2baffb764c2bd0a0c54fe","target":"graph","created_at":"2026-07-05T01:42:11Z","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/1811.07212/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most existing work that grounds natural language phrases in images starts with the assumption that the phrase in question is relevant to the image. In this paper we address a more realistic version of the natural language grounding task where we must both identify whether the phrase is relevant to an image and localize the phrase. This can also be viewed as a generalization of object detection to an open-ended vocabulary, introducing elements of few- and zero-shot detection. We propose an approach for this task that extends Faster R-CNN to relate image regions and phrases. By carefully initial","authors_text":"Bryan A. Plummer, Kate Saenko, Kevin J. Shih, Ke Xu, Stan Sclaroff, Svetlana Lazebnik, Yichen Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-17T19:45:05Z","title":"Revisiting Image-Language Networks for Open-ended Phrase Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.07212","kind":"arxiv","version":3},"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":"sha256:68edde1f0f8273431d81ed49a8a0cff5f5e18e222c052e8ebd005bc526811284","target":"record","created_at":"2026-07-05T01:42:11Z","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":"047215f3b36f0171a30c57633f3ff4eac56dcb0b70b2e568f5437fececdfdde3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-17T19:45:05Z","title_canon_sha256":"9c19758b0d5ac08215c6c1adb9c6baec776c82d4ec2c10c84201fcd14e984282"},"schema_version":"1.0","source":{"id":"1811.07212","kind":"arxiv","version":3}},"canonical_sha256":"e3fad96e8ebbb84f840acd06e32cac9008498281826c1005b10582d1c6e1ba8f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e3fad96e8ebbb84f840acd06e32cac9008498281826c1005b10582d1c6e1ba8f","first_computed_at":"2026-07-05T01:42:11.987401Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:42:11.987401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tKyRT+TOeB1sQyJHXIIZUgC/s+7j0QDpj5FNB0g54yKmLKa4xujyYYQCrxMX3h33CkGwgmYdlE7kUdc4R59iCw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:42:11.987794Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.07212","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:68edde1f0f8273431d81ed49a8a0cff5f5e18e222c052e8ebd005bc526811284","sha256:5034aa112e1c5c119ab94a64af359f9ecabe1aecbac2baffb764c2bd0a0c54fe"],"state_sha256":"f7931fff86d219043ffabcefcf5de7e28188b1f847bb452915391bd62e7a47cf"}