{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WCMZYE6AZHUSLON6RK6QH7PLQH","short_pith_number":"pith:WCMZYE6A","canonical_record":{"source":{"id":"2507.20842","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-28T13:50:53Z","cross_cats_sorted":[],"title_canon_sha256":"348e6828ce77ceec004cd086197ad144269dcf4faf451f654649ebdbd0ba0999","abstract_canon_sha256":"fa0f91a6b770ffc9d10ec8d9aac2949b15f00a96992ca7446b6ddaaeca062eea"},"schema_version":"1.0"},"canonical_sha256":"b0999c13c0c9e925b9be8abd03fdeb81c654fd8eabf633c69b6596aefa0966df","source":{"kind":"arxiv","id":"2507.20842","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.20842","created_at":"2026-07-05T11:44:26Z"},{"alias_kind":"arxiv_version","alias_value":"2507.20842v1","created_at":"2026-07-05T11:44:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.20842","created_at":"2026-07-05T11:44:26Z"},{"alias_kind":"pith_short_12","alias_value":"WCMZYE6AZHUS","created_at":"2026-07-05T11:44:26Z"},{"alias_kind":"pith_short_16","alias_value":"WCMZYE6AZHUSLON6","created_at":"2026-07-05T11:44:26Z"},{"alias_kind":"pith_short_8","alias_value":"WCMZYE6A","created_at":"2026-07-05T11:44:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WCMZYE6AZHUSLON6RK6QH7PLQH","target":"record","payload":{"canonical_record":{"source":{"id":"2507.20842","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-28T13:50:53Z","cross_cats_sorted":[],"title_canon_sha256":"348e6828ce77ceec004cd086197ad144269dcf4faf451f654649ebdbd0ba0999","abstract_canon_sha256":"fa0f91a6b770ffc9d10ec8d9aac2949b15f00a96992ca7446b6ddaaeca062eea"},"schema_version":"1.0"},"canonical_sha256":"b0999c13c0c9e925b9be8abd03fdeb81c654fd8eabf633c69b6596aefa0966df","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:26.854064Z","signature_b64":"qP+sMrPGHFWlS6fJ36P2TmxsjbkUujktU5aFslDBVIwvcxf6u+ONN64yPti+/KgpnTpWt8fpZIQ/26P8Sj4WCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0999c13c0c9e925b9be8abd03fdeb81c654fd8eabf633c69b6596aefa0966df","last_reissued_at":"2026-07-05T11:44:26.853561Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:26.853561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.20842","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":"2026-07-05T11:44:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"46L/es7ix5GPoMrvpDrdvIJ06B3cEzsZiTvJSEnrL0U+tFdFYN6D6GTPtV1+IXVHbtGQfpCJDrC759LyW2osCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T15:14:24.942968Z"},"content_sha256":"986ae3ffbf5dc649e71c655fad9636c30db9670071ca7b4bcf669295879855f4","schema_version":"1.0","event_id":"sha256:986ae3ffbf5dc649e71c655fad9636c30db9670071ca7b4bcf669295879855f4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WCMZYE6AZHUSLON6RK6QH7PLQH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"METEOR: Multi-Encoder Collaborative Token Pruning for Efficient Vision Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bowen Shi, Chenglin Li, Hongkai Xiong, Qi Tian, Wenrui Dai, Xiaopeng Zhang, Yaoming Wang, Yuchen Liu","submitted_at":"2025-07-28T13:50:53Z","abstract_excerpt":"Vision encoders serve as the cornerstone of multimodal understanding. Single-encoder architectures like CLIP exhibit inherent constraints in generalizing across diverse multimodal tasks, while recent multi-encoder fusion methods introduce prohibitive computational overhead to achieve superior performance using complementary visual representations from multiple vision encoders. To address this, we propose a progressive pruning framework, namely Multi-Encoder collaboraTivE tOken pRuning (METEOR), that eliminates redundant visual tokens across the encoding, fusion, and decoding stages for multi-e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.20842","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/2507.20842/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":"2026-07-05T11:44:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ft4r5I6zN5gLNwoGnq/k88NrxzVstud3FMj2HPGpXocwoGFDnwRbS8TYG7TBsT5xWAQt1/GvrEiby+r1LRV1DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T15:14:24.943487Z"},"content_sha256":"b83ae594d32c1c644e2908bd321b20fd80d45e93ed093ee0af6731c46f82f715","schema_version":"1.0","event_id":"sha256:b83ae594d32c1c644e2908bd321b20fd80d45e93ed093ee0af6731c46f82f715"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WCMZYE6AZHUSLON6RK6QH7PLQH/bundle.json","state_url":"https://pith.science