{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:N3PFCFKYU42BGYIMCLCFUPI2DD","short_pith_number":"pith:N3PFCFKY","canonical_record":{"source":{"id":"2504.17892","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-24T19:11:10Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"fef537e35fa740e9a61e8b8ab815c25f68300a65a7634e3075c7c0897e95f67b","abstract_canon_sha256":"3048ca0630efe8dabfc680433fd8b981d3e6c37f06eccf3893e5ce1fbd5f1da1"},"schema_version":"1.0"},"canonical_sha256":"6ede511558a73413610c12c45a3d1a18f77a1e957396d38d3221b28f3312a5bb","source":{"kind":"arxiv","id":"2504.17892","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.17892","created_at":"2026-07-05T10:53:58Z"},{"alias_kind":"arxiv_version","alias_value":"2504.17892v1","created_at":"2026-07-05T10:53:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.17892","created_at":"2026-07-05T10:53:58Z"},{"alias_kind":"pith_short_12","alias_value":"N3PFCFKYU42B","created_at":"2026-07-05T10:53:58Z"},{"alias_kind":"pith_short_16","alias_value":"N3PFCFKYU42BGYIM","created_at":"2026-07-05T10:53:58Z"},{"alias_kind":"pith_short_8","alias_value":"N3PFCFKY","created_at":"2026-07-05T10:53:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:N3PFCFKYU42BGYIMCLCFUPI2DD","target":"record","payload":{"canonical_record":{"source":{"id":"2504.17892","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-24T19:11:10Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"fef537e35fa740e9a61e8b8ab815c25f68300a65a7634e3075c7c0897e95f67b","abstract_canon_sha256":"3048ca0630efe8dabfc680433fd8b981d3e6c37f06eccf3893e5ce1fbd5f1da1"},"schema_version":"1.0"},"canonical_sha256":"6ede511558a73413610c12c45a3d1a18f77a1e957396d38d3221b28f3312a5bb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:58.269474Z","signature_b64":"yLwq2nZOvNzjGb4e7BpoeyuGjKZD7pKRZGtJND/Y/eb0ryCyIGup95raAjHQkOX05egKY8lFPHM5LDssy/isDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ede511558a73413610c12c45a3d1a18f77a1e957396d38d3221b28f3312a5bb","last_reissued_at":"2026-07-05T10:53:58.268922Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:58.268922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.17892","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:53:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HOn1Y4yvZgZroPqM+l6oMDbqYOESNTqbat5ufgCiy7hgsP0dOQ3C9408w+jBtsH+Ynh22T97ZshGG9Tmf+djDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T01:18:49.758930Z"},"content_sha256":"e41270ec03f5fbd2ba29626fdfb78b20deadc08d86e69f6381c223707519de4e","schema_version":"1.0","event_id":"sha256:e41270ec03f5fbd2ba29626fdfb78b20deadc08d86e69f6381c223707519de4e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:N3PFCFKYU42BGYIMCLCFUPI2DD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Token Sequence Compression for Efficient Multimodal Computing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Parth Shroff, Thierry Tambe, Yasmine Omri","submitted_at":"2025-04-24T19:11:10Z","abstract_excerpt":"The exponential growth of Large Multimodal Models (LMMs) has driven advancements in cross-modal reasoning but at significant computational costs. In this work, we focus on visual language models. We highlight the redundancy and inefficiency in current vision encoders, and seek to construct an adaptive compression method for multimodal data. In this work, we characterize a panoply of visual token selection and merging approaches through both benchmarking and qualitative analysis. In particular, we demonstrate that simple cluster-level token aggregation outperforms prior state-of-the-art works i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.17892","kind":"arxiv","version":1},"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/2504.17892/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":"2026-07-05T10:53:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"25bM2Uozfey57x4I/CHTFk3NzJ4vUvQUjwLv0hxscCUAg3HBB6V9FmE9m0kAjIA/Nf7eRO5hBtcfybHkt7JdDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T01:18:49.759595Z"},"content_sha256":"e1144d03848b1531f43571a0c72a07f30724e7a4ab94161a8853e79bb45761bd","schema_version":"1.0","event_id":"sha256:e1144d03848b1531f43571a0c72a07f30724e7a4ab94161a8853e79bb45761bd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N3PFCFKYU42BGYIMCLCFUPI2DD/bundle.json","state_url":"https