{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FWZSGL5ZSMVLAG72PWK4RBXKBB","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":"0647c58bd0b4b10f83c4e81dce49adcb26f71a1faa3c9a209ea602b81d5ac30b","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T06:21:33Z","title_canon_sha256":"95abf542b51a0a190867ac697eeef473919ffaf173d5797d143475fb14c4d95c"},"schema_version":"1.0","source":{"id":"2412.08125","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.08125","created_at":"2026-07-05T09:51:39Z"},{"alias_kind":"arxiv_version","alias_value":"2412.08125v2","created_at":"2026-07-05T09:51:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08125","created_at":"2026-07-05T09:51:39Z"},{"alias_kind":"pith_short_12","alias_value":"FWZSGL5ZSMVL","created_at":"2026-07-05T09:51:39Z"},{"alias_kind":"pith_short_16","alias_value":"FWZSGL5ZSMVLAG72","created_at":"2026-07-05T09:51:39Z"},{"alias_kind":"pith_short_8","alias_value":"FWZSGL5Z","created_at":"2026-07-05T09:51:39Z"}],"graph_snapshots":[{"event_id":"sha256:3ee13252cf44bb350a2f26f12a94df71153ec02938fa385722952445ba8a590f","target":"graph","created_at":"2026-07-05T09:51:39Z","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/2412.08125/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing Large Vision-Language Models (LVLMs) excel at matching concepts across multi-modal inputs but struggle with compositional concepts and high-level relationships between entities. This paper introduces Progressive multi-granular Vision-Language alignments (PromViL), a novel framework to enhance LVLMs' ability in performing grounded compositional visual reasoning tasks. Our approach constructs a hierarchical structure of multi-modal alignments, ranging from simple to complex concepts. By progressively aligning textual descriptions with corresponding visual regions, our model learns to le","authors_text":"Long Hoang Dang, Ngan Le, Quang-Hung Le, Thao Minh Le, Truyen Tran","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T06:21:33Z","title":"Progressive Multi-granular Alignments for Grounded Reasoning in Large Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08125","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:f9620fd664747b2e26758e39d2ea575a3c51f602e2202e3aeb063bd099999bba","target":"record","created_at":"2026-07-05T09:51:39Z","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":"0647c58bd0b4b10f83c4e81dce49adcb26f71a1faa3c9a209ea602b81d5ac30b","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T06:21:33Z","title_canon_sha256":"95abf542b51a0a190867ac697eeef473919ffaf173d5797d143475fb14c4d95c"},"schema_version":"1.0","source":{"id":"2412.08125","kind":"arxiv","version":2}},"canonical_sha256":"2db3232fb9932ab01bfa7d95c886ea0848aa866be694eec3034cd99243270ea6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2db3232fb9932ab01bfa7d95c886ea0848aa866be694eec3034cd99243270ea6","first_computed_at":"2026-07-05T09:51:39.512813Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:51:39.512813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VTHwcqdTA60w7zTvSI12x7+NJAZdg+1jIhZsDUycg/xODwQIl3ZX4J8wc3cvgtYVft1NrPVooFRrfMay8Ar6AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:51:39.513247Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.08125","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f9620fd664747b2e26758e39d2ea575a3c51f602e2202e3aeb063bd099999bba","sha256:3ee13252cf44bb350a2f26f12a94df71153ec02938fa385722952445ba8a590f"],"state_sha256":"67ca8c1f82e508625d920b249cc98d88d27b2446a275899e87bc21636c06d247"}