{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:I4BF7DSGGRCUZDE2GJKTUA3IX4","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":"7e2c0464e73e4849f905a874a00d8e25777503e69b74114b3ddb9b82440a967e","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-27T17:36:23Z","title_canon_sha256":"1c635c82c852bda35c29d0de8aeb8405766de849ce8df912609bdab5764a0734"},"schema_version":"1.0","source":{"id":"2505.21465","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.21465","created_at":"2026-07-05T11:10:42Z"},{"alias_kind":"arxiv_version","alias_value":"2505.21465v1","created_at":"2026-07-05T11:10:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21465","created_at":"2026-07-05T11:10:42Z"},{"alias_kind":"pith_short_12","alias_value":"I4BF7DSGGRCU","created_at":"2026-07-05T11:10:42Z"},{"alias_kind":"pith_short_16","alias_value":"I4BF7DSGGRCUZDE2","created_at":"2026-07-05T11:10:42Z"},{"alias_kind":"pith_short_8","alias_value":"I4BF7DSG","created_at":"2026-07-05T11:10:42Z"}],"graph_snapshots":[{"event_id":"sha256:21fa4a2e1f0264ddcfb081f94e32fb23c79f4b869f9bd68553cbbb2dfc30c11a","target":"graph","created_at":"2026-07-05T11:10:42Z","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/2505.21465/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Currently, a prevalent approach for enhancing Vision-Language Models (VLMs) performance is to encode both the high-resolution version and the thumbnail of an image simultaneously. While effective, this method generates a large number of image tokens. When combined with the widely used Rotary Position Embedding (RoPE), its long-term decay property hinders the interaction between high-resolution tokens and thumbnail tokens, as well as between text and image. To address these issues, we propose ID-Align, which alleviates these problems by reordering position IDs. In this method, high-resolution t","authors_text":"Bozhou Li, Wentao Zhang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-27T17:36:23Z","title":"ID-Align: RoPE-Conscious Position Remapping for Dynamic High-Resolution Adaptation in Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21465","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:fc2ea0192274b49e7896cbdb59e3738ed47c277c0b88649b187167c3b0470716","target":"record","created_at":"2026-07-05T11:10:42Z","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":"7e2c0464e73e4849f905a874a00d8e25777503e69b74114b3ddb9b82440a967e","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-27T17:36:23Z","title_canon_sha256":"1c635c82c852bda35c29d0de8aeb8405766de849ce8df912609bdab5764a0734"},"schema_version":"1.0","source":{"id":"2505.21465","kind":"arxiv","version":1}},"canonical_sha256":"47025f8e4634454c8c9a32553a0368bf17d2ea13615ff7b104d9a8d0b712d0ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"47025f8e4634454c8c9a32553a0368bf17d2ea13615ff7b104d9a8d0b712d0ae","first_computed_at":"2026-07-05T11:10:42.425471Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:42.425471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rqu2j9WWbFIzaSV23HVlIQUceRsDOzB2I+IeUN1IW9NnlW+bQk/hzZG4tfBRLYMGQzddWIHHqsOPgY48AbZsCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:42.425954Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.21465","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc2ea0192274b49e7896cbdb59e3738ed47c277c0b88649b187167c3b0470716","sha256:21fa4a2e1f0264ddcfb081f94e32fb23c79f4b869f9bd68553cbbb2dfc30c11a"],"state_sha256":"41c4b554747b10aa76e30b093d05dcfeeb44d607d88d4034efe618a3b373f234"}