{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VDFWFBKD6BSKLTWZQ5PWBARQIT","short_pith_number":"pith:VDFWFBKD","canonical_record":{"source":{"id":"2410.10319","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-14T09:25:09Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"c8e4d87f53dae5a87e8b158c534749a7d6ece8961b1302eab98bd2faf22b191f","abstract_canon_sha256":"e710946dd72c74d57f91775f061d9cc8a3e5a3b40a5b980837812fa2d4a86135"},"schema_version":"1.0"},"canonical_sha256":"a8cb628543f064a5ced9875f60823044ce2f758be1d61c5c1c88f8870f4b892a","source":{"kind":"arxiv","id":"2410.10319","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.10319","created_at":"2026-07-05T09:20:14Z"},{"alias_kind":"arxiv_version","alias_value":"2410.10319v1","created_at":"2026-07-05T09:20:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10319","created_at":"2026-07-05T09:20:14Z"},{"alias_kind":"pith_short_12","alias_value":"VDFWFBKD6BSK","created_at":"2026-07-05T09:20:14Z"},{"alias_kind":"pith_short_16","alias_value":"VDFWFBKD6BSKLTWZ","created_at":"2026-07-05T09:20:14Z"},{"alias_kind":"pith_short_8","alias_value":"VDFWFBKD","created_at":"2026-07-05T09:20:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VDFWFBKD6BSKLTWZQ5PWBARQIT","target":"record","payload":{"canonical_record":{"source":{"id":"2410.10319","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-14T09:25:09Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"c8e4d87f53dae5a87e8b158c534749a7d6ece8961b1302eab98bd2faf22b191f","abstract_canon_sha256":"e710946dd72c74d57f91775f061d9cc8a3e5a3b40a5b980837812fa2d4a86135"},"schema_version":"1.0"},"canonical_sha256":"a8cb628543f064a5ced9875f60823044ce2f758be1d61c5c1c88f8870f4b892a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:14.852869Z","signature_b64":"MK4PUqL54GDmTnKlBeD4UrrwCch5RIBonX4mtYzHXyrO62Ggvc3E/VSYFya7uFvFfd4t06prMod1uTfisOwTDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8cb628543f064a5ced9875f60823044ce2f758be1d61c5c1c88f8870f4b892a","last_reissued_at":"2026-07-05T09:20:14.852486Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:14.852486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.10319","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":"2026-07-05T09:20:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B3LOs6jooZ2TufLNgmzD6Y2Kl0XGwnEQlGaHuWKhYpk/o7i3LdoqUP5PiOWLiaPAqh1+l5YW6bkw+432L/aYAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T21:33:23.840690Z"},"content_sha256":"0258e04475584505aec5e5e77a7d9159ef8d1a290ae1e1e48359dd5c7e0bda7a","schema_version":"1.0","event_id":"sha256:0258e04475584505aec5e5e77a7d9159ef8d1a290ae1e1e48359dd5c7e0bda7a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VDFWFBKD6BSKLTWZQ5PWBARQIT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Spatial-Aware Efficient Projector for MLLMs via Multi-Layer Feature Aggregation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Baoxun Wang, Bingquan Liu, Chengjie Sun, Shun Qian, Zhen Xu","submitted_at":"2024-10-14T09:25:09Z","abstract_excerpt":"The projector plays a crucial role in multi-modal language models (MLLMs). The number of visual tokens it outputs affects the efficiency of the MLLM, while the quality of the visual tokens influences the visual understanding capabilities of the MLLM. Current explorations on the projector focus on reducing the number of visual tokens to improve efficiency, often overlooking the inherent spatial discrepancy between the serialized 2-dimensional visual token sequences and natural language token sequences. A Spatial-Aware Efficient Projector (SAEP) is proposed to address this issue. In detail, our "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10319","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/2410.10319/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":"2026-07-05T09:20:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OorPBB0c0zG/DqYJdd6WKB/DP9GN1SyYeyuRTykA5OizPStBe+Yy4weJV1bpDSP8gG1h1HKrXOUuvzyiQ0mOBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T21:33:23.841180Z"},"content_sha256":"767a1873a8c69639b685c1b87aa266ddc3b4b3b495e1d3d8c428ba197c77dbfc","schema_version":"1.0","event_id":"sha256:767a1873a8c69639b685c1b87aa266ddc3b4b3b495e1d3d8c428ba197c77dbfc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VDFWFBKD6BSKLTWZQ5PWBARQIT/bundle.json","state_url":"https://pith.science