{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:S4NMTYBNW4UCGSGO52X5ENSYTU","short_pith_number":"pith:S4NMTYBN","canonical_record":{"source":{"id":"2504.20199","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-28T19:02:18Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"dcd089e8f5c098ce2e8353ce04c3f53ded8bcfd42eea56534939df6f9652594d","abstract_canon_sha256":"59238d9913e89ed033634dd84597c2138a0feb17515fbc7a08f8d54ab0aac326"},"schema_version":"1.0"},"canonical_sha256":"971ac9e02db7282348ceeeafd236589d093e2fa37be4ebe05e25f95bb49718af","source":{"kind":"arxiv","id":"2504.20199","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.20199","created_at":"2026-07-05T10:55:38Z"},{"alias_kind":"arxiv_version","alias_value":"2504.20199v1","created_at":"2026-07-05T10:55:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.20199","created_at":"2026-07-05T10:55:38Z"},{"alias_kind":"pith_short_12","alias_value":"S4NMTYBNW4UC","created_at":"2026-07-05T10:55:38Z"},{"alias_kind":"pith_short_16","alias_value":"S4NMTYBNW4UCGSGO","created_at":"2026-07-05T10:55:38Z"},{"alias_kind":"pith_short_8","alias_value":"S4NMTYBN","created_at":"2026-07-05T10:55:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:S4NMTYBNW4UCGSGO52X5ENSYTU","target":"record","payload":{"canonical_record":{"source":{"id":"2504.20199","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-28T19:02:18Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"dcd089e8f5c098ce2e8353ce04c3f53ded8bcfd42eea56534939df6f9652594d","abstract_canon_sha256":"59238d9913e89ed033634dd84597c2138a0feb17515fbc7a08f8d54ab0aac326"},"schema_version":"1.0"},"canonical_sha256":"971ac9e02db7282348ceeeafd236589d093e2fa37be4ebe05e25f95bb49718af","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:55:38.249908Z","signature_b64":"8YUC56Rn7KdWGnXNUOzKwsd7hlJr3XaYX8/+4tK6/EbXBPht6+8OHa0zVyvcgrNQeLMafjMLjyTZ3DNt0uNvCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"971ac9e02db7282348ceeeafd236589d093e2fa37be4ebe05e25f95bb49718af","last_reissued_at":"2026-07-05T10:55:38.249446Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:55:38.249446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.20199","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":"2026-07-05T10:55:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ym5GkKzzkOzJDRVnATaJvWEgsCs5StD8DfuC7qIT4yD7v2Mg+G1OMlJNKx7F5O7Ci4C8Sx2xhrmHLldTngJ5Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T02:17:19.788925Z"},"content_sha256":"ffcdef3e361a9e83947faf17119100f250bb5e2e52fe58b79e39151a1216b7e6","schema_version":"1.0","event_id":"sha256:ffcdef3e361a9e83947faf17119100f250bb5e2e52fe58b79e39151a1216b7e6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:S4NMTYBNW4UCGSGO52X5ENSYTU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Weaving Context Across Images: Improving Vision-Language Models through Focus-Centric Visual Chains","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Chuanqi Cheng, Jian Luan, Juntian Zhang, Rui Yan, Wei Liu, Yuhan Liu","submitted_at":"2025-04-28T19:02:18Z","abstract_excerpt":"Vision-language models (VLMs) achieve remarkable success in single-image tasks. However, real-world scenarios often involve intricate multi-image inputs, leading to a notable performance decline as models struggle to disentangle critical information scattered across complex visual features. In this work, we propose Focus-Centric Visual Chain, a novel paradigm that enhances VLMs'perception, comprehension, and reasoning abilities in multi-image scenarios. To facilitate this paradigm, we propose Focus-Centric Data Synthesis, a scalable bottom-up approach for synthesizing high-quality data with el"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.20199","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/2504.20199/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":"2026-07-05T10:55:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u86HKoP3EcSTdzEI/BDnHQ3QUUoIekMk3oQvKPe5LjzasddRbt0poDXbsVzJJvw3JFZyuvDcpl0IxMZAllm1AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T02:17:19.789429Z"},"content_sha256":"b3f3f4ac990fcc1ef3d4c79a6d08ab6101051aef62de4350aa30be0f816a3de6","schema_version":"1.0","event_id":"sha256:b3f3f4ac990fcc1ef3d4c79a6d08ab6101051aef62de4350aa30be0f816a3de6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S4NMTYBNW4UCGSGO52X5ENSYTU/bundle.json","