{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YJ6KXVDDRVCTYLDB45FY2SLDOG","short_pith_number":"pith:YJ6KXVDD","schema_version":"1.0","canonical_sha256":"c27cabd4638d453c2c61e74b8d4963719453fce24f89e928c6f48d3085df8d63","source":{"kind":"arxiv","id":"2409.08464","version":2},"attestation_state":"computed","paper":{"title":"VLTP: Vision-Language Guided Token Pruning for Task-Oriented Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fei Wen, Hanning Chen, Hugo Latapie, Mohsen Imani, Nathaniel Bastian, Sungheon Jeong, Wenjun Huang, Yang Ni, Yezi Liu","submitted_at":"2024-09-13T01:30:24Z","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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2409.08464","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-13T01:30:24Z","cross_cats_sorted":[],"title_canon_sha256":"53c4787a2fbd3a30191f8888e5ce3e03f68f55190302dda3ee1528d5383f1282","abstract_canon_sha256":"48d5a96cbb6ca7f06d9ae55e7ce26b19bf76cca4fd3d8dc4de210d02f45aed77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:41.684272Z","signature_b64":"qr5in401YWgdmR1hLTv2xobKegrMamPf1A3vqACXA40pHC2AqujQxfvTuaMsqBo5pAVX8Ze4sicbg28wAvy0AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c27cabd4638d453c2c61e74b8d4963719453fce24f89e928c6f48d3085df8d63","last_reissued_at":"2026-07-05T09:41:41.683797Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:41.683797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VLTP: Vision-Language Guided Token Pruning for Task-Oriented Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fei Wen, Hanning Chen, Hugo Latapie, Mohsen Imani, Nathaniel Bastian, Sungheon Jeong, Wenjun Huang, Yang Ni, Yezi Liu","submitted_at":"2024-09-13T01:30:24Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08464","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/2409.08464/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2409.08464","created_at":"2026-07-05T09:41:41.683860+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.08464v2","created_at":"2026-07-05T09:41:41.683860+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08464","created_at":"2026-07-05T09:41:41.683860+00:00"},{"alias_kind":"pith_short_12","alias_value":"YJ6KXVDDRVCT","created_at":"2026-07-05T09:41:41.683860+00:00"},{"alias_kind":"pith_short_16","alias_value":"YJ6KXVDDRVCTYLDB","created_at":"2026-07-05T09:41:41.683860+00:00"},{"alias_kind":"pith_short_8","alias_value":"YJ6KXVDD","created_at":"2026-07-05T09:41:41.683860+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.16082","citing_title":"Leverage Task Context for Object Affordance Ranking","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YJ6KXVDDRVCTYLDB45FY2SLDOG","json":"https://pith.science/pith/YJ6KXVDDRVCTYLDB45FY2SLDOG.json","graph_json":"https://pith.science/api/pith-number/YJ6KXVDDRVCTYLDB45FY2SLDOG/graph.json","events_json":"https://pith.science/api/pith-number/YJ6KXVDDRVCTYLDB45FY2SLDOG/events.json","paper":"https://pith.science/paper/YJ6KXVDD"},"agent_actions":{"view_html":"https://pith.science/pith/YJ6KXVDDRVCTYLDB45FY2SLDOG","download_json":"https://pith.science/pith/YJ6KXVDDRVCTYLDB45FY2SLDOG.json","view_paper":"https://pith.science/paper/YJ6KXVDD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.08464&json=true","fetch_graph":"https://pith.science/api/pith-number/YJ6KXVDDRVCTYLDB45FY2SLDOG/graph.json","fetch_events":"https://pith.science/api/pith-number/YJ6KXVDDRVCTYLDB45FY2SLDOG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YJ6KXVDDRVCTYLDB45FY2SLDOG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YJ6KXVDDRVCTYLDB45FY2SLDOG/action/storage_attestation","attest_author":"https://pith.science/pith/YJ6KXVDDRVCTYLDB45FY2SLDOG/action/author_attestation","sign_citation":"https://pith.science/pith/YJ6KXVDDRVCTYLDB45FY2SLDOG/action/citation_signature","submit_replication":"https://pith.science/pith/YJ6KXVDDRVCTYLDB45FY2SLDOG/action/replication_record"}},"created_at":"2026-07-05T09:41:41.683860+00:00","updated_at":"2026-07-05T09:41:41.683860+00:00"}