/pith/VDFWFBKD6BSKLTWZQ5PWBARQIT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VDFWFBKD6BSKLTWZQ5PWBARQIT/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":"2026-08-08T21:33:23Z","links":{"resolver":"https://pith.science/pith/VDFWFBKD6BSKLTWZQ5PWBARQIT","bundle":"https://pith.science/pith/VDFWFBKD6BSKLTWZQ5PWBARQIT/bundle.json","state":"https://pith.science/pith/VDFWFBKD6BSKLTWZQ5PWBARQIT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VDFWFBKD6BSKLTWZQ5PWBARQIT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VDFWFBKD6BSKLTWZQ5PWBARQIT","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":"e710946dd72c74d57f91775f061d9cc8a3e5a3b40a5b980837812fa2d4a86135","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-14T09:25:09Z","title_canon_sha256":"c8e4d87f53dae5a87e8b158c534749a7d6ece8961b1302eab98bd2faf22b191f"},"schema_version":"1.0","source":{"id":"2410.10319","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.10319","created_at":"2026-07-05T09:20:14Z"},{"alias_kind":"arxiv_version","alias_value":"2410.10319v1","created_at":"2026-07-05T09:20:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10319","created_at":"2026-07-05T09:20:14Z"},{"alias_kind":"pith_short_12","alias_value":"VDFWFBKD6BSK","created_at":"2026-07-05T09:20:14Z"},{"alias_kind":"pith_short_16","alias_value":"VDFWFBKD6BSKLTWZ","created_at":"2026-07-05T09:20:14Z"},{"alias_kind":"pith_short_8","alias_value":"VDFWFBKD","created_at":"2026-07-05T09:20:14Z"}],"graph_snapshots":[{"event_id":"sha256:767a1873a8c69639b685c1b87aa266ddc3b4b3b495e1d3d8c428ba197c77dbfc","target":"graph","created_at":"2026-07-05T09:20:14Z","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/2410.10319/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The projector plays a crucial role in multi-modal language models (MLLMs). The number of visual tokens it outputs affects the efficiency of the MLLM, while the quality of the visual tokens influences the visual understanding capabilities of the MLLM. Current explorations on the projector focus on reducing the number of visual tokens to improve efficiency, often overlooking the inherent spatial discrepancy between the serialized 2-dimensional visual token sequences and natural language token sequences. A Spatial-Aware Efficient Projector (SAEP) is proposed to address this issue. In detail, our ","authors_text":"Baoxun Wang, Bingquan Liu, Chengjie Sun, Shun Qian, Zhen Xu","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-14T09:25:09Z","title":"Spatial-Aware Efficient Projector for MLLMs via Multi-Layer Feature Aggregation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10319","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":"sha256:0258e04475584505aec5e5e77a7d9159ef8d1a290ae1e1e48359dd5c7e0bda7a","target":"record","created_at":"2026-07-05T09:20:14Z","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":"e710946dd72c74d57f91775f061d9cc8a3e5a3b40a5b980837812fa2d4a86135","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-14T09:25:09Z","title_canon_sha256":"c8e4d87f53dae5a87e8b158c534749a7d6ece8961b1302eab98bd2faf22b191f"},"schema_version":"1.0","source":{"id":"2410.10319","kind":"arxiv","version":1}},"canonical_sha256":"a8cb628543f064a5ced9875f60823044ce2f758be1d61c5c1c88f8870f4b892a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a8cb628543f064a5ced9875f60823044ce2f758be1d61c5c1c88f8870f4b892a","first_computed_at":"2026-07-05T09:20:14.852486Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:20:14.852486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MK4PUqL54GDmTnKlBeD4UrrwCch5RIBonX4mtYzHXyrO62Ggvc3E/VSYFya7uFvFfd4t06prMod1uTfisOwTDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:20:14.852869Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.10319","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0258e04475584505aec5e5e77a7d9159ef8d1a290ae1e1e48359dd5c7e0bda7a","sha256:767a1873a8c69639b685c1b87aa266ddc3b4b3b495e1d3d8c428ba197c77dbfc"],"state_sha256":"69638a1046259765a75f1b891c48a937e021608960e56cbceba9df5d034dc3de"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cFNcbbGv6Q/SoBsd9s2GFMoDAEe0oAqgK1+M877ZIR/R5pMu5mLsng9e6IhgQwSOgMbcvkxwPP9CHFd9hq5xAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T21:33:23.845879Z","bundle_sha256":"0b439dc2efeb92f6e9f9d84587d7fedfbd66049bbab1a17a3e846167c49dd3c8"}}