{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TNHMUXAXSV37XMEGJHECPU2PCC","short_pith_number":"pith:TNHMUXAX","canonical_record":{"source":{"id":"2412.12940","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T14:18:50Z","cross_cats_sorted":[],"title_canon_sha256":"82462bc30ec37baf533bc4c6f432181c20e5cf043293fef20e1daf09417ba1e9","abstract_canon_sha256":"b764b261547d6e14526cdbbef8b0277d018b3cfc902b901d6f931ee14d530039"},"schema_version":"1.0"},"canonical_sha256":"9b4eca5c179577fbb08649c827d34f10b6a3a3910281417f4309ee9008b4902f","source":{"kind":"arxiv","id":"2412.12940","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.12940","created_at":"2026-07-05T10:41:51Z"},{"alias_kind":"arxiv_version","alias_value":"2412.12940v1","created_at":"2026-07-05T10:41:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12940","created_at":"2026-07-05T10:41:51Z"},{"alias_kind":"pith_short_12","alias_value":"TNHMUXAXSV37","created_at":"2026-07-05T10:41:51Z"},{"alias_kind":"pith_short_16","alias_value":"TNHMUXAXSV37XMEG","created_at":"2026-07-05T10:41:51Z"},{"alias_kind":"pith_short_8","alias_value":"TNHMUXAX","created_at":"2026-07-05T10:41:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TNHMUXAXSV37XMEGJHECPU2PCC","target":"record","payload":{"canonical_record":{"source":{"id":"2412.12940","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T14:18:50Z","cross_cats_sorted":[],"title_canon_sha256":"82462bc30ec37baf533bc4c6f432181c20e5cf043293fef20e1daf09417ba1e9","abstract_canon_sha256":"b764b261547d6e14526cdbbef8b0277d018b3cfc902b901d6f931ee14d530039"},"schema_version":"1.0"},"canonical_sha256":"9b4eca5c179577fbb08649c827d34f10b6a3a3910281417f4309ee9008b4902f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:51.263994Z","signature_b64":"LUI5PrqoRoNl2NXtbMJlRGPC074JGkFkK4MwAUov4KhlNAwp6zUM/yQGlJW+VoTElHe2YC2Pt20v3DbiEYtKDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b4eca5c179577fbb08649c827d34f10b6a3a3910281417f4309ee9008b4902f","last_reissued_at":"2026-07-05T10:41:51.263542Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:51.263542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.12940","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:41:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bw+t4rETkUALDtiiN/3j3LamxgvH44QQbAQPK0QsJ9oCgw1eWTXvc+4lIdljRhAiNh59vCdTL2hQ2ABpT5ZMBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:51:14.266119Z"},"content_sha256":"90c232fcf575e33e146ae15dcb69d815cdafb433463f26267706eb474257ccf8","schema_version":"1.0","event_id":"sha256:90c232fcf575e33e146ae15dcb69d815cdafb433463f26267706eb474257ccf8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TNHMUXAXSV37XMEGJHECPU2PCC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Fine-grained Visual Understanding in VLMs through Text-Only Training","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dasol Choi, Gio Paik, Guijin Son, Seunghyeok Hong, Soo Yong Kim","submitted_at":"2024-12-17T14:18:50Z","abstract_excerpt":"Visual-Language Models (VLMs) have become a powerful tool for bridging the gap between visual and linguistic understanding. However, the conventional learning approaches for VLMs often suffer from limitations, such as the high resource requirements of collecting and training image-text paired data. Recent research has suggested that language understanding plays a crucial role in the performance of VLMs, potentially indicating that text-only training could be a viable approach. In this work, we investigate the feasibility of enhancing fine-grained visual understanding in VLMs through text-only "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12940","kind":"arxiv","version":1},"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/2412.12940/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":"2026-07-05T10:41:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yVy1lDAA3GzSNxbz96ioRXINxnv+UPMNxauiXd/u1NdB9Hn2VPknAZEx5II6JafOPNMf/wr+24lpiclk9STmBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:51:14.267129Z"},"content_sha256":"2f4fb72be6e522d8c32cd2e1fe83f0f64fff2953e4efacb2f92ae612993bd409","schema_version":"1.0","event_id":"sha256:2f4fb72be6e522d8c32cd2e1fe83f0f64fff2953e4efacb2f92ae612993bd409"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TNHMUXAXSV37XMEGJHECPU2PCC/bundle.json","state_url":"https://pith.science/pith/