{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:N4SZNAHWZ76TWHJQB2IAYHLJUZ","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":"30fd9ff726cc461e66155741cdfd7f964d61454a6acd4d98a1b6b6836a103106","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-02T12:36:24Z","title_canon_sha256":"949ba01f9623439f310208dbf2c86b92c86d6d8c92ceb43b742cbf25cc903681"},"schema_version":"1.0","source":{"id":"2606.03569","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03569","created_at":"2026-06-03T01:06:01Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03569v1","created_at":"2026-06-03T01:06:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03569","created_at":"2026-06-03T01:06:01Z"},{"alias_kind":"pith_short_12","alias_value":"N4SZNAHWZ76T","created_at":"2026-06-03T01:06:01Z"},{"alias_kind":"pith_short_16","alias_value":"N4SZNAHWZ76TWHJQ","created_at":"2026-06-03T01:06:01Z"},{"alias_kind":"pith_short_8","alias_value":"N4SZNAHW","created_at":"2026-06-03T01:06:01Z"}],"graph_snapshots":[{"event_id":"sha256:d90f8b65a7d3d19642b661efc1da76b2d6c31b69d4bf5a8aa112ad15d49738d7","target":"graph","created_at":"2026-06-03T01:06:01Z","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/2606.03569/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Models (VLMs) have demonstrated remarkable capabilities but suffer from significant computational overhead during inference. While visual token pruning offers a promising solution, existing methods predominantly rely on initial attention scores. This single-metric paradigm presents a critical flaw: high attention scores inherently collapse onto semantically similar regions, thereby severely reducing feature diversity and discarding vital contextual details. To address this, we introduce Structure-to-Semantics (STS), a novel two-stage visual token pruning framework that explicit","authors_text":"Huanghe Zhang, Jiahui Wang, Kai Zhang, Mai Han","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-02T12:36:24Z","title":"When Attention Collapses: Stage-Aware Visual Token Pruning from Structure to Semantics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03569","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:b837f19db000709123ee4cbee927ed97927e82658059b22abe061bfedc556fce","target":"record","created_at":"2026-06-03T01:06:01Z","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":"30fd9ff726cc461e66155741cdfd7f964d61454a6acd4d98a1b6b6836a103106","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-02T12:36:24Z","title_canon_sha256":"949ba01f9623439f310208dbf2c86b92c86d6d8c92ceb43b742cbf25cc903681"},"schema_version":"1.0","source":{"id":"2606.03569","kind":"arxiv","version":1}},"canonical_sha256":"6f259680f6cffd3b1d300e900c1d69a66cfb7e7cd5e464779ae43c26e69bbfe2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6f259680f6cffd3b1d300e900c1d69a66cfb7e7cd5e464779ae43c26e69bbfe2","first_computed_at":"2026-06-03T01:06:01.129769Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:06:01.129769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a3goQSxEFbsaRvvZJQIUtsg3SuAET1u87N067Y6VX0laKXEXQiZnR+qPqan39ZJtZIAV5kPg6QRlFL9hHSZyDg==","signature_status":"signed_v1","signed_at":"2026-06-03T01:06:01.130165Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.03569","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b837f19db000709123ee4cbee927ed97927e82658059b22abe061bfedc556fce","sha256:d90f8b65a7d3d19642b661efc1da76b2d6c31b69d4bf5a8aa112ad15d49738d7"],"state_sha256":"4ae17d50eb47a642c319c84a764f103295e73b97c96fe0e9bfae9057607c1743"}