state_url":"https://pith.science/pith/S4NMTYBNW4UCGSGO52X5ENSYTU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S4NMTYBNW4UCGSGO52X5ENSYTU/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":"2026-08-09T02:17:19Z","links":{"resolver":"https://pith.science/pith/S4NMTYBNW4UCGSGO52X5ENSYTU","bundle":"https://pith.science/pith/S4NMTYBNW4UCGSGO52X5ENSYTU/bundle.json","state":"https://pith.science/pith/S4NMTYBNW4UCGSGO52X5ENSYTU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S4NMTYBNW4UCGSGO52X5ENSYTU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:S4NMTYBNW4UCGSGO52X5ENSYTU","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":"59238d9913e89ed033634dd84597c2138a0feb17515fbc7a08f8d54ab0aac326","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-28T19:02:18Z","title_canon_sha256":"dcd089e8f5c098ce2e8353ce04c3f53ded8bcfd42eea56534939df6f9652594d"},"schema_version":"1.0","source":{"id":"2504.20199","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.20199","created_at":"2026-07-05T10:55:38Z"},{"alias_kind":"arxiv_version","alias_value":"2504.20199v1","created_at":"2026-07-05T10:55:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.20199","created_at":"2026-07-05T10:55:38Z"},{"alias_kind":"pith_short_12","alias_value":"S4NMTYBNW4UC","created_at":"2026-07-05T10:55:38Z"},{"alias_kind":"pith_short_16","alias_value":"S4NMTYBNW4UCGSGO","created_at":"2026-07-05T10:55:38Z"},{"alias_kind":"pith_short_8","alias_value":"S4NMTYBN","created_at":"2026-07-05T10:55:38Z"}],"graph_snapshots":[{"event_id":"sha256:b3f3f4ac990fcc1ef3d4c79a6d08ab6101051aef62de4350aa30be0f816a3de6","target":"graph","created_at":"2026-07-05T10:55:38Z","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/2504.20199/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) achieve remarkable success in single-image tasks. However, real-world scenarios often involve intricate multi-image inputs, leading to a notable performance decline as models struggle to disentangle critical information scattered across complex visual features. In this work, we propose Focus-Centric Visual Chain, a novel paradigm that enhances VLMs'perception, comprehension, and reasoning abilities in multi-image scenarios. To facilitate this paradigm, we propose Focus-Centric Data Synthesis, a scalable bottom-up approach for synthesizing high-quality data with el","authors_text":"Chuanqi Cheng, Jian Luan, Juntian Zhang, Rui Yan, Wei Liu, Yuhan Liu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-28T19:02:18Z","title":"Weaving Context Across Images: Improving Vision-Language Models through Focus-Centric Visual Chains"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.20199","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:ffcdef3e361a9e83947faf17119100f250bb5e2e52fe58b79e39151a1216b7e6","target":"record","created_at":"2026-07-05T10:55:38Z","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":"59238d9913e89ed033634dd84597c2138a0feb17515fbc7a08f8d54ab0aac326","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-28T19:02:18Z","title_canon_sha256":"dcd089e8f5c098ce2e8353ce04c3f53ded8bcfd42eea56534939df6f9652594d"},"schema_version":"1.0","source":{"id":"2504.20199","kind":"arxiv","version":1}},"canonical_sha256":"971ac9e02db7282348ceeeafd236589d093e2fa37be4ebe05e25f95bb49718af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"971ac9e02db7282348ceeeafd236589d093e2fa37be4ebe05e25f95bb49718af","first_computed_at":"2026-07-05T10:55:38.249446Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:55:38.249446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8YUC56Rn7KdWGnXNUOzKwsd7hlJr3XaYX8/+4tK6/EbXBPht6+8OHa0zVyvcgrNQeLMafjMLjyTZ3DNt0uNvCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:55:38.249908Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.20199","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ffcdef3e361a9e83947faf17119100f250bb5e2e52fe58b79e39151a1216b7e6","sha256:b3f3f4ac990fcc1ef3d4c79a6d08ab6101051aef62de4350aa30be0f816a3de6"],"state_sha256":"600c5098389e659a8e63a5d2fa070123fb2167577055bd4795140364dc77ac27"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m1PDKuvdrqwaPAu9WTEGNF/sByaVzNuc8jIIvdQQFzJWwT5BkjdLZ+XvnGiLWu1c0qNVX7YyqfExLF5XUW3pBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T02:17:19.793826Z","bundle_sha256":"b6e552a0442d831241c1ca812bf1ffb195b8ca39a57b71a994e49030e1490b38"}}