{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7DQW2RXXGF6ZHB5SIV6C6CISVU","short_pith_number":"pith:7DQW2RXX","canonical_record":{"source":{"id":"2503.02175","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-04T01:33:14Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0b2d0e16ba7cf145abfe24bc20331882959aad1f073b5a7c5ef9cc8ff5dbfce7","abstract_canon_sha256":"daa9d4ee9685f4a5f4c0a3dc8c0ea208e0fa02eab56d4838195114838ee8ce55"},"schema_version":"1.0"},"canonical_sha256":"f8e16d46f7317d9387b2457c2f0912ad28d27ec1659bdb304b77e308273c4459","source":{"kind":"arxiv","id":"2503.02175","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.02175","created_at":"2026-07-05T10:43:05Z"},{"alias_kind":"arxiv_version","alias_value":"2503.02175v2","created_at":"2026-07-05T10:43:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.02175","created_at":"2026-07-05T10:43:05Z"},{"alias_kind":"pith_short_12","alias_value":"7DQW2RXXGF6Z","created_at":"2026-07-05T10:43:05Z"},{"alias_kind":"pith_short_16","alias_value":"7DQW2RXXGF6ZHB5S","created_at":"2026-07-05T10:43:05Z"},{"alias_kind":"pith_short_8","alias_value":"7DQW2RXX","created_at":"2026-07-05T10:43:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7DQW2RXXGF6ZHB5SIV6C6CISVU","target":"record","payload":{"canonical_record":{"source":{"id":"2503.02175","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-04T01:33:14Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0b2d0e16ba7cf145abfe24bc20331882959aad1f073b5a7c5ef9cc8ff5dbfce7","abstract_canon_sha256":"daa9d4ee9685f4a5f4c0a3dc8c0ea208e0fa02eab56d4838195114838ee8ce55"},"schema_version":"1.0"},"canonical_sha256":"f8e16d46f7317d9387b2457c2f0912ad28d27ec1659bdb304b77e308273c4459","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:05.198544Z","signature_b64":"Xfe20UOr7Jl/LprafOYmocLAj9FQ3w90z0+xcUVaE63S3OcRUWTxnzM4Lv7CsXt6R+LphbWCqXMzhOSXGwtXCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8e16d46f7317d9387b2457c2f0912ad28d27ec1659bdb304b77e308273c4459","last_reissued_at":"2026-07-05T10:43:05.198020Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:05.198020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.02175","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:43:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t3t6TZS+x1aFaUdOM/62KXb396D3yDxli9YseNacMzIGCH8E8eIYMESICj6fC1U3STIcbbMDel6cQWJPdrDHAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:52:19.927274Z"},"content_sha256":"00527b6b02585cd57abce98902728d97642fc01a1106b577f02a228e94e6c95b","schema_version":"1.0","event_id":"sha256:00527b6b02585cd57abce98902728d97642fc01a1106b577f02a228e94e6c95b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7DQW2RXXGF6ZHB5SIV6C6CISVU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Gursimran Singh, Mohammad Akbari, Saeed Ranjbar Alvar, Yong Zhang","submitted_at":"2025-03-04T01:33:14Z","abstract_excerpt":"Large Multimodal Models (LMMs) have emerged as powerful models capable of understanding various data modalities, including text, images, and videos. LMMs encode both text and visual data into tokens that are then combined and processed by an integrated Large Language Model (LLM). Including visual tokens substantially increases the total token count, often by thousands. The increased input length for LLM significantly raises the complexity of inference, resulting in high latency in LMMs. To address this issue, token pruning methods, which remove part of the visual tokens, are proposed. The exis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.02175","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/2503.02175/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:43:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vw1gY1dTilEok/ypGUq/glhBCOuJUJUH5A+UkLl7c7N5phmtjTyXRP5hTgqXKBFcupRTih4V1GmvZeZAL1n7Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:52:19.927838Z"},"content_sha256":"85b9d325c8927b8a5fb2ca550fda9a93be61c143b40c6b4200c3c38a529b6535","schema_version":"1.0","event_id":"sha256:85b9d325c8927b8a5fb2ca550fda9a93be61c143b40c6b4200c3c38a529b6535"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7DQW2RXXGF6ZHB5SIV6C6CISVU/bundle.json","state_url":"https://pith.science/pith/7DQW2RXXGF6ZHB5SIV6C6CISVU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7DQW2RXXGF6ZHB5SIV6C6CISVU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T22:52:19Z","links":{"resolver":"https://pith.science/pith/7DQW2RXXGF6ZHB5SIV6C6CISVU","bundle":"https://pith.science/pith/7DQW2RXXGF6ZHB5SIV6C6CISVU/bundle.json","state":"https://pith.science/pith/7DQW2RXXGF6ZHB5SIV6C6CISVU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7DQW2RXXGF6ZHB5SIV6C6CISVU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7DQW2RXXGF6ZHB5SIV6C6CISVU","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":"daa9d4ee9685f4a5f4c0a3dc8c0ea208e0fa02eab56d4838195114838ee8ce55","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-04T01:33:14Z","title_canon_sha256":"0b2d0e16ba7cf145abfe24bc20331882959aad1f073b5a7c5ef9cc8ff5dbfce7"},"schema_version":"1.0","source":{"id":"2503.02175","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.02175","created_at":"2026-07-05T10:43:05Z"},{"alias_kind":"arxiv_version","alias_value":"2503.02175v2","created_at":"2026-07-05T10:43:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.02175","created_at":"2026-07-05T10:43:05Z"},{"alias_kind":"pith_short_12","alias_value":"7DQW2RXXGF6Z","created_at":"2026-07-05T10:43:05Z"},{"alias_kind":"pith_short_16","alias_value":"7DQW2RXXGF6ZHB5S","created_at":"2026-07-05T10:43:05Z"},{"alias_kind":"pith_short_8","alias_value":"7DQW2RXX","created_at":"2026-07-05T10:43:05Z"}],"graph_snapshots":[{"event_id":"sha256:85b9d325c8927b8a5fb2ca550fda9a93be61c143b40c6b4200c3c38a529b6535","target":"graph","created_at":"2026-07-05T10:43:05Z","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/2503.02175/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Multimodal Models (LMMs) have emerged as powerful models capable of understanding various data modalities, including text, images, and videos. LMMs encode both text and visual data into tokens that are then combined and processed by an integrated Large Language Model (LLM). Including visual tokens substantially increases the total token count, often by thousands. The increased input length for LLM significantly raises the complexity of inference, resulting in high latency in LMMs. To address this issue, token pruning methods, which remove part of the visual tokens, are proposed. The exis","authors_text":"Gursimran Singh, Mohammad Akbari, Saeed Ranjbar Alvar, Yong Zhang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-04T01:33:14Z","title":"DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.02175","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":"sha256:00527b6b02585cd57abce98902728d97642fc01a1106b577f02a228e94e6c95b","target":"record","created_at":"2026-07-05T10:43:05Z","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":"daa9d4ee9685f4a5f4c0a3dc8c0ea208e0fa02eab56d4838195114838ee8ce55","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-04T01:33:14Z","title_canon_sha256":"0b2d0e16ba7cf145abfe24bc20331882959aad1f073b5a7c5ef9cc8ff5dbfce7"},"schema_version":"1.0","source":{"id":"2503.02175","kind":"arxiv","version":2}},"canonical_sha256":"f8e16d46f7317d9387b2457c2f0912ad28d27ec1659bdb304b77e308273c4459","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8e16d46f7317d9387b2457c2f0912ad28d27ec1659bdb304b77e308273c4459","first_computed_at":"2026-07-05T10:43:05.198020Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:43:05.198020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Xfe20UOr7Jl/LprafOYmocLAj9FQ3w90z0+xcUVaE63S3OcRUWTxnzM4Lv7CsXt6R+LphbWCqXMzhOSXGwtXCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:43:05.198544Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.02175","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:00527b6b02585cd57abce98902728d97642fc01a1106b577f02a228e94e6c95b","sha256:85b9d325c8927b8a5fb2ca550fda9a93be61c143b40c6b4200c3c38a529b6535"],"state_sha256":"7f370b7fa40b1ccead35a3c24cb5214cbeb959189028cc5a0021fa541d951580"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4vBOlQoL7Zy2XxkD0YaPeGF/z3fnJkbsCcJA8f6bcp5hDeCPWAsY+yYumJzyFA7c82YsZR297ogDSAiL3NhZBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T22:52:19.933594Z","bundle_sha256":"e9b83dbd100e5c4d2a06cf29f90e415756605ba2b64f22db60fc3c413c33eb41"}}