{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EB2YPQINTQJX3BNPMGSJNHGFBQ","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":"316848347a45262d38ade6820dbc288001d2c511dcfa594cc8f059076548afba","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T17:54:27Z","title_canon_sha256":"118e18906f7df8c3bee8ec917f409343f973195af9c5c873d499da89a2759f6e"},"schema_version":"1.0","source":{"id":"2412.04378","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.04378","created_at":"2026-07-05T11:00:25Z"},{"alias_kind":"arxiv_version","alias_value":"2412.04378v3","created_at":"2026-07-05T11:00:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04378","created_at":"2026-07-05T11:00:25Z"},{"alias_kind":"pith_short_12","alias_value":"EB2YPQINTQJX","created_at":"2026-07-05T11:00:25Z"},{"alias_kind":"pith_short_16","alias_value":"EB2YPQINTQJX3BNP","created_at":"2026-07-05T11:00:25Z"},{"alias_kind":"pith_short_8","alias_value":"EB2YPQIN","created_at":"2026-07-05T11:00:25Z"}],"graph_snapshots":[{"event_id":"sha256:292cc2098898ae8dc36a56c1c596a14d9fc75329f8a481c2e25dba0a8ce15859","target":"graph","created_at":"2026-07-05T11:00:25Z","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/2412.04378/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastively-trained Vision-Language Models (VLMs) like CLIP have become the de facto approach for discriminative vision-language representation learning. However, these models have limited language understanding, often exhibiting a \"bag of words\" behavior. At the same time, Large Vision-Language Models (LVLMs), which combine vision encoders with LLMs, have been shown to be capable of detailed vision-language reasoning, yet their autoregressive nature renders them less suitable for discriminative tasks.\n  In this work, we propose to combine \"the best of both worlds\": a new training approach f","authors_text":"Adrian Bulat, Alexandros Xenos, Anestis Zaganidis, Brais Martinez, Georgios Tzimiropoulos, Ioannis Maniadis Metaxas, Yassine Ouali","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T17:54:27Z","title":"VladVA: Discriminative Fine-tuning of LVLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04378","kind":"arxiv","version":3},"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":"sha256:1ed9f2716d722bbadf417312735e4a50ed0328aed708472485924bb7d8d1127a","target":"record","created_at":"2026-07-05T11:00:25Z","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":"316848347a45262d38ade6820dbc288001d2c511dcfa594cc8f059076548afba","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T17:54:27Z","title_canon_sha256":"118e18906f7df8c3bee8ec917f409343f973195af9c5c873d499da89a2759f6e"},"schema_version":"1.0","source":{"id":"2412.04378","kind":"arxiv","version":3}},"canonical_sha256":"207587c10d9c137d85af61a4969cc50c048af5e258f9b793dc72fd9bda61607b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"207587c10d9c137d85af61a4969cc50c048af5e258f9b793dc72fd9bda61607b","first_computed_at":"2026-07-05T11:00:25.645778Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:00:25.645778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xuZyGxc7gk0cbyjkocB551mr9hpysLGyKf44hONbjtGZEnhJOuztDOAiBF7tnDha8TMsnPI/KDKBEDH0pgG8DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:00:25.646330Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.04378","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ed9f2716d722bbadf417312735e4a50ed0328aed708472485924bb7d8d1127a","sha256:292cc2098898ae8dc36a56c1c596a14d9fc75329f8a481c2e25dba0a8ce15859"],"state_sha256":"2227adce7e999b8db994c998696e5abed4017bda1126d4beb7945d090a04f1d8"}