TNHMUXAXSV37XMEGJHECPU2PCC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TNHMUXAXSV37XMEGJHECPU2PCC/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":"2026-08-07T17:51:14Z","links":{"resolver":"https://pith.science/pith/TNHMUXAXSV37XMEGJHECPU2PCC","bundle":"https://pith.science/pith/TNHMUXAXSV37XMEGJHECPU2PCC/bundle.json","state":"https://pith.science/pith/TNHMUXAXSV37XMEGJHECPU2PCC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TNHMUXAXSV37XMEGJHECPU2PCC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TNHMUXAXSV37XMEGJHECPU2PCC","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":"b764b261547d6e14526cdbbef8b0277d018b3cfc902b901d6f931ee14d530039","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T14:18:50Z","title_canon_sha256":"82462bc30ec37baf533bc4c6f432181c20e5cf043293fef20e1daf09417ba1e9"},"schema_version":"1.0","source":{"id":"2412.12940","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.12940","created_at":"2026-07-05T10:41:51Z"},{"alias_kind":"arxiv_version","alias_value":"2412.12940v1","created_at":"2026-07-05T10:41:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12940","created_at":"2026-07-05T10:41:51Z"},{"alias_kind":"pith_short_12","alias_value":"TNHMUXAXSV37","created_at":"2026-07-05T10:41:51Z"},{"alias_kind":"pith_short_16","alias_value":"TNHMUXAXSV37XMEG","created_at":"2026-07-05T10:41:51Z"},{"alias_kind":"pith_short_8","alias_value":"TNHMUXAX","created_at":"2026-07-05T10:41:51Z"}],"graph_snapshots":[{"event_id":"sha256:2f4fb72be6e522d8c32cd2e1fe83f0f64fff2953e4efacb2f92ae612993bd409","target":"graph","created_at":"2026-07-05T10:41:51Z","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/2412.12940/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual-Language Models (VLMs) have become a powerful tool for bridging the gap between visual and linguistic understanding. However, the conventional learning approaches for VLMs often suffer from limitations, such as the high resource requirements of collecting and training image-text paired data. Recent research has suggested that language understanding plays a crucial role in the performance of VLMs, potentially indicating that text-only training could be a viable approach. In this work, we investigate the feasibility of enhancing fine-grained visual understanding in VLMs through text-only ","authors_text":"Dasol Choi, Gio Paik, Guijin Son, Seunghyeok Hong, Soo Yong Kim","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T14:18:50Z","title":"Improving Fine-grained Visual Understanding in VLMs through Text-Only Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12940","kind":"arxiv","version":1},"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":"sha256:90c232fcf575e33e146ae15dcb69d815cdafb433463f26267706eb474257ccf8","target":"record","created_at":"2026-07-05T10:41:51Z","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":"b764b261547d6e14526cdbbef8b0277d018b3cfc902b901d6f931ee14d530039","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T14:18:50Z","title_canon_sha256":"82462bc30ec37baf533bc4c6f432181c20e5cf043293fef20e1daf09417ba1e9"},"schema_version":"1.0","source":{"id":"2412.12940","kind":"arxiv","version":1}},"canonical_sha256":"9b4eca5c179577fbb08649c827d34f10b6a3a3910281417f4309ee9008b4902f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9b4eca5c179577fbb08649c827d34f10b6a3a3910281417f4309ee9008b4902f","first_computed_at":"2026-07-05T10:41:51.263542Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:41:51.263542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LUI5PrqoRoNl2NXtbMJlRGPC074JGkFkK4MwAUov4KhlNAwp6zUM/yQGlJW+VoTElHe2YC2Pt20v3DbiEYtKDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:41:51.263994Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.12940","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90c232fcf575e33e146ae15dcb69d815cdafb433463f26267706eb474257ccf8","sha256:2f4fb72be6e522d8c32cd2e1fe83f0f64fff2953e4efacb2f92ae612993bd409"],"state_sha256":"16e13a8e6e6629d410cb2963f7161d29518a4e0fc9fe671fe7c15e730c24e0a5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UEgnJRo+h7VNsG6Be3XVrSKAI0C7ZooT+dXdTb7JTUkh05HOYHoBx5LNDAEwZ3zDb3AQOplEbqV6FIm/dhPvAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T17:51:14.274762Z","bundle_sha256":"d642dc5762165e0be756d1a740c50f7b786577a28845c7cec82ada3fb7b2ab0f"}}