{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7CKV3UHJOHKSX2XI4FZISJX7T4","short_pith_number":"pith:7CKV3UHJ","canonical_record":{"source":{"id":"2502.10250","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-14T15:59:33Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"2e55dad38553cf21adf772102d86b2567a149f748cd324928d5f5832241ca45c","abstract_canon_sha256":"9f5497f8bdc45bcab15d21fa732978bac8e5ae6dcc65430a2713394f43b2a922"},"schema_version":"1.0"},"canonical_sha256":"f8955dd0e971d52beae8e1728926ff9f36ddf2f2fe64a7d1024432505c1db93e","source":{"kind":"arxiv","id":"2502.10250","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.10250","created_at":"2026-07-05T10:18:50Z"},{"alias_kind":"arxiv_version","alias_value":"2502.10250v2","created_at":"2026-07-05T10:18:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10250","created_at":"2026-07-05T10:18:50Z"},{"alias_kind":"pith_short_12","alias_value":"7CKV3UHJOHKS","created_at":"2026-07-05T10:18:50Z"},{"alias_kind":"pith_short_16","alias_value":"7CKV3UHJOHKSX2XI","created_at":"2026-07-05T10:18:50Z"},{"alias_kind":"pith_short_8","alias_value":"7CKV3UHJ","created_at":"2026-07-05T10:18:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7CKV3UHJOHKSX2XI4FZISJX7T4","target":"record","payload":{"canonical_record":{"source":{"id":"2502.10250","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-14T15:59:33Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"2e55dad38553cf21adf772102d86b2567a149f748cd324928d5f5832241ca45c","abstract_canon_sha256":"9f5497f8bdc45bcab15d21fa732978bac8e5ae6dcc65430a2713394f43b2a922"},"schema_version":"1.0"},"canonical_sha256":"f8955dd0e971d52beae8e1728926ff9f36ddf2f2fe64a7d1024432505c1db93e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:50.582426Z","signature_b64":"Dn5f+4F1dn9e6BlkL498JAjhb26efs51BFF8i7rtad+ijsWGK6+Ya5yYyQqZa1OYKlUJx0hrANNqBp2h4G5WBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8955dd0e971d52beae8e1728926ff9f36ddf2f2fe64a7d1024432505c1db93e","last_reissued_at":"2026-07-05T10:18:50.581916Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:50.581916Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.10250","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:18:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hyJNNN2hi3t+mpWic0szYZbjahrwivv388TUibzi00tt6EfIJtAXMyMEoORjHZEx+eYBHaL873E6QQNB8cjaDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T00:32:32.279415Z"},"content_sha256":"9e555efafc59a8caed0d16e13f292bcaa5cff1d0fb6b4b236a7cc1ae5a220eae","schema_version":"1.0","event_id":"sha256:9e555efafc59a8caed0d16e13f292bcaa5cff1d0fb6b4b236a7cc1ae5a220eae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7CKV3UHJOHKSX2XI4FZISJX7T4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VisCon-100K: Leveraging Contextual Web Data for Fine-tuning Vision Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Gokul Karthik Kumar, Iheb Chaabane, Kebin Wu","submitted_at":"2025-02-14T15:59:33Z","abstract_excerpt":"Vision-language models (VLMs) excel in various visual benchmarks but are often constrained by the lack of high-quality visual fine-tuning data. To address this challenge, we introduce VisCon-100K, a novel dataset derived from interleaved image-text web documents. Our approach transforms 45K web documents from the OBELICS dataset into 100K image conversation samples. We utilize GPT-4V to generate image-contextual captions and OpenChat 3.5 model to convert these captions into diverse free-form and multiple-choice question-answer pairs. Integrating this dataset for fine-tuning considerably enhanc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10250","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/2502.10250/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":"2026-07-05T10:18:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+nVjG6ddNlAgoYEY4m+F4PpoaTN90OtouZAOieZ/kjX8v+ghhIPW5J5k0WUMHnOzg25d3i92cuc/z29pHPhJCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T00:32:32.280001Z"},"content_sha256":"9686c37fed0acb29d480f753acde70438527a3a5ec6230830ae8f3ef96f2ee04","schema_version":"1.0","event_id":"sha256:9686c37fed0acb29d480f753acde70438527a3a5ec6230830ae8f3ef96f2ee04"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7CKV3UHJOHKSX2XI4FZISJX7T4/bundle.json","state_url":"https://