{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YJ6KXVDDRVCTYLDB45FY2SLDOG","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":"48d5a96cbb6ca7f06d9ae55e7ce26b19bf76cca4fd3d8dc4de210d02f45aed77","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-13T01:30:24Z","title_canon_sha256":"53c4787a2fbd3a30191f8888e5ce3e03f68f55190302dda3ee1528d5383f1282"},"schema_version":"1.0","source":{"id":"2409.08464","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.08464","created_at":"2026-07-05T09:41:41Z"},{"alias_kind":"arxiv_version","alias_value":"2409.08464v2","created_at":"2026-07-05T09:41:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08464","created_at":"2026-07-05T09:41:41Z"},{"alias_kind":"pith_short_12","alias_value":"YJ6KXVDDRVCT","created_at":"2026-07-05T09:41:41Z"},{"alias_kind":"pith_short_16","alias_value":"YJ6KXVDDRVCTYLDB","created_at":"2026-07-05T09:41:41Z"},{"alias_kind":"pith_short_8","alias_value":"YJ6KXVDD","created_at":"2026-07-05T09:41:41Z"}],"graph_snapshots":[{"event_id":"sha256:badcb09b1abf3243786d8a3d05ecb34d0205217a8a1bd09901be1415d24da5e6","target":"graph","created_at":"2026-07-05T09:41:41Z","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/2409.08464/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision Transformers (ViTs) have emerged as the backbone of many segmentation models, consistently achieving state-of-the-art (SOTA) performance. However, their success comes at a significant computational cost. Image token pruning is one of the most effective strategies to address this complexity. However, previous approaches fall short when applied to more complex task-oriented segmentation (TOS), where the class of each image patch is not predefined but dependent on the specific input task. This work introduces the Vision Language Guided Token Pruning (VLTP), a novel token pruning mechanism ","authors_text":"Fei Wen, Hanning Chen, Hugo Latapie, Mohsen Imani, Nathaniel Bastian, Sungheon Jeong, Wenjun Huang, Yang Ni, Yezi Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-13T01:30:24Z","title":"VLTP: Vision-Language Guided Token Pruning for Task-Oriented Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08464","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":"sha256:6f38b27388171204d885edc50d7822efa54b41d8dff5652dc66ce7ac035ba9bf","target":"record","created_at":"2026-07-05T09:41:41Z","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":"48d5a96cbb6ca7f06d9ae55e7ce26b19bf76cca4fd3d8dc4de210d02f45aed77","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-13T01:30:24Z","title_canon_sha256":"53c4787a2fbd3a30191f8888e5ce3e03f68f55190302dda3ee1528d5383f1282"},"schema_version":"1.0","source":{"id":"2409.08464","kind":"arxiv","version":2}},"canonical_sha256":"c27cabd4638d453c2c61e74b8d4963719453fce24f89e928c6f48d3085df8d63","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c27cabd4638d453c2c61e74b8d4963719453fce24f89e928c6f48d3085df8d63","first_computed_at":"2026-07-05T09:41:41.683797Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:41:41.683797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qr5in401YWgdmR1hLTv2xobKegrMamPf1A3vqACXA40pHC2AqujQxfvTuaMsqBo5pAVX8Ze4sicbg28wAvy0AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:41:41.684272Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.08464","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f38b27388171204d885edc50d7822efa54b41d8dff5652dc66ce7ac035ba9bf","sha256:badcb09b1abf3243786d8a3d05ecb34d0205217a8a1bd09901be1415d24da5e6"],"state_sha256":"cf74cc4cccc5df7902b3dc83013a24f5f973525ae849ef52aa608e0c54fe933c"}