{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4QJ4REQ7RCXTZ5DXWXARP2EXSG","short_pith_number":"pith:4QJ4REQ7","schema_version":"1.0","canonical_sha256":"e413c8921f88af3cf477b5c117e897918c4c421e7a62c079e4a5d6c0a5794144","source":{"kind":"arxiv","id":"2608.07886","version":1},"attestation_state":"computed","paper":{"title":"Vision-Language Grounding as Bidirectional Concept Correspondence","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Jieyu Zhang, Luke Zettlemoyer, Ranjay Krishna, Ziqi Gao","submitted_at":"2026-08-08T03:26:38Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.07886","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-08T03:26:38Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"644b87635b471da6e27deaa995c4aaea40a72086b44322367db8db00cba3885a","abstract_canon_sha256":"7979ffbcf1ad0bbfe90613749c7caa1fbce3dec19fdc8ba08ce132a00278be0d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T01:18:50.295782Z","signature_b64":"/cZ7FrwW7PjQ0IRnq7RpAHi54xHwtHnidkCTfgTmglG5NSdzQnK3GxtUA+AhbhM+IiToYALojZRFA4ysWooSDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e413c8921f88af3cf477b5c117e897918c4c421e7a62c079e4a5d6c0a5794144","last_reissued_at":"2026-08-11T01:18:50.293367Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T01:18:50.293367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vision-Language Grounding as Bidirectional Concept Correspondence","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Jieyu Zhang, Luke Zettlemoyer, Ranjay Krishna, Ziqi Gao","submitted_at":"2026-08-08T03:26:38Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.07886","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2608.07886/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.07886","created_at":"2026-08-11T01:18:50.294125+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.07886v1","created_at":"2026-08-11T01:18:50.294125+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.07886","created_at":"2026-08-11T01:18:50.294125+00:00"},{"alias_kind":"pith_short_12","alias_value":"4QJ4REQ7RCXT","created_at":"2026-08-11T01:18:50.294125+00:00"},{"alias_kind":"pith_short_16","alias_value":"4QJ4REQ7RCXTZ5DX","created_at":"2026-08-11T01:18:50.294125+00:00"},{"alias_kind":"pith_short_8","alias_value":"4QJ4REQ7","created_at":"2026-08-11T01:18:50.294125+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4QJ4REQ7RCXTZ5DXWXARP2EXSG","json":"https://pith.science/pith/4QJ4REQ7RCXTZ5DXWXARP2EXSG.json","graph_json":"https://pith.science/api/pith-number/4QJ4REQ7RCXTZ5DXWXARP2EXSG/graph.json","events_json":"https://pith.science/api/pith-number/4QJ4REQ7RCXTZ5DXWXARP2EXSG/events.json","paper":"https://pith.science/paper/4QJ4REQ7"},"agent_actions":{"view_html":"https://pith.science/pith/4QJ4REQ7RCXTZ5DXWXARP2EXSG","download_json":"https://pith.science/pith/4QJ4REQ7RCXTZ5DXWXARP2EXSG.json","view_paper":"https://pith.science/paper/4QJ4REQ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.07886&json=true","fetch_graph":"https://pith.science/api/pith-number/4QJ4REQ7RCXTZ5DXWXARP2EXSG/graph.json","fetch_events":"https://pith.science/api/pith-number/4QJ4REQ7RCXTZ5DXWXARP2EXSG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4QJ4REQ7RCXTZ5DXWXARP2EXSG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4QJ4REQ7RCXTZ5DXWXARP2EXSG/action/storage_attestation","attest_author":"https://pith.science/pith/4QJ4REQ7RCXTZ5DXWXARP2EXSG/action/author_attestation","sign_citation":"https://pith.science/pith/4QJ4REQ7RCXTZ5DXWXARP2EXSG/action/citation_signature","submit_replication":"https://pith.science/pith/4QJ4REQ7RCXTZ5DXWXARP2EXSG/action/replication_record"}},"created_at":"2026-08-11T01:18:50.294125+00:00","updated_at":"2026-08-11T01:18:50.294125+00:00"}