pith.science/pith/7CKV3UHJOHKSX2XI4FZISJX7T4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7CKV3UHJOHKSX2XI4FZISJX7T4/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":"2026-08-18T00:32:32Z","links":{"resolver":"https://pith.science/pith/7CKV3UHJOHKSX2XI4FZISJX7T4","bundle":"https://pith.science/pith/7CKV3UHJOHKSX2XI4FZISJX7T4/bundle.json","state":"https://pith.science/pith/7CKV3UHJOHKSX2XI4FZISJX7T4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7CKV3UHJOHKSX2XI4FZISJX7T4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7CKV3UHJOHKSX2XI4FZISJX7T4","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":"9f5497f8bdc45bcab15d21fa732978bac8e5ae6dcc65430a2713394f43b2a922","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-14T15:59:33Z","title_canon_sha256":"2e55dad38553cf21adf772102d86b2567a149f748cd324928d5f5832241ca45c"},"schema_version":"1.0","source":{"id":"2502.10250","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.10250","created_at":"2026-07-05T10:18:50Z"},{"alias_kind":"arxiv_version","alias_value":"2502.10250v2","created_at":"2026-07-05T10:18:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10250","created_at":"2026-07-05T10:18:50Z"},{"alias_kind":"pith_short_12","alias_value":"7CKV3UHJOHKS","created_at":"2026-07-05T10:18:50Z"},{"alias_kind":"pith_short_16","alias_value":"7CKV3UHJOHKSX2XI","created_at":"2026-07-05T10:18:50Z"},{"alias_kind":"pith_short_8","alias_value":"7CKV3UHJ","created_at":"2026-07-05T10:18:50Z"}],"graph_snapshots":[{"event_id":"sha256:9686c37fed0acb29d480f753acde70438527a3a5ec6230830ae8f3ef96f2ee04","target":"graph","created_at":"2026-07-05T10:18:50Z","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/2502.10250/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) excel in various visual benchmarks but are often constrained by the lack of high-quality visual fine-tuning data. To address this challenge, we introduce VisCon-100K, a novel dataset derived from interleaved image-text web documents. Our approach transforms 45K web documents from the OBELICS dataset into 100K image conversation samples. We utilize GPT-4V to generate image-contextual captions and OpenChat 3.5 model to convert these captions into diverse free-form and multiple-choice question-answer pairs. Integrating this dataset for fine-tuning considerably enhanc","authors_text":"Gokul Karthik Kumar, Iheb Chaabane, Kebin Wu","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-14T15:59:33Z","title":"VisCon-100K: Leveraging Contextual Web Data for Fine-tuning Vision Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10250","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":"sha256:9e555efafc59a8caed0d16e13f292bcaa5cff1d0fb6b4b236a7cc1ae5a220eae","target":"record","created_at":"2026-07-05T10:18:50Z","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":"9f5497f8bdc45bcab15d21fa732978bac8e5ae6dcc65430a2713394f43b2a922","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-14T15:59:33Z","title_canon_sha256":"2e55dad38553cf21adf772102d86b2567a149f748cd324928d5f5832241ca45c"},"schema_version":"1.0","source":{"id":"2502.10250","kind":"arxiv","version":2}},"canonical_sha256":"f8955dd0e971d52beae8e1728926ff9f36ddf2f2fe64a7d1024432505c1db93e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8955dd0e971d52beae8e1728926ff9f36ddf2f2fe64a7d1024432505c1db93e","first_computed_at":"2026-07-05T10:18:50.581916Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:18:50.581916Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Dn5f+4F1dn9e6BlkL498JAjhb26efs51BFF8i7rtad+ijsWGK6+Ya5yYyQqZa1OYKlUJx0hrANNqBp2h4G5WBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:18:50.582426Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.10250","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9e555efafc59a8caed0d16e13f292bcaa5cff1d0fb6b4b236a7cc1ae5a220eae","sha256:9686c37fed0acb29d480f753acde70438527a3a5ec6230830ae8f3ef96f2ee04"],"state_sha256":"2f3ecbca071929109be012ca09f8510ae636411e5531c0a070632c4be7b55a82"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"idrxJ3NwGghZ4mBPofzdu6EmscePbhpcGbBwS3IBXGhTU2gwEbtC3klrq63BBY8ovnEDuZGb+P2lKO0xDVrPDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T00:32:32.284315Z","bundle_sha256":"b1241732e55735f44eff56ad031e3cefbc4f29df4c2cd6c60022bbfebdac3f1d"}}