{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TTBVR45UY7XXAWK6JN4YXO7DTI","short_pith_number":"pith:TTBVR45U","canonical_record":{"source":{"id":"2411.08840","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-13T18:19:51Z","cross_cats_sorted":[],"title_canon_sha256":"5f447e221fac4d7bd4d8b50f94177f7db727f6300013c78d0dce9acda9045c14","abstract_canon_sha256":"b470c95a1b2fb5c6a152f65f0311aa45420c018daaa1a8773bbbe6fb42e97ac3"},"schema_version":"1.0"},"canonical_sha256":"9cc358f3b4c7ef70595e4b798bbbe39a18f7829143dff1710bebad0f9345b1c9","source":{"kind":"arxiv","id":"2411.08840","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.08840","created_at":"2026-07-05T09:35:03Z"},{"alias_kind":"arxiv_version","alias_value":"2411.08840v1","created_at":"2026-07-05T09:35:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.08840","created_at":"2026-07-05T09:35:03Z"},{"alias_kind":"pith_short_12","alias_value":"TTBVR45UY7XX","created_at":"2026-07-05T09:35:03Z"},{"alias_kind":"pith_short_16","alias_value":"TTBVR45UY7XXAWK6","created_at":"2026-07-05T09:35:03Z"},{"alias_kind":"pith_short_8","alias_value":"TTBVR45U","created_at":"2026-07-05T09:35:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TTBVR45UY7XXAWK6JN4YXO7DTI","target":"record","payload":{"canonical_record":{"source":{"id":"2411.08840","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-13T18:19:51Z","cross_cats_sorted":[],"title_canon_sha256":"5f447e221fac4d7bd4d8b50f94177f7db727f6300013c78d0dce9acda9045c14","abstract_canon_sha256":"b470c95a1b2fb5c6a152f65f0311aa45420c018daaa1a8773bbbe6fb42e97ac3"},"schema_version":"1.0"},"canonical_sha256":"9cc358f3b4c7ef70595e4b798bbbe39a18f7829143dff1710bebad0f9345b1c9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:35:03.243778Z","signature_b64":"7qJcC7QlAojeOmeweGDDO64LWGdGXVu4dMUzYp77DqiwGrcJ9KYCckD9CiFDOCtxONJHXZQdMq3Kp68QIeSpCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9cc358f3b4c7ef70595e4b798bbbe39a18f7829143dff1710bebad0f9345b1c9","last_reissued_at":"2026-07-05T09:35:03.243352Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:35:03.243352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.08840","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":"2026-07-05T09:35:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wr8CT4QJ+v6IuhsTBy5kAJysj8YqZrh9PvypWEC9QpmyAnmhgeBOJabNMhmU4g4uL8oNNJVs+33GafF9tBtLCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T12:40:25.042279Z"},"content_sha256":"47dd3ab2c0f8fe2be634e71c707028828a4ae8499ef6f6ce9a7ddfa6406fd734","schema_version":"1.0","event_id":"sha256:47dd3ab2c0f8fe2be634e71c707028828a4ae8499ef6f6ce9a7ddfa6406fd734"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TTBVR45UY7XXAWK6JN4YXO7DTI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multimodal Instruction Tuning with Hybrid State Space Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Han Li, Jianing Zhou, Lingyun Wang, Ning Xie, Ruijie Wang, Sheng Liu, Shuai Zhang, Xiaohan Nie","submitted_at":"2024-11-13T18:19:51Z","abstract_excerpt":"Handling lengthy context is crucial for enhancing the recognition and understanding capabilities of multimodal large language models (MLLMs) in applications such as processing high-resolution images or high frame rate videos. The rise in image resolution and frame rate substantially increases computational demands due to the increased number of input tokens. This challenge is further exacerbated by the quadratic complexity with respect to sequence length of the self-attention mechanism. Most prior works either pre-train models with long contexts, overlooking the efficiency problem, or attempt "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.08840","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/2411.08840/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":"2026-07-05T09:35:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HV+mdZBl7NoVsljz1ZkmeaJvpwRjjo9qRgspSNIAJ5srQRc1kJXden1tlnm43vvoR+kA47gEhC9QkgnJ9bsBBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T12:40:25.042882Z"},"content_sha256":"1fa867bc65c9b9d91dc803b525e1852355f97c34ae7a872bf84d9de55f0438a2","schema_version":"1.0","event_id":"sha256:1fa867bc65c9b9d91dc803b525e1852355f97c34ae7a872bf84d9de55f0438a2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TTBVR45UY7XXAWK6JN4YXO7DTI/bundle.json","state_url":"https://pith