{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4S5AL3B24HVIYDFKF6KBF62C4E","short_pith_number":"pith:4S5AL3B2","canonical_record":{"source":{"id":"2410.02745","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-20T10:50:21Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"73975adf3906c8925b7a0bb732788abc9eb13bba2a3c039fdf03e5a77bb054cb","abstract_canon_sha256":"26b7d4ee79deb9b2defd216396cf2bce87243c224fb3d0335a1d4a21b5dd3b6e"},"schema_version":"1.0"},"canonical_sha256":"e4ba05ec3ae1ea8c0caa2f9412fb42e139d73a002ead5c616ccc6c508203852d","source":{"kind":"arxiv","id":"2410.02745","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.02745","created_at":"2026-07-05T11:49:04Z"},{"alias_kind":"arxiv_version","alias_value":"2410.02745v3","created_at":"2026-07-05T11:49:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02745","created_at":"2026-07-05T11:49:04Z"},{"alias_kind":"pith_short_12","alias_value":"4S5AL3B24HVI","created_at":"2026-07-05T11:49:04Z"},{"alias_kind":"pith_short_16","alias_value":"4S5AL3B24HVIYDFK","created_at":"2026-07-05T11:49:04Z"},{"alias_kind":"pith_short_8","alias_value":"4S5AL3B2","created_at":"2026-07-05T11:49:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4S5AL3B24HVIYDFKF6KBF62C4E","target":"record","payload":{"canonical_record":{"source":{"id":"2410.02745","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-20T10:50:21Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"73975adf3906c8925b7a0bb732788abc9eb13bba2a3c039fdf03e5a77bb054cb","abstract_canon_sha256":"26b7d4ee79deb9b2defd216396cf2bce87243c224fb3d0335a1d4a21b5dd3b6e"},"schema_version":"1.0"},"canonical_sha256":"e4ba05ec3ae1ea8c0caa2f9412fb42e139d73a002ead5c616ccc6c508203852d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:04.383974Z","signature_b64":"Q0YQlLRrb9MxZA65CIzQlKFm78DzclXhGWYNGrRbuMWOlo/eBHSEqWHsEOuC+ZeQiogPSnR6pJ2VzGYz5VGeCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4ba05ec3ae1ea8c0caa2f9412fb42e139d73a002ead5c616ccc6c508203852d","last_reissued_at":"2026-07-05T11:49:04.383516Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:04.383516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.02745","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:49:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t7GNXX4JMx2u3wqelKYvFrwdemvVEECWjtcyZu9yuuMnBZp/TqzB/7WdzpcVrh63nMOslwxDPDg6ty6Rxi8JDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T23:29:46.671282Z"},"content_sha256":"3fbc9befe47000fd3dab4eadca6ef18efd0b85d9e2b7c8732982d27925f6d168","schema_version":"1.0","event_id":"sha256:3fbc9befe47000fd3dab4eadca6ef18efd0b85d9e2b7c8732982d27925f6d168"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4S5AL3B24HVIYDFKF6KBF62C4E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AVG-LLaVA: An Efficient Large Multimodal Model with Adaptive Visual Granularity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Fandong Meng, Jie Zhou, Jinsong Su, Liqiang Niu, Wenbo Li, Zhibin Lan","submitted_at":"2024-09-20T10:50:21Z","abstract_excerpt":"Recently, large multimodal models (LMMs) have achieved significant advancements. When dealing with high-resolution images, dominant LMMs typically divide them into multiple local images and a global image, leading to a large number of visual tokens. In this work, we introduce AVG-LLaVA, an LMM that can adaptively select the appropriate visual granularity based on the input image and instruction. Specifically, we first apply the multiple pooling layers to obtain visual tokens at different granularities. Then we propose a visual granularity router, which includes a Transformer layer, an MLP laye"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02745","kind":"arxiv","version":3},"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/2410.02745/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":"2026-07-05T11:49:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GQ9tfwKeqMxpBANQE2El1XGbCodeZ5YsOgAMyU8kpUhJoS8GReYa0M8GuUdsNVIFR8Mxk51Uu83mu6kBoZgvCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T23:29:46.671799Z"},"content_sha256":"dcb345ba104c1b0bbf6405a46c041886bcf319df03d034dc352bdcbec93da21b","schema_version":"1.0","event_id":"sha256:dcb345ba104c1b0bbf6405a46c041886bcf319df03d034dc352bdcbec93da21b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4S5AL3B24HVIYDFKF6KBF62C4E/bundle.json","state_url":"https://pith.science