{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FWZSGL5ZSMVLAG72PWK4RBXKBB","short_pith_number":"pith:FWZSGL5Z","schema_version":"1.0","canonical_sha256":"2db3232fb9932ab01bfa7d95c886ea0848aa866be694eec3034cd99243270ea6","source":{"kind":"arxiv","id":"2412.08125","version":2},"attestation_state":"computed","paper":{"title":"Progressive Multi-granular Alignments for Grounded Reasoning in Large Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Long Hoang Dang, Ngan Le, Quang-Hung Le, Thao Minh Le, Truyen Tran","submitted_at":"2024-12-11T06:21:33Z","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"},"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":"2412.08125","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T06:21:33Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"95abf542b51a0a190867ac697eeef473919ffaf173d5797d143475fb14c4d95c","abstract_canon_sha256":"0647c58bd0b4b10f83c4e81dce49adcb26f71a1faa3c9a209ea602b81d5ac30b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:39.513247Z","signature_b64":"VTHwcqdTA60w7zTvSI12x7+NJAZdg+1jIhZsDUycg/xODwQIl3ZX4J8wc3cvgtYVft1NrPVooFRrfMay8Ar6AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2db3232fb9932ab01bfa7d95c886ea0848aa866be694eec3034cd99243270ea6","last_reissued_at":"2026-07-05T09:51:39.512813Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:39.512813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Progressive Multi-granular Alignments for Grounded Reasoning in Large Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Long Hoang Dang, Ngan Le, Quang-Hung Le, Thao Minh Le, Truyen Tran","submitted_at":"2024-12-11T06:21:33Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08125","kind":"arxiv","version":2},"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/2412.08125/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":"2412.08125","created_at":"2026-07-05T09:51:39.512869+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.08125v2","created_at":"2026-07-05T09:51:39.512869+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08125","created_at":"2026-07-05T09:51:39.512869+00:00"},{"alias_kind":"pith_short_12","alias_value":"FWZSGL5ZSMVL","created_at":"2026-07-05T09:51:39.512869+00:00"},{"alias_kind":"pith_short_16","alias_value":"FWZSGL5ZSMVLAG72","created_at":"2026-07-05T09:51:39.512869+00:00"},{"alias_kind":"pith_short_8","alias_value":"FWZSGL5Z","created_at":"2026-07-05T09:51:39.512869+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/FWZSGL5ZSMVLAG72PWK4RBXKBB","json":"https://pith.science/pith/FWZSGL5ZSMVLAG72PWK4RBXKBB.json","graph_json":"https://pith.science/api/pith-number/FWZSGL5ZSMVLAG72PWK4RBXKBB/graph.json","events_json":"https://pith.science/api/pith-number/FWZSGL5ZSMVLAG72PWK4RBXKBB/events.json","paper":"https://pith.science/paper/FWZSGL5Z"},"agent_actions":{"view_html":"https://pith.science/pith/FWZSGL5ZSMVLAG72PWK4RBXKBB","download_json":"https://pith.science/pith/FWZSGL5ZSMVLAG72PWK4RBXKBB.json","view_paper":"https://pith.science/paper/FWZSGL5Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.08125&json=true","fetch_graph":"https://pith.science/api/pith-number/FWZSGL5ZSMVLAG72PWK4RBXKBB/graph.json","fetch_events":"https://pith.science/api/pith-number/FWZSGL5ZSMVLAG72PWK4RBXKBB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FWZSGL5ZSMVLAG72PWK4RBXKBB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FWZSGL5ZSMVLAG72PWK4RBXKBB/action/storage_attestation","attest_author":"https://pith.science/pith/FWZSGL5ZSMVLAG72PWK4RBXKBB/action/author_attestation","sign_citation":"https://pith.science/pith/FWZSGL5ZSMVLAG72PWK4RBXKBB/action/citation_signature","submit_replication":"https://pith.science/pith/FWZSGL5ZSMVLAG72PWK4RBXKBB/action/replication_record"}},"created_at":"2026-07-05T09:51:39.512869+00:00","updated_at":"2026-07-05T09:51:39.512869+00:00"}