{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GYSVCYMYHIE5GA5E6TKBAD3J2M","short_pith_number":"pith:GYSVCYMY","canonical_record":{"source":{"id":"2502.14834","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-20T18:47:36Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"1c891d7ff4558b3c7833b4b22dacf676655f70fbb7d2c28025e4fb629e4fd624","abstract_canon_sha256":"5119418dbfe062d695ebcb2150fc5272768c37f125a6931702e9a6e40d9ac272"},"schema_version":"1.0"},"canonical_sha256":"36255161983a09d303a4f4d4100f69d33e490ed81602fdbd78da13c299bd9bea","source":{"kind":"arxiv","id":"2502.14834","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14834","created_at":"2026-07-05T10:17:33Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14834v1","created_at":"2026-07-05T10:17:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14834","created_at":"2026-07-05T10:17:33Z"},{"alias_kind":"pith_short_12","alias_value":"GYSVCYMYHIE5","created_at":"2026-07-05T10:17:33Z"},{"alias_kind":"pith_short_16","alias_value":"GYSVCYMYHIE5GA5E","created_at":"2026-07-05T10:17:33Z"},{"alias_kind":"pith_short_8","alias_value":"GYSVCYMY","created_at":"2026-07-05T10:17:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GYSVCYMYHIE5GA5E6TKBAD3J2M","target":"record","payload":{"canonical_record":{"source":{"id":"2502.14834","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-20T18:47:36Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"1c891d7ff4558b3c7833b4b22dacf676655f70fbb7d2c28025e4fb629e4fd624","abstract_canon_sha256":"5119418dbfe062d695ebcb2150fc5272768c37f125a6931702e9a6e40d9ac272"},"schema_version":"1.0"},"canonical_sha256":"36255161983a09d303a4f4d4100f69d33e490ed81602fdbd78da13c299bd9bea","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:33.269311Z","signature_b64":"CEUWMbfSeIetKHu+xvdC3RqWByyyMutaUUPH3FXwf9TjJdB+fZcsWQNk5MV3QRIuwQIlXiwdJeCj1hus4yhmCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36255161983a09d303a4f4d4100f69d33e490ed81602fdbd78da13c299bd9bea","last_reissued_at":"2026-07-05T10:17:33.268778Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:33.268778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.14834","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":"2026-07-05T10:17:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"66Q4d27QD/YeKEjMaCqZyuSCqN6Hma9cKOvDF+wVxEKRjk8IsFMP/C/Nm2X/QMuBj6GNfU/qAMbdsZu+tHw3AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T12:25:17.667496Z"},"content_sha256":"7cb63bba772de2eff6ac42805b832900f231615b34326febf6c05748441e620e","schema_version":"1.0","event_id":"sha256:7cb63bba772de2eff6ac42805b832900f231615b34326febf6c05748441e620e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GYSVCYMYHIE5GA5E6TKBAD3J2M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LongWriter-V: Enabling Ultra-Long and High-Fidelity Generation in Vision-Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Bin Xu, Daniel Zhang-Li, Huiqin Liu, Jifan Yu, Juanzi Li, Lei Hou, Shangqing Tu, Yucheng Wang, Yuhao Wu, Yushi Bai, Zhiyuan Liu","submitted_at":"2025-02-20T18:47:36Z","abstract_excerpt":"Existing Large Vision-Language Models (LVLMs) can process inputs with context lengths up to 128k visual and text tokens, yet they struggle to generate coherent outputs beyond 1,000 words. We find that the primary limitation is the absence of long output examples during supervised fine-tuning (SFT). To tackle this issue, we introduce LongWriter-V-22k, a SFT dataset comprising 22,158 examples, each with multiple input images, an instruction, and corresponding outputs ranging from 0 to 10,000 words. Moreover, to achieve long outputs that maintain high-fidelity to the input images, we employ Direc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14834","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/2502.14834/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":"2026-07-05T10:17:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vrkT0oixEEhphFb1UOtDMsLur0OMsytph+cfAA+Rb4zypSroHn/U7to0BFb4zj98ucQ9Ke6DXSrfz9rS+ImHBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T12:25:17.667868Z"},"content_sha256":"18f3230ca0332c3e61bf68c07b4702062768f096ac9714401a88e12b9584c116","schema_version":"1.0","event_id":"sha256:18f3230ca0332c3e61bf68c07b4702062768f096ac9714401a88e12b9584c116"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GYSVCYMYHIE5GA5E6TKBAD3J2M/bundle.json","state_url":"https