/pith/4S5AL3B24HVIYDFKF6KBF62C4E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4S5AL3B24HVIYDFKF6KBF62C4E/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":"2026-08-09T23:29:46Z","links":{"resolver":"https://pith.science/pith/4S5AL3B24HVIYDFKF6KBF62C4E","bundle":"https://pith.science/pith/4S5AL3B24HVIYDFKF6KBF62C4E/bundle.json","state":"https://pith.science/pith/4S5AL3B24HVIYDFKF6KBF62C4E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4S5AL3B24HVIYDFKF6KBF62C4E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4S5AL3B24HVIYDFKF6KBF62C4E","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":"26b7d4ee79deb9b2defd216396cf2bce87243c224fb3d0335a1d4a21b5dd3b6e","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-20T10:50:21Z","title_canon_sha256":"73975adf3906c8925b7a0bb732788abc9eb13bba2a3c039fdf03e5a77bb054cb"},"schema_version":"1.0","source":{"id":"2410.02745","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.02745","created_at":"2026-07-05T11:49:04Z"},{"alias_kind":"arxiv_version","alias_value":"2410.02745v3","created_at":"2026-07-05T11:49:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02745","created_at":"2026-07-05T11:49:04Z"},{"alias_kind":"pith_short_12","alias_value":"4S5AL3B24HVI","created_at":"2026-07-05T11:49:04Z"},{"alias_kind":"pith_short_16","alias_value":"4S5AL3B24HVIYDFK","created_at":"2026-07-05T11:49:04Z"},{"alias_kind":"pith_short_8","alias_value":"4S5AL3B2","created_at":"2026-07-05T11:49:04Z"}],"graph_snapshots":[{"event_id":"sha256:dcb345ba104c1b0bbf6405a46c041886bcf319df03d034dc352bdcbec93da21b","target":"graph","created_at":"2026-07-05T11:49:04Z","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/2410.02745/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, large multimodal models (LMMs) have achieved significant advancements. When dealing with high-resolution images, dominant LMMs typically divide them into multiple local images and a global image, leading to a large number of visual tokens. In this work, we introduce AVG-LLaVA, an LMM that can adaptively select the appropriate visual granularity based on the input image and instruction. Specifically, we first apply the multiple pooling layers to obtain visual tokens at different granularities. Then we propose a visual granularity router, which includes a Transformer layer, an MLP laye","authors_text":"Fandong Meng, Jie Zhou, Jinsong Su, Liqiang Niu, Wenbo Li, Zhibin Lan","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-20T10:50:21Z","title":"AVG-LLaVA: An Efficient Large Multimodal Model with Adaptive Visual Granularity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02745","kind":"arxiv","version":3},"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":"sha256:3fbc9befe47000fd3dab4eadca6ef18efd0b85d9e2b7c8732982d27925f6d168","target":"record","created_at":"2026-07-05T11:49:04Z","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":"26b7d4ee79deb9b2defd216396cf2bce87243c224fb3d0335a1d4a21b5dd3b6e","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-20T10:50:21Z","title_canon_sha256":"73975adf3906c8925b7a0bb732788abc9eb13bba2a3c039fdf03e5a77bb054cb"},"schema_version":"1.0","source":{"id":"2410.02745","kind":"arxiv","version":3}},"canonical_sha256":"e4ba05ec3ae1ea8c0caa2f9412fb42e139d73a002ead5c616ccc6c508203852d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e4ba05ec3ae1ea8c0caa2f9412fb42e139d73a002ead5c616ccc6c508203852d","first_computed_at":"2026-07-05T11:49:04.383516Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:49:04.383516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q0YQlLRrb9MxZA65CIzQlKFm78DzclXhGWYNGrRbuMWOlo/eBHSEqWHsEOuC+ZeQiogPSnR6pJ2VzGYz5VGeCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:49:04.383974Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.02745","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3fbc9befe47000fd3dab4eadca6ef18efd0b85d9e2b7c8732982d27925f6d168","sha256:dcb345ba104c1b0bbf6405a46c041886bcf319df03d034dc352bdcbec93da21b"],"state_sha256":"dd8fd1abad706e988a8d5c2ee3bb99b4afcd95906cbe2868591c7076bc0a5822"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q59RScuXwk4o1V2KCTmhXIFdstIjST7ay4PDpBmfNJxCsbkGzFT3zDJ0pzUd0yTD/KwWXq0VqDUDYIiBX/exCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T23:29:46.676891Z","bundle_sha256":"51ef888e1d2f7b0dc86d41b69981b45389093fa756899f416b64765346c6b0c5"}}