/pith/WCMZYE6AZHUSLON6RK6QH7PLQH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WCMZYE6AZHUSLON6RK6QH7PLQH/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":"2026-08-17T15:14:24Z","links":{"resolver":"https://pith.science/pith/WCMZYE6AZHUSLON6RK6QH7PLQH","bundle":"https://pith.science/pith/WCMZYE6AZHUSLON6RK6QH7PLQH/bundle.json","state":"https://pith.science/pith/WCMZYE6AZHUSLON6RK6QH7PLQH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WCMZYE6AZHUSLON6RK6QH7PLQH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WCMZYE6AZHUSLON6RK6QH7PLQH","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":"fa0f91a6b770ffc9d10ec8d9aac2949b15f00a96992ca7446b6ddaaeca062eea","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-28T13:50:53Z","title_canon_sha256":"348e6828ce77ceec004cd086197ad144269dcf4faf451f654649ebdbd0ba0999"},"schema_version":"1.0","source":{"id":"2507.20842","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.20842","created_at":"2026-07-05T11:44:26Z"},{"alias_kind":"arxiv_version","alias_value":"2507.20842v1","created_at":"2026-07-05T11:44:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.20842","created_at":"2026-07-05T11:44:26Z"},{"alias_kind":"pith_short_12","alias_value":"WCMZYE6AZHUS","created_at":"2026-07-05T11:44:26Z"},{"alias_kind":"pith_short_16","alias_value":"WCMZYE6AZHUSLON6","created_at":"2026-07-05T11:44:26Z"},{"alias_kind":"pith_short_8","alias_value":"WCMZYE6A","created_at":"2026-07-05T11:44:26Z"}],"graph_snapshots":[{"event_id":"sha256:b83ae594d32c1c644e2908bd321b20fd80d45e93ed093ee0af6731c46f82f715","target":"graph","created_at":"2026-07-05T11:44:26Z","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/2507.20842/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision encoders serve as the cornerstone of multimodal understanding. Single-encoder architectures like CLIP exhibit inherent constraints in generalizing across diverse multimodal tasks, while recent multi-encoder fusion methods introduce prohibitive computational overhead to achieve superior performance using complementary visual representations from multiple vision encoders. To address this, we propose a progressive pruning framework, namely Multi-Encoder collaboraTivE tOken pRuning (METEOR), that eliminates redundant visual tokens across the encoding, fusion, and decoding stages for multi-e","authors_text":"Bowen Shi, Chenglin Li, Hongkai Xiong, Qi Tian, Wenrui Dai, Xiaopeng Zhang, Yaoming Wang, Yuchen Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-28T13:50:53Z","title":"METEOR: Multi-Encoder Collaborative Token Pruning for Efficient Vision Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.20842","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":"sha256:986ae3ffbf5dc649e71c655fad9636c30db9670071ca7b4bcf669295879855f4","target":"record","created_at":"2026-07-05T11:44:26Z","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":"fa0f91a6b770ffc9d10ec8d9aac2949b15f00a96992ca7446b6ddaaeca062eea","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-28T13:50:53Z","title_canon_sha256":"348e6828ce77ceec004cd086197ad144269dcf4faf451f654649ebdbd0ba0999"},"schema_version":"1.0","source":{"id":"2507.20842","kind":"arxiv","version":1}},"canonical_sha256":"b0999c13c0c9e925b9be8abd03fdeb81c654fd8eabf633c69b6596aefa0966df","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b0999c13c0c9e925b9be8abd03fdeb81c654fd8eabf633c69b6596aefa0966df","first_computed_at":"2026-07-05T11:44:26.853561Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:44:26.853561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qP+sMrPGHFWlS6fJ36P2TmxsjbkUujktU5aFslDBVIwvcxf6u+ONN64yPti+/KgpnTpWt8fpZIQ/26P8Sj4WCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:44:26.854064Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.20842","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:986ae3ffbf5dc649e71c655fad9636c30db9670071ca7b4bcf669295879855f4","sha256:b83ae594d32c1c644e2908bd321b20fd80d45e93ed093ee0af6731c46f82f715"],"state_sha256":"1b89a7fd6f4ba747de42a1378529580286f4c0fee60adedafaa27fda4862c4c4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4u+E8F66/7AwUyv6DXii1b2sUa4IDGAa2MAkoDQteV4Jz5OX0wPByTNnx3/fVWZhnsgFGTwEwPWyyLwIgBvMBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T15:14:24.949680Z","bundle_sha256":"4dd7967ad2e9050ef6dde46252936e458d4a705c6ba991df3dfdf5c9a649c25f"}}