{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EORAJE6JRTD7TJBJTZBWDVGG3W","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":"040fd464f9933c791afcd503504d91465cd7be27f7db6f124b77d38faeb2d4d9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-03T12:55:16Z","title_canon_sha256":"f92d0846a218dac390eb69314ad86d37181c53dbab9651ebc00a0409e02732e7"},"schema_version":"1.0","source":{"id":"2507.02591","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.02591","created_at":"2026-07-05T11:41:43Z"},{"alias_kind":"arxiv_version","alias_value":"2507.02591v3","created_at":"2026-07-05T11:41:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02591","created_at":"2026-07-05T11:41:43Z"},{"alias_kind":"pith_short_12","alias_value":"EORAJE6JRTD7","created_at":"2026-07-05T11:41:43Z"},{"alias_kind":"pith_short_16","alias_value":"EORAJE6JRTD7TJBJ","created_at":"2026-07-05T11:41:43Z"},{"alias_kind":"pith_short_8","alias_value":"EORAJE6J","created_at":"2026-07-05T11:41:43Z"}],"graph_snapshots":[{"event_id":"sha256:fe0b472b1e09eba617795a7dfdf8183d17fac955a12eda78b3617bdb6419c42b","target":"graph","created_at":"2026-07-05T11:41:43Z","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/2507.02591/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The challenge of long video understanding lies in its high computational complexity and prohibitive memory cost, since the memory and computation required by transformer-based LLMs scale quadratically with input sequence length. We propose AuroraLong to address this challenge by replacing the LLM component in MLLMs with a linear RNN language model that handles input sequence of arbitrary length with constant-size hidden states. To further increase throughput and efficiency, we combine visual token merge with linear RNN models by reordering the visual tokens by their sizes in ascending order. D","authors_text":"Enxin Song, Gaoang Wang, Tian Ye, Weili Xu, Wenhao Chai, Xuexiang Wen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-03T12:55:16Z","title":"AuroraLong: Bringing RNNs Back to Efficient Open-Ended Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02591","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":"sha256:858ddd7b810e33be9e9740de1f8c1a41b55e93a2054f16de974f3b5e425225c3","target":"record","created_at":"2026-07-05T11:41:43Z","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":"040fd464f9933c791afcd503504d91465cd7be27f7db6f124b77d38faeb2d4d9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-03T12:55:16Z","title_canon_sha256":"f92d0846a218dac390eb69314ad86d37181c53dbab9651ebc00a0409e02732e7"},"schema_version":"1.0","source":{"id":"2507.02591","kind":"arxiv","version":3}},"canonical_sha256":"23a20493c98cc7f9a4299e4361d4c6ddb4ffd277dac81f50879b9bf620ff0860","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23a20493c98cc7f9a4299e4361d4c6ddb4ffd277dac81f50879b9bf620ff0860","first_computed_at":"2026-07-05T11:41:43.739295Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:41:43.739295Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wUMgNzv3AHqV9WZxTyjXnjFPyWT4AHfsOQ04cuBuL9a6SIjha9+v9VcIv8OVNk2gm2YjbUQMW1kt569C9WWzAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:41:43.739758Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.02591","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:858ddd7b810e33be9e9740de1f8c1a41b55e93a2054f16de974f3b5e425225c3","sha256:fe0b472b1e09eba617795a7dfdf8183d17fac955a12eda78b3617bdb6419c42b"],"state_sha256":"8f79d8234cb3058228a67975594720b2db6fc8aff9d15e62196dcaf97ea77f79"}