{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PHV67C645GFZLJFZEFEWRXFIFW","short_pith_number":"pith:PHV67C64","canonical_record":{"source":{"id":"2405.14295","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-23T08:15:49Z","cross_cats_sorted":[],"title_canon_sha256":"af232d658d3af2ae0478ffddfc76723351eb86ca92ec78d798873d47afb8f7bb","abstract_canon_sha256":"5a7164bc9eed80a38b7c37db66a3afc994c8c0d67ca704d570f9bad1e6a677f0"},"schema_version":"1.0"},"canonical_sha256":"79ebef8bdce98b95a4b9214968dca82d8ed67d89143b6bcab8e5d77282134793","source":{"kind":"arxiv","id":"2405.14295","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.14295","created_at":"2026-07-05T08:22:12Z"},{"alias_kind":"arxiv_version","alias_value":"2405.14295v1","created_at":"2026-07-05T08:22:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14295","created_at":"2026-07-05T08:22:12Z"},{"alias_kind":"pith_short_12","alias_value":"PHV67C645GFZ","created_at":"2026-07-05T08:22:12Z"},{"alias_kind":"pith_short_16","alias_value":"PHV67C645GFZLJFZ","created_at":"2026-07-05T08:22:12Z"},{"alias_kind":"pith_short_8","alias_value":"PHV67C64","created_at":"2026-07-05T08:22:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PHV67C645GFZLJFZEFEWRXFIFW","target":"record","payload":{"canonical_record":{"source":{"id":"2405.14295","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-23T08:15:49Z","cross_cats_sorted":[],"title_canon_sha256":"af232d658d3af2ae0478ffddfc76723351eb86ca92ec78d798873d47afb8f7bb","abstract_canon_sha256":"5a7164bc9eed80a38b7c37db66a3afc994c8c0d67ca704d570f9bad1e6a677f0"},"schema_version":"1.0"},"canonical_sha256":"79ebef8bdce98b95a4b9214968dca82d8ed67d89143b6bcab8e5d77282134793","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:12.554098Z","signature_b64":"JtCaoc24IoVhmrHd9+yqFs80yibLv38yW0U1SiD8Ad82oavMCj5i0YESu/3k4mmot/rMTSAwPFJzmGh+GJjUCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79ebef8bdce98b95a4b9214968dca82d8ed67d89143b6bcab8e5d77282134793","last_reissued_at":"2026-07-05T08:22:12.553589Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:12.553589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.14295","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":"2026-07-05T08:22:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/QfdKquT9AqSec1VoLEAqB9v/t635nYnBoO9vQIfTu4TRPaMFC8HpiQUo2hEbgQmFz4kIGBq+F8YSMxriDnIBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T13:46:35.213796Z"},"content_sha256":"ffd03b91fa088689c1b32c8dcda7e751b660ca60e77fecc518cb2fa9719f2d48","schema_version":"1.0","event_id":"sha256:ffd03b91fa088689c1b32c8dcda7e751b660ca60e77fecc518cb2fa9719f2d48"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PHV67C645GFZLJFZEFEWRXFIFW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Focus Anywhere for Fine-grained Multi-page Document Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenglong Liu, Chunrui Han, Haoran Wei, Jianjian Sun, Jinyue Chen, Liang Zhao, Lingyu Kong, Xiangyu Zhang, Zheng Ge, Zining Zhu","submitted_at":"2024-05-23T08:15:49Z","abstract_excerpt":"Modern LVLMs still struggle to achieve fine-grained document understanding, such as OCR/translation/caption for regions of interest to the user, tasks that require the context of the entire page, or even multiple pages. Accordingly, this paper proposes Fox, an effective pipeline, hybrid data, and tuning strategy, that catalyzes LVLMs to focus anywhere on single/multi-page documents. We introduce a novel task to boost the document understanding by making LVLMs focus attention on the document-level region, such as redefining full-page OCR as foreground focus. We employ multiple vision vocabulari"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14295","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/2405.14295/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":"2026-07-05T08:22:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vt4jFETje7IgTGWgwZ/uiq0eiAnysa09xE67ver7md0cZn17uc0v0xJWdB4HmRPtecvgYgnM63ELRg2S9L1wAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T13:46:35.214167Z"},"content_sha256":"866412f03cc680f070bf93acc54c345f0ef5d3f57e501ac31d94cbaa68a1456a","schema_version":"1.0","event_id":"sha256:866412f03cc680f070bf93acc54c345f0ef5d3f57e501ac31d94cbaa68a1456a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PHV67C645GFZLJFZEFEWRXFIFW/bundle.json","state_url":"https://pith