{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TYNO45SLGU4EPSBMS7GVPKTS4M","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":"e38c46ba006d7a0b1314c5f94197b7981abb825ec1e62ce61c0e825c6ffc6bb7","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-27T17:16:27Z","title_canon_sha256":"94d3df60c57455a02f8cacf408cba7529606e2f5f5748b6424010ef25748caab"},"schema_version":"1.0","source":{"id":"2305.17530","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.17530","created_at":"2026-07-05T06:14:45Z"},{"alias_kind":"arxiv_version","alias_value":"2305.17530v1","created_at":"2026-07-05T06:14:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17530","created_at":"2026-07-05T06:14:45Z"},{"alias_kind":"pith_short_12","alias_value":"TYNO45SLGU4E","created_at":"2026-07-05T06:14:45Z"},{"alias_kind":"pith_short_16","alias_value":"TYNO45SLGU4EPSBM","created_at":"2026-07-05T06:14:45Z"},{"alias_kind":"pith_short_8","alias_value":"TYNO45SL","created_at":"2026-07-05T06:14:45Z"}],"graph_snapshots":[{"event_id":"sha256:b6e89e9e49a3e806620da2f3cc252fce9c54604ac6a58314524f8eaa11a51fca","target":"graph","created_at":"2026-07-05T06:14:45Z","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/2305.17530/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale vision language (VL) models use Transformers to perform cross-modal interactions between the input text and image. These cross-modal interactions are computationally expensive and memory-intensive due to the quadratic complexity of processing the input image and text. We present PuMer: a token reduction framework that uses text-informed Pruning and modality-aware Merging strategies to progressively reduce the tokens of input image and text, improving model inference speed and reducing memory footprint. PuMer learns to keep salient image tokens related to the input text and merges s","authors_text":"Bhargavi Paranjape, Hannaneh Hajishirzi, Qingqing Cao","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-27T17:16:27Z","title":"PuMer: Pruning and Merging Tokens for Efficient Vision Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17530","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:ef78cf72a5297792b88295d40f7b595356e0f74a90de0f4da630ecd4e4449334","target":"record","created_at":"2026-07-05T06:14:45Z","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":"e38c46ba006d7a0b1314c5f94197b7981abb825ec1e62ce61c0e825c6ffc6bb7","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-27T17:16:27Z","title_canon_sha256":"94d3df60c57455a02f8cacf408cba7529606e2f5f5748b6424010ef25748caab"},"schema_version":"1.0","source":{"id":"2305.17530","kind":"arxiv","version":1}},"canonical_sha256":"9e1aee764b353847c82c97cd57aa72e328cb5a4fa34e3af7cfca5b1cd38c0abd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e1aee764b353847c82c97cd57aa72e328cb5a4fa34e3af7cfca5b1cd38c0abd","first_computed_at":"2026-07-05T06:14:45.575967Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:14:45.575967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Lr9UE2L62cN00M5NNXUpSFLVDmvUK7N86eo5iBqzmBjEZf+8dxV09kQW6ixHdIlkKXA+O84lYOxif6O/LSO3DA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:14:45.576372Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.17530","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef78cf72a5297792b88295d40f7b595356e0f74a90de0f4da630ecd4e4449334","sha256:b6e89e9e49a3e806620da2f3cc252fce9c54604ac6a58314524f8eaa11a51fca"],"state_sha256":"f7c97874bc0d136bfcaf6d361ba6f7a118359fe0157ec4e27d41325e20e143e9"}