://pith.science/pith/GYSVCYMYHIE5GA5E6TKBAD3J2M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GYSVCYMYHIE5GA5E6TKBAD3J2M/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":"2026-07-06T12:25:17Z","links":{"resolver":"https://pith.science/pith/GYSVCYMYHIE5GA5E6TKBAD3J2M","bundle":"https://pith.science/pith/GYSVCYMYHIE5GA5E6TKBAD3J2M/bundle.json","state":"https://pith.science/pith/GYSVCYMYHIE5GA5E6TKBAD3J2M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GYSVCYMYHIE5GA5E6TKBAD3J2M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GYSVCYMYHIE5GA5E6TKBAD3J2M","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":"5119418dbfe062d695ebcb2150fc5272768c37f125a6931702e9a6e40d9ac272","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-20T18:47:36Z","title_canon_sha256":"1c891d7ff4558b3c7833b4b22dacf676655f70fbb7d2c28025e4fb629e4fd624"},"schema_version":"1.0","source":{"id":"2502.14834","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14834","created_at":"2026-07-05T10:17:33Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14834v1","created_at":"2026-07-05T10:17:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14834","created_at":"2026-07-05T10:17:33Z"},{"alias_kind":"pith_short_12","alias_value":"GYSVCYMYHIE5","created_at":"2026-07-05T10:17:33Z"},{"alias_kind":"pith_short_16","alias_value":"GYSVCYMYHIE5GA5E","created_at":"2026-07-05T10:17:33Z"},{"alias_kind":"pith_short_8","alias_value":"GYSVCYMY","created_at":"2026-07-05T10:17:33Z"}],"graph_snapshots":[{"event_id":"sha256:18f3230ca0332c3e61bf68c07b4702062768f096ac9714401a88e12b9584c116","target":"graph","created_at":"2026-07-05T10:17:33Z","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/2502.14834/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing Large Vision-Language Models (LVLMs) can process inputs with context lengths up to 128k visual and text tokens, yet they struggle to generate coherent outputs beyond 1,000 words. We find that the primary limitation is the absence of long output examples during supervised fine-tuning (SFT). To tackle this issue, we introduce LongWriter-V-22k, a SFT dataset comprising 22,158 examples, each with multiple input images, an instruction, and corresponding outputs ranging from 0 to 10,000 words. Moreover, to achieve long outputs that maintain high-fidelity to the input images, we employ Direc","authors_text":"Bin Xu, Daniel Zhang-Li, Huiqin Liu, Jifan Yu, Juanzi Li, Lei Hou, Shangqing Tu, Yucheng Wang, Yuhao Wu, Yushi Bai, Zhiyuan Liu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-20T18:47:36Z","title":"LongWriter-V: Enabling Ultra-Long and High-Fidelity Generation in Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14834","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":"sha256:7cb63bba772de2eff6ac42805b832900f231615b34326febf6c05748441e620e","target":"record","created_at":"2026-07-05T10:17:33Z","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":"5119418dbfe062d695ebcb2150fc5272768c37f125a6931702e9a6e40d9ac272","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-20T18:47:36Z","title_canon_sha256":"1c891d7ff4558b3c7833b4b22dacf676655f70fbb7d2c28025e4fb629e4fd624"},"schema_version":"1.0","source":{"id":"2502.14834","kind":"arxiv","version":1}},"canonical_sha256":"36255161983a09d303a4f4d4100f69d33e490ed81602fdbd78da13c299bd9bea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"36255161983a09d303a4f4d4100f69d33e490ed81602fdbd78da13c299bd9bea","first_computed_at":"2026-07-05T10:17:33.268778Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:17:33.268778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CEUWMbfSeIetKHu+xvdC3RqWByyyMutaUUPH3FXwf9TjJdB+fZcsWQNk5MV3QRIuwQIlXiwdJeCj1hus4yhmCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:17:33.269311Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.14834","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7cb63bba772de2eff6ac42805b832900f231615b34326febf6c05748441e620e","sha256:18f3230ca0332c3e61bf68c07b4702062768f096ac9714401a88e12b9584c116"],"state_sha256":"ccc4e10673ef5a5b8eace311b2d6795481bd0c90f758d66a4dab97f9e0dc66a8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZFB3sPBVDpm2xHzzzhj5a7wtHwWE4MWH4MlJyJzF2ZaJ+oRVi8QaTw88g4G5AEvsVdFHeWh1KSWe3rcuoIkKDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T12:25:17.669818Z","bundle_sha256":"6dd09010cafcda5ecf43fb7ab3e0ac277a2383b86e9cfdd6906d28585d0d2030"}}