{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XLVUEGHLB7O6TO6CR4XI4F2IF6","short_pith_number":"pith:XLVUEGHL","canonical_record":{"source":{"id":"2412.09616","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T18:59:46Z","cross_cats_sorted":[],"title_canon_sha256":"7e32d43344742147c59ca6d1a86670528cd0bf511af34beb84809c2ae10fece1","abstract_canon_sha256":"44927dc7d963a95e49d7dfd655e4264875de4ca4ddd6cb00bce25e6a46693a4f"},"schema_version":"1.0"},"canonical_sha256":"baeb4218eb0fdde9bbc28f2e8e17482f86607a9f9c80957231a86dd780a6317e","source":{"kind":"arxiv","id":"2412.09616","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.09616","created_at":"2026-07-05T09:48:39Z"},{"alias_kind":"arxiv_version","alias_value":"2412.09616v2","created_at":"2026-07-05T09:48:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09616","created_at":"2026-07-05T09:48:39Z"},{"alias_kind":"pith_short_12","alias_value":"XLVUEGHLB7O6","created_at":"2026-07-05T09:48:39Z"},{"alias_kind":"pith_short_16","alias_value":"XLVUEGHLB7O6TO6C","created_at":"2026-07-05T09:48:39Z"},{"alias_kind":"pith_short_8","alias_value":"XLVUEGHL","created_at":"2026-07-05T09:48:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XLVUEGHLB7O6TO6CR4XI4F2IF6","target":"record","payload":{"canonical_record":{"source":{"id":"2412.09616","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T18:59:46Z","cross_cats_sorted":[],"title_canon_sha256":"7e32d43344742147c59ca6d1a86670528cd0bf511af34beb84809c2ae10fece1","abstract_canon_sha256":"44927dc7d963a95e49d7dfd655e4264875de4ca4ddd6cb00bce25e6a46693a4f"},"schema_version":"1.0"},"canonical_sha256":"baeb4218eb0fdde9bbc28f2e8e17482f86607a9f9c80957231a86dd780a6317e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:39.114697Z","signature_b64":"YOValGsOTe+K1dEYhzt4rmMa/uReH0waILZp1S9n9XDStW+FbjpFrcgvSqT5yt1b9mTT99pbNggVp5DWnJVBBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"baeb4218eb0fdde9bbc28f2e8e17482f86607a9f9c80957231a86dd780a6317e","last_reissued_at":"2026-07-05T09:48:39.114215Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:39.114215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.09616","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":"2026-07-05T09:48:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"skZrz+xLIyakxDLHCh8+hHjNfl4g0SBilt5jM6ZwoX7eB0sM/4zPyeeGat3B/+xJdJsqfqngH9Ve7OLNEslkBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T20:43:31.618705Z"},"content_sha256":"11a7c5cb4ab6b723d2aa8e064d823d209f259f8b6533ad9e72b193742157fe71","schema_version":"1.0","event_id":"sha256:11a7c5cb4ab6b723d2aa8e064d823d209f259f8b6533ad9e72b193742157fe71"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XLVUEGHLB7O6TO6CR4XI4F2IF6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jifeng Dai, Jinguo Zhu, Jintao Lin, Junqi Ge, Xihui Liu, Xizhou Zhu, Ziyi Chen","submitted_at":"2024-12-12T18:59:46Z","abstract_excerpt":"Vision-Language Models (VLMs) have shown promising capabilities in handling various multimodal tasks, yet they struggle in long-context scenarios, particularly in tasks involving videos, high-resolution images, or lengthy image-text documents. In our work, we first conduct an empirical analysis of the long-context capabilities of VLMs using our augmented long-context multimodal datasets. Our findings reveal that directly applying the positional encoding mechanism used for textual tokens to visual tokens is suboptimal, and VLM performance degrades sharply when the position encoding exceeds the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09616","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/2412.09616/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":"2026-07-05T09:48:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yDaADwC5b3zdZK454ERO8lNbYaIK7jlxhZyzTb3yQFvDWhWwbUDIwQfw6mpFd/5sGcaazVYN/QqXsOq487CWBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T20:43:31.619021Z"},"content_sha256":"e6c5a0b69a92442bd5fd8f3dc350bb28f2d02dba7d6e71c5955bc9c318f3b102","schema_version":"1.0","event_id":"sha256:e6c5a0b69a92442bd5fd8f3dc350bb28f2d02dba7d6e71c5955bc9c318f3b102"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XLVUEGHLB7O6TO6CR4XI4F2IF6/bundle.json","state_url":"https://pith.science/pith/XLVUEGHLB7O6TO6CR4XI4F2IF6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XLVUEGHLB7O6TO6CR4XI4F2IF6/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":"2026-08-14T20:43:31Z","links":{"resolver":"https://pith.science/pith/XLVUEGHLB7O6TO6CR4XI4F2IF6","bundle":"https://pith.science/pith/XLVUEGHLB7O6TO6CR4XI4F2IF6/bundle.json","state":"https://pith.science/pith/XLVUEGHLB7O6TO6CR4XI4F2IF6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XLVUEGHLB7O6TO6CR4XI4F2IF6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XLVUEGHLB7O6TO6CR4XI4F2IF6","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":"44927dc7d963a95e49d7dfd655e4264875de4ca4ddd6cb00bce25e6a46693a4f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T18:59:46Z","title_canon_sha256":"7e32d43344742147c59ca6d1a86670528cd0bf511af34beb84809c2ae10fece1"},"schema_version":"1.0","source":{"id":"2412.09616","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.09616","created_at":"2026-07-05T09:48:39Z"},{"alias_kind":"arxiv_version","alias_value":"2412.09616v2","created_at":"2026-07-05T09:48:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09616","created_at":"2026-07-05T09:48:39Z"},{"alias_kind":"pith_short_12","alias_value":"XLVUEGHLB7O6","created_at":"2026-07-05T09:48:39Z"},{"alias_kind":"pith_short_16","alias_value":"XLVUEGHLB7O6TO6C","created_at":"2026-07-05T09:48:39Z"},{"alias_kind":"pith_short_8","alias_value":"XLVUEGHL","created_at":"2026-07-05T09:48:39Z"}],"graph_snapshots":[{"event_id":"sha256:e6c5a0b69a92442bd5fd8f3dc350bb28f2d02dba7d6e71c5955bc9c318f3b102","target":"graph","created_at":"2026-07-05T09:48:39Z","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/2412.09616/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Models (VLMs) have shown promising capabilities in handling various multimodal tasks, yet they struggle in long-context scenarios, particularly in tasks involving videos, high-resolution images, or lengthy image-text documents. In our work, we first conduct an empirical analysis of the long-context capabilities of VLMs using our augmented long-context multimodal datasets. Our findings reveal that directly applying the positional encoding mechanism used for textual tokens to visual tokens is suboptimal, and VLM performance degrades sharply when the position encoding exceeds the ","authors_text":"Jifeng Dai, Jinguo Zhu, Jintao Lin, Junqi Ge, Xihui Liu, Xizhou Zhu, Ziyi Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T18:59:46Z","title":"V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09616","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":"sha256:11a7c5cb4ab6b723d2aa8e064d823d209f259f8b6533ad9e72b193742157fe71","target":"record","created_at":"2026-07-05T09:48:39Z","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":"44927dc7d963a95e49d7dfd655e4264875de4ca4ddd6cb00bce25e6a46693a4f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T18:59:46Z","title_canon_sha256":"7e32d43344742147c59ca6d1a86670528cd0bf511af34beb84809c2ae10fece1"},"schema_version":"1.0","source":{"id":"2412.09616","kind":"arxiv","version":2}},"canonical_sha256":"baeb4218eb0fdde9bbc28f2e8e17482f86607a9f9c80957231a86dd780a6317e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"baeb4218eb0fdde9bbc28f2e8e17482f86607a9f9c80957231a86dd780a6317e","first_computed_at":"2026-07-05T09:48:39.114215Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:48:39.114215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YOValGsOTe+K1dEYhzt4rmMa/uReH0waILZp1S9n9XDStW+FbjpFrcgvSqT5yt1b9mTT99pbNggVp5DWnJVBBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:48:39.114697Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.09616","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:11a7c5cb4ab6b723d2aa8e064d823d209f259f8b6533ad9e72b193742157fe71","sha256:e6c5a0b69a92442bd5fd8f3dc350bb28f2d02dba7d6e71c5955bc9c318f3b102"],"state_sha256":"39a38e9a8f29ec7f86325bf4e0864a66fa6a8c52c652f282492eb4bf48cd0b85"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c69vrQv1K2jgL890LKVreyO2VkNlYgsYEyP2VPM/bTKoR3n8jiPZaVkdlQx1zNLJntngQL8VOLSP5DppPeJxBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T20:43:31.621247Z","bundle_sha256":"27eadcaba509a214118607452f9f11067b175299383f65404396de55671cf7db"}}