{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:JBXQCPCPQGAR5WUOQNLHU42XYL","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":"0d0690829ad802be0653046fcf58cc50c394e2f73cd1cf3c5c5ee7fb3edc34d6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-27T18:55:32Z","title_canon_sha256":"be923f2e2ff6bec03dacd16e3b9fd57c7e89081cce76bf8bdaa45587854b22ca"},"schema_version":"1.0","source":{"id":"1903.11649","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.11649","created_at":"2026-07-05T00:11:57Z"},{"alias_kind":"arxiv_version","alias_value":"1903.11649v2","created_at":"2026-07-05T00:11:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.11649","created_at":"2026-07-05T00:11:57Z"},{"alias_kind":"pith_short_12","alias_value":"JBXQCPCPQGAR","created_at":"2026-07-05T00:11:57Z"},{"alias_kind":"pith_short_16","alias_value":"JBXQCPCPQGAR5WUO","created_at":"2026-07-05T00:11:57Z"},{"alias_kind":"pith_short_8","alias_value":"JBXQCPCP","created_at":"2026-07-05T00:11:57Z"}],"graph_snapshots":[{"event_id":"sha256:c37c4d1b24589154657fe7428c93501df815c193c102fc3c0741f9672c9c3b4e","target":"graph","created_at":"2026-07-05T00:11:57Z","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/1903.11649/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We address the problem of grounding free-form textual phrases by using weak supervision from image-caption pairs. We propose a novel end-to-end model that uses caption-to-image retrieval as a `downstream' task to guide the process of phrase localization. Our method, as a first step, infers the latent correspondences between regions-of-interest (RoIs) and phrases in the caption and creates a discriminative image representation using these matched RoIs. In a subsequent step, this (learned) representation is aligned with the caption. Our key contribution lies in building this `caption-conditioned","authors_text":"Ajay Divakaran, Anirban Roy, Devi Parikh, Karan Sikka, Karuna Ahuja, Samyak Datta","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-27T18:55:32Z","title":"Align2Ground: Weakly Supervised Phrase Grounding Guided by Image-Caption Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.11649","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":"sha256:2fa643099c2e17a7d1f219705771e6ad5ef9fa4597f742e9981b77f7e79d903b","target":"record","created_at":"2026-07-05T00:11:57Z","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":"0d0690829ad802be0653046fcf58cc50c394e2f73cd1cf3c5c5ee7fb3edc34d6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-27T18:55:32Z","title_canon_sha256":"be923f2e2ff6bec03dacd16e3b9fd57c7e89081cce76bf8bdaa45587854b22ca"},"schema_version":"1.0","source":{"id":"1903.11649","kind":"arxiv","version":2}},"canonical_sha256":"486f013c4f81811eda8e83567a7357c2d1b5776789cda3940936506b4fdd9524","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"486f013c4f81811eda8e83567a7357c2d1b5776789cda3940936506b4fdd9524","first_computed_at":"2026-07-05T00:11:57.775532Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:11:57.775532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w6aLUqPH/GmxkDiZP6m4ltG31tq2A1xC9r5UlHZRwInUlxNFXAUOp06FSO61ea+Gq/yjk7ujM/vYMdjAnr32BA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:11:57.776023Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.11649","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2fa643099c2e17a7d1f219705771e6ad5ef9fa4597f742e9981b77f7e79d903b","sha256:c37c4d1b24589154657fe7428c93501df815c193c102fc3c0741f9672c9c3b4e"],"state_sha256":"18a0ca6899801c2ee037cb5e45e87e8b626ef4fc33764069ba2d8c30fb31b275"}