{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YHCH2VY34UPSVGPQX3TNASRJZ3","short_pith_number":"pith:YHCH2VY3","schema_version":"1.0","canonical_sha256":"c1c47d571be51f2a99f0bee6d04a29cee0ec08c0eb869b19d36aa1bb1970db4a","source":{"kind":"arxiv","id":"2507.09068","version":2},"attestation_state":"computed","paper":{"title":"Infinite Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Changzhi Sun, Dell Zhang, Hao Sun, Jingren Liu, Jixiang Luo, Mengxi Jia, Ruilong Ren, Xiangyu Chen, Xuelong Li","submitted_at":"2025-07-11T23:07:04Z","abstract_excerpt":"The rapid advancements in Large Language Models (LLMs) and their multimodal extensions (MLLMs) have ushered in remarkable progress in video understanding. However, a fundamental challenge persists: effectively processing and comprehending video content that extends beyond minutes or hours. While recent efforts like Video-XL-2 have demonstrated novel architectural solutions for extreme efficiency, and advancements in positional encoding such as HoPE and VideoRoPE++ aim to improve spatio-temporal understanding over extensive contexts, current state-of-the-art models still encounter significant c"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2507.09068","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-11T23:07:04Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG","cs.MM"],"title_canon_sha256":"504899bd77e7b0cada6fba53d7142d7457de5e9ee26730bf19b62a16b9d3fbaa","abstract_canon_sha256":"5e47f513c4c7629e85b3e9fc939cbf89501bd84a64b8942276748dee199551b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:41:44.462593Z","signature_b64":"G5V2Pm5O8wxLM1U/M3zLbWvH4159YnEGty6iLXPKJkjFO9qMfks3FZnwMlbJD3ol7LZ7xwyf++tLhq8QZOEFBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1c47d571be51f2a99f0bee6d04a29cee0ec08c0eb869b19d36aa1bb1970db4a","last_reissued_at":"2026-07-05T11:41:44.462112Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:41:44.462112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Infinite Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Changzhi Sun, Dell Zhang, Hao Sun, Jingren Liu, Jixiang Luo, Mengxi Jia, Ruilong Ren, Xiangyu Chen, Xuelong Li","submitted_at":"2025-07-11T23:07:04Z","abstract_excerpt":"The rapid advancements in Large Language Models (LLMs) and their multimodal extensions (MLLMs) have ushered in remarkable progress in video understanding. However, a fundamental challenge persists: effectively processing and comprehending video content that extends beyond minutes or hours. While recent efforts like Video-XL-2 have demonstrated novel architectural solutions for extreme efficiency, and advancements in positional encoding such as HoPE and VideoRoPE++ aim to improve spatio-temporal understanding over extensive contexts, current state-of-the-art models still encounter significant c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09068","kind":"arxiv","version":2},"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/2507.09068/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2507.09068","created_at":"2026-07-05T11:41:44.462167+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.09068v2","created_at":"2026-07-05T11:41:44.462167+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09068","created_at":"2026-07-05T11:41:44.462167+00:00"},{"alias_kind":"pith_short_12","alias_value":"YHCH2VY34UPS","created_at":"2026-07-05T11:41:44.462167+00:00"},{"alias_kind":"pith_short_16","alias_value":"YHCH2VY34UPSVGPQ","created_at":"2026-07-05T11:41:44.462167+00:00"},{"alias_kind":"pith_short_8","alias_value":"YHCH2VY3","created_at":"2026-07-05T11:41:44.462167+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YHCH2VY34UPSVGPQX3TNASRJZ3","json":"https://pith.science/pith/YHCH2VY34UPSVGPQX3TNASRJZ3.json","graph_json":"https://pith.science/api/pith-number/YHCH2VY34UPSVGPQX3TNASRJZ3/graph.json","events_json":"https://pith.science/api/pith-number/YHCH2VY34UPSVGPQX3TNASRJZ3/events.json","paper":"https://pith.science/paper/YHCH2VY3"},"agent_actions":{"view_html":"https://pith.science/pith/YHCH2VY34UPSVGPQX3TNASRJZ3","download_json":"https://pith.science/pith/YHCH2VY34UPSVGPQX3TNASRJZ3.json","view_paper":"https://pith.science/paper/YHCH2VY3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.09068&json=true","fetch_graph":"https://pith.science/api/pith-number/YHCH2VY34UPSVGPQX3TNASRJZ3/graph.json","fetch_events":"https://pith.science/api/pith-number/YHCH2VY34UPSVGPQX3TNASRJZ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YHCH2VY34UPSVGPQX3TNASRJZ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YHCH2VY34UPSVGPQX3TNASRJZ3/action/storage_attestation","attest_author":"https://pith.science/pith/YHCH2VY34UPSVGPQX3TNASRJZ3/action/author_attestation","sign_citation":"https://pith.science/pith/YHCH2VY34UPSVGPQX3TNASRJZ3/action/citation_signature","submit_replication":"https://pith.science/pith/YHCH2VY34UPSVGPQX3TNASRJZ3/action/replication_record"}},"created_at":"2026-07-05T11:41:44.462167+00:00","updated_at":"2026-07-05T11:41:44.462167+00:00"}