://pith.science/pith/N3PFCFKYU42BGYIMCLCFUPI2DD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N3PFCFKYU42BGYIMCLCFUPI2DD/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":"2026-08-19T01:18:49Z","links":{"resolver":"https://pith.science/pith/N3PFCFKYU42BGYIMCLCFUPI2DD","bundle":"https://pith.science/pith/N3PFCFKYU42BGYIMCLCFUPI2DD/bundle.json","state":"https://pith.science/pith/N3PFCFKYU42BGYIMCLCFUPI2DD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N3PFCFKYU42BGYIMCLCFUPI2DD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:N3PFCFKYU42BGYIMCLCFUPI2DD","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":"3048ca0630efe8dabfc680433fd8b981d3e6c37f06eccf3893e5ce1fbd5f1da1","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-24T19:11:10Z","title_canon_sha256":"fef537e35fa740e9a61e8b8ab815c25f68300a65a7634e3075c7c0897e95f67b"},"schema_version":"1.0","source":{"id":"2504.17892","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.17892","created_at":"2026-07-05T10:53:58Z"},{"alias_kind":"arxiv_version","alias_value":"2504.17892v1","created_at":"2026-07-05T10:53:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.17892","created_at":"2026-07-05T10:53:58Z"},{"alias_kind":"pith_short_12","alias_value":"N3PFCFKYU42B","created_at":"2026-07-05T10:53:58Z"},{"alias_kind":"pith_short_16","alias_value":"N3PFCFKYU42BGYIM","created_at":"2026-07-05T10:53:58Z"},{"alias_kind":"pith_short_8","alias_value":"N3PFCFKY","created_at":"2026-07-05T10:53:58Z"}],"graph_snapshots":[{"event_id":"sha256:e1144d03848b1531f43571a0c72a07f30724e7a4ab94161a8853e79bb45761bd","target":"graph","created_at":"2026-07-05T10:53:58Z","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/2504.17892/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The exponential growth of Large Multimodal Models (LMMs) has driven advancements in cross-modal reasoning but at significant computational costs. In this work, we focus on visual language models. We highlight the redundancy and inefficiency in current vision encoders, and seek to construct an adaptive compression method for multimodal data. In this work, we characterize a panoply of visual token selection and merging approaches through both benchmarking and qualitative analysis. In particular, we demonstrate that simple cluster-level token aggregation outperforms prior state-of-the-art works i","authors_text":"Parth Shroff, Thierry Tambe, Yasmine Omri","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-24T19:11:10Z","title":"Token Sequence Compression for Efficient Multimodal Computing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.17892","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:e41270ec03f5fbd2ba29626fdfb78b20deadc08d86e69f6381c223707519de4e","target":"record","created_at":"2026-07-05T10:53:58Z","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":"3048ca0630efe8dabfc680433fd8b981d3e6c37f06eccf3893e5ce1fbd5f1da1","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-24T19:11:10Z","title_canon_sha256":"fef537e35fa740e9a61e8b8ab815c25f68300a65a7634e3075c7c0897e95f67b"},"schema_version":"1.0","source":{"id":"2504.17892","kind":"arxiv","version":1}},"canonical_sha256":"6ede511558a73413610c12c45a3d1a18f77a1e957396d38d3221b28f3312a5bb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ede511558a73413610c12c45a3d1a18f77a1e957396d38d3221b28f3312a5bb","first_computed_at":"2026-07-05T10:53:58.268922Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:53:58.268922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yLwq2nZOvNzjGb4e7BpoeyuGjKZD7pKRZGtJND/Y/eb0ryCyIGup95raAjHQkOX05egKY8lFPHM5LDssy/isDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:53:58.269474Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.17892","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e41270ec03f5fbd2ba29626fdfb78b20deadc08d86e69f6381c223707519de4e","sha256:e1144d03848b1531f43571a0c72a07f30724e7a4ab94161a8853e79bb45761bd"],"state_sha256":"812c198839a5745c6b6713a0ee52a76296d309ccb0f13d8a62da76a1f747ff7b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nbsYSMSqqkgOU5FatB94FlKZLjr0wmW5B2pOyiuAPXEACxECpFWABUgrmWhgKeEIfLdi2CVcKQG6z/UcMRY3BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T01:18:49.766778Z","bundle_sha256":"12cde32203d4467c8801cc20987a3dd03409c94462747d6b7e45494b303cb439"}}