{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EB2YPQINTQJX3BNPMGSJNHGFBQ","short_pith_number":"pith:EB2YPQIN","canonical_record":{"source":{"id":"2412.04378","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T17:54:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"118e18906f7df8c3bee8ec917f409343f973195af9c5c873d499da89a2759f6e","abstract_canon_sha256":"316848347a45262d38ade6820dbc288001d2c511dcfa594cc8f059076548afba"},"schema_version":"1.0"},"canonical_sha256":"207587c10d9c137d85af61a4969cc50c048af5e258f9b793dc72fd9bda61607b","source":{"kind":"arxiv","id":"2412.04378","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EB2YPQINTQJX3BNPMGSJNHGFBQ","target":"record","payload":{"canonical_record":{"source":{"id":"2412.04378","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T17:54:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"118e18906f7df8c3bee8ec917f409343f973195af9c5c873d499da89a2759f6e","abstract_canon_sha256":"316848347a45262d38ade6820dbc288001d2c511dcfa594cc8f059076548afba"},"schema_version":"1.0"},"canonical_sha256":"207587c10d9c137d85af61a4969cc50c048af5e258f9b793dc72fd9bda61607b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:00:25.646330Z","signature_b64":"xuZyGxc7gk0cbyjkocB551mr9hpysLGyKf44hONbjtGZEnhJOuztDOAiBF7tnDha8TMsnPI/KDKBEDH0pgG8DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"207587c10d9c137d85af61a4969cc50c048af5e258f9b793dc72fd9bda61607b","last_reissued_at":"2026-07-05T11:00:25.645778Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:00:25.645778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.04378","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:00:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pSVz+L7qEzamgCIUHNHdsGp/6l6OlkRT1FUIWuWSmr3yTZ57qfGbuhcNoETVicNbRGurxuu3GgNphkBb3qPDBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:32:43.466936Z"},"content_sha256":"1ed9f2716d722bbadf417312735e4a50ed0328aed708472485924bb7d8d1127a","schema_version":"1.0","event_id":"sha256:1ed9f2716d722bbadf417312735e4a50ed0328aed708472485924bb7d8d1127a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EB2YPQINTQJX3BNPMGSJNHGFBQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VladVA: Discriminative Fine-tuning of LVLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Adrian Bulat, Alexandros Xenos, Anestis Zaganidis, Brais Martinez, Georgios Tzimiropoulos, Ioannis Maniadis Metaxas, Yassine Ouali","submitted_at":"2024-12-05T17:54:27Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04378","kind":"arxiv","version":3},"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/2412.04378/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:00:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lndW/ogdXt32gxl4c9A8lts8bTawKM36mbomXwAfUyFf3W1yqyv4S3XZhneE7oyI1hpTj1bNUK/5f8BE/fmBCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:32:43.467516Z"},"content_sha256":"292cc2098898ae8dc36a56c1c596a14d9fc75329f8a481c2e25dba0a8ce15859","schema_version":"1.0","event_id":"sha256:292cc2098898ae8dc36a56c1c596a14d9fc75329f8a481c2e25dba0a8ce15859"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EB2YPQINTQJX3BNPMGSJNHGFBQ/bundle.json","state_url":"https://pith.science/pith/EB2YPQINTQJX3BNPMGSJNHGFBQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EB2YPQINTQJX3BNPMGSJNHGFBQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T11:32:43Z","links":{"resolver":"https://pith.science/pith/EB2YPQINTQJX3BNPMGSJNHGFBQ","bundle":"https://pith.science/pith/EB2YPQINTQJX3BNPMGSJNHGFBQ/bundle.json","state":"https://pith.science/pith/EB2YPQINTQJX3BNPMGSJNHGFBQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EB2YPQINTQJX3BNPMGSJNHGFBQ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pWexy4qewy7OiMzinMmYrM6mHSF16ZXpPBK/uSgY3DTLoMLf70+vlxSFjCcB8nfO1c3HPXGGNVW3KKozpuQnAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:32:43.472847Z","bundle_sha256":"7bf746a0fad858a45733807290edaa2739bd8c0f1faeecdccd8fac3085f834e0"}}