.science/pith/TTBVR45UY7XXAWK6JN4YXO7DTI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TTBVR45UY7XXAWK6JN4YXO7DTI/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":"2026-08-19T12:40:25Z","links":{"resolver":"https://pith.science/pith/TTBVR45UY7XXAWK6JN4YXO7DTI","bundle":"https://pith.science/pith/TTBVR45UY7XXAWK6JN4YXO7DTI/bundle.json","state":"https://pith.science/pith/TTBVR45UY7XXAWK6JN4YXO7DTI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TTBVR45UY7XXAWK6JN4YXO7DTI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TTBVR45UY7XXAWK6JN4YXO7DTI","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":"b470c95a1b2fb5c6a152f65f0311aa45420c018daaa1a8773bbbe6fb42e97ac3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-13T18:19:51Z","title_canon_sha256":"5f447e221fac4d7bd4d8b50f94177f7db727f6300013c78d0dce9acda9045c14"},"schema_version":"1.0","source":{"id":"2411.08840","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.08840","created_at":"2026-07-05T09:35:03Z"},{"alias_kind":"arxiv_version","alias_value":"2411.08840v1","created_at":"2026-07-05T09:35:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.08840","created_at":"2026-07-05T09:35:03Z"},{"alias_kind":"pith_short_12","alias_value":"TTBVR45UY7XX","created_at":"2026-07-05T09:35:03Z"},{"alias_kind":"pith_short_16","alias_value":"TTBVR45UY7XXAWK6","created_at":"2026-07-05T09:35:03Z"},{"alias_kind":"pith_short_8","alias_value":"TTBVR45U","created_at":"2026-07-05T09:35:03Z"}],"graph_snapshots":[{"event_id":"sha256:1fa867bc65c9b9d91dc803b525e1852355f97c34ae7a872bf84d9de55f0438a2","target":"graph","created_at":"2026-07-05T09:35:03Z","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/2411.08840/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Handling lengthy context is crucial for enhancing the recognition and understanding capabilities of multimodal large language models (MLLMs) in applications such as processing high-resolution images or high frame rate videos. The rise in image resolution and frame rate substantially increases computational demands due to the increased number of input tokens. This challenge is further exacerbated by the quadratic complexity with respect to sequence length of the self-attention mechanism. Most prior works either pre-train models with long contexts, overlooking the efficiency problem, or attempt ","authors_text":"Han Li, Jianing Zhou, Lingyun Wang, Ning Xie, Ruijie Wang, Sheng Liu, Shuai Zhang, Xiaohan Nie","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-13T18:19:51Z","title":"Multimodal Instruction Tuning with Hybrid State Space Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.08840","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":"sha256:47dd3ab2c0f8fe2be634e71c707028828a4ae8499ef6f6ce9a7ddfa6406fd734","target":"record","created_at":"2026-07-05T09:35:03Z","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":"b470c95a1b2fb5c6a152f65f0311aa45420c018daaa1a8773bbbe6fb42e97ac3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-13T18:19:51Z","title_canon_sha256":"5f447e221fac4d7bd4d8b50f94177f7db727f6300013c78d0dce9acda9045c14"},"schema_version":"1.0","source":{"id":"2411.08840","kind":"arxiv","version":1}},"canonical_sha256":"9cc358f3b4c7ef70595e4b798bbbe39a18f7829143dff1710bebad0f9345b1c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9cc358f3b4c7ef70595e4b798bbbe39a18f7829143dff1710bebad0f9345b1c9","first_computed_at":"2026-07-05T09:35:03.243352Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:35:03.243352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7qJcC7QlAojeOmeweGDDO64LWGdGXVu4dMUzYp77DqiwGrcJ9KYCckD9CiFDOCtxONJHXZQdMq3Kp68QIeSpCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:35:03.243778Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.08840","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:47dd3ab2c0f8fe2be634e71c707028828a4ae8499ef6f6ce9a7ddfa6406fd734","sha256:1fa867bc65c9b9d91dc803b525e1852355f97c34ae7a872bf84d9de55f0438a2"],"state_sha256":"b8247beb19b2cd8b693634b8f7876fa78f5f29a0a651f5ad55600b40d0ce9ab4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WNiZYGroNRsL5Yk0oIYGqwMSuOygWSaPLL7lEBuQJIw98Nr68FhAfTMN5PIPnJm92/nHcfUp1gKx1rlqjKIwDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T12:40:25.047603Z","bundle_sha256":"0e3e150d78e0180420425261dfe6627ae33367bdea856bf7f0438e1589e01f0a"}}