.science/pith/PHV67C645GFZLJFZEFEWRXFIFW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PHV67C645GFZLJFZEFEWRXFIFW/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":"2026-07-10T13:46:35Z","links":{"resolver":"https://pith.science/pith/PHV67C645GFZLJFZEFEWRXFIFW","bundle":"https://pith.science/pith/PHV67C645GFZLJFZEFEWRXFIFW/bundle.json","state":"https://pith.science/pith/PHV67C645GFZLJFZEFEWRXFIFW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PHV67C645GFZLJFZEFEWRXFIFW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PHV67C645GFZLJFZEFEWRXFIFW","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":"5a7164bc9eed80a38b7c37db66a3afc994c8c0d67ca704d570f9bad1e6a677f0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-23T08:15:49Z","title_canon_sha256":"af232d658d3af2ae0478ffddfc76723351eb86ca92ec78d798873d47afb8f7bb"},"schema_version":"1.0","source":{"id":"2405.14295","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.14295","created_at":"2026-07-05T08:22:12Z"},{"alias_kind":"arxiv_version","alias_value":"2405.14295v1","created_at":"2026-07-05T08:22:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14295","created_at":"2026-07-05T08:22:12Z"},{"alias_kind":"pith_short_12","alias_value":"PHV67C645GFZ","created_at":"2026-07-05T08:22:12Z"},{"alias_kind":"pith_short_16","alias_value":"PHV67C645GFZLJFZ","created_at":"2026-07-05T08:22:12Z"},{"alias_kind":"pith_short_8","alias_value":"PHV67C64","created_at":"2026-07-05T08:22:12Z"}],"graph_snapshots":[{"event_id":"sha256:866412f03cc680f070bf93acc54c345f0ef5d3f57e501ac31d94cbaa68a1456a","target":"graph","created_at":"2026-07-05T08:22:12Z","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/2405.14295/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern LVLMs still struggle to achieve fine-grained document understanding, such as OCR/translation/caption for regions of interest to the user, tasks that require the context of the entire page, or even multiple pages. Accordingly, this paper proposes Fox, an effective pipeline, hybrid data, and tuning strategy, that catalyzes LVLMs to focus anywhere on single/multi-page documents. We introduce a novel task to boost the document understanding by making LVLMs focus attention on the document-level region, such as redefining full-page OCR as foreground focus. We employ multiple vision vocabulari","authors_text":"Chenglong Liu, Chunrui Han, Haoran Wei, Jianjian Sun, Jinyue Chen, Liang Zhao, Lingyu Kong, Xiangyu Zhang, Zheng Ge, Zining Zhu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-23T08:15:49Z","title":"Focus Anywhere for Fine-grained Multi-page Document Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14295","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:ffd03b91fa088689c1b32c8dcda7e751b660ca60e77fecc518cb2fa9719f2d48","target":"record","created_at":"2026-07-05T08:22:12Z","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":"5a7164bc9eed80a38b7c37db66a3afc994c8c0d67ca704d570f9bad1e6a677f0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-23T08:15:49Z","title_canon_sha256":"af232d658d3af2ae0478ffddfc76723351eb86ca92ec78d798873d47afb8f7bb"},"schema_version":"1.0","source":{"id":"2405.14295","kind":"arxiv","version":1}},"canonical_sha256":"79ebef8bdce98b95a4b9214968dca82d8ed67d89143b6bcab8e5d77282134793","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"79ebef8bdce98b95a4b9214968dca82d8ed67d89143b6bcab8e5d77282134793","first_computed_at":"2026-07-05T08:22:12.553589Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:22:12.553589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JtCaoc24IoVhmrHd9+yqFs80yibLv38yW0U1SiD8Ad82oavMCj5i0YESu/3k4mmot/rMTSAwPFJzmGh+GJjUCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:22:12.554098Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.14295","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ffd03b91fa088689c1b32c8dcda7e751b660ca60e77fecc518cb2fa9719f2d48","sha256:866412f03cc680f070bf93acc54c345f0ef5d3f57e501ac31d94cbaa68a1456a"],"state_sha256":"db9b24849cb8d0dc3f5fa1c637b736c4fd75a384d23c52fdd6dffe34939c1214"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"16fSitjCvNLCzl3udBZiXNNMObE2zP+GKv65syuQRe23il96d2MzZz7F/Brf7hWcfIO5KSOfXxUP+EdlOPy1BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T13:46:35.216066Z","bundle_sha256":"70e1eaea646babe49427c07cf4595960d1bb9fbe9ab96a4e4315b823aedc12c3"}}