{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4QJ4REQ7RCXTZ5DXWXARP2EXSG","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":"7979ffbcf1ad0bbfe90613749c7caa1fbce3dec19fdc8ba08ce132a00278be0d","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-08T03:26:38Z","title_canon_sha256":"644b87635b471da6e27deaa995c4aaea40a72086b44322367db8db00cba3885a"},"schema_version":"1.0","source":{"id":"2608.07886","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.07886","created_at":"2026-08-11T01:18:50Z"},{"alias_kind":"arxiv_version","alias_value":"2608.07886v1","created_at":"2026-08-11T01:18:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.07886","created_at":"2026-08-11T01:18:50Z"},{"alias_kind":"pith_short_12","alias_value":"4QJ4REQ7RCXT","created_at":"2026-08-11T01:18:50Z"},{"alias_kind":"pith_short_16","alias_value":"4QJ4REQ7RCXTZ5DX","created_at":"2026-08-11T01:18:50Z"},{"alias_kind":"pith_short_8","alias_value":"4QJ4REQ7","created_at":"2026-08-11T01:18:50Z"}],"graph_snapshots":[{"event_id":"sha256:22529aa54ad8ff5fd04b4e9ca84ec72e8c317be40d0512a9ba8bd15c7c34869a","target":"graph","created_at":"2026-08-11T01:18:50Z","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/2608.07886/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language grounding connects language to visual content, yet most existing formulations reduce grounding to a unidirectional localization problem: given a prespecified text phrase or category name, identify the corresponding image region. This setup assumes that the relevant linguistic unit is already known, overlooking a more basic challenge in grounded communication: determining which parts of the text are visually referential and how they correspond to entities in the image. We formulate grounding as $\\textit{bidirectional concept correspondence}$ over an image-text pair. Given an ima","authors_text":"Jieyu Zhang, Luke Zettlemoyer, Ranjay Krishna, Ziqi Gao","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-08T03:26:38Z","title":"Vision-Language Grounding as Bidirectional Concept Correspondence"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.07886","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":"sha256:74c518f932fd0c76c26064f07155c0b8fde3ce180721630461dd1c6822d94234","target":"record","created_at":"2026-08-11T01:18:50Z","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":"7979ffbcf1ad0bbfe90613749c7caa1fbce3dec19fdc8ba08ce132a00278be0d","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-08T03:26:38Z","title_canon_sha256":"644b87635b471da6e27deaa995c4aaea40a72086b44322367db8db00cba3885a"},"schema_version":"1.0","source":{"id":"2608.07886","kind":"arxiv","version":1}},"canonical_sha256":"e413c8921f88af3cf477b5c117e897918c4c421e7a62c079e4a5d6c0a5794144","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e413c8921f88af3cf477b5c117e897918c4c421e7a62c079e4a5d6c0a5794144","first_computed_at":"2026-08-11T01:18:50.293367Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T01:18:50.293367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/cZ7FrwW7PjQ0IRnq7RpAHi54xHwtHnidkCTfgTmglG5NSdzQnK3GxtUA+AhbhM+IiToYALojZRFA4ysWooSDg==","signature_status":"signed_v1","signed_at":"2026-08-11T01:18:50.295782Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.07886","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:74c518f932fd0c76c26064f07155c0b8fde3ce180721630461dd1c6822d94234","sha256:22529aa54ad8ff5fd04b4e9ca84ec72e8c317be40d0512a9ba8bd15c7c34869a"],"state_sha256":"cf14e1a586b28fdacc15a63dd7c795e9db0840b1b4dacf100ed0df1b8281ea8e"}