{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:G3HZWKGES57YTPYT3DOBWHXCEJ","short_pith_number":"pith:G3HZWKGE","canonical_record":{"source":{"id":"2504.01328","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-02T03:24:58Z","cross_cats_sorted":[],"title_canon_sha256":"671ced2c663cffe6af5eba633748fa9b9389e80b1adc104878d49142c11448c3","abstract_canon_sha256":"925d8332a22a39ec0f19b1d32312dc9a2307f54dfa5c4b3aece3288ae595f737"},"schema_version":"1.0"},"canonical_sha256":"36cf9b28c4977f89bf13d8dc1b1ee22271ba77f2817854329c587b5a2c78d133","source":{"kind":"arxiv","id":"2504.01328","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.01328","created_at":"2026-07-05T10:43:13Z"},{"alias_kind":"arxiv_version","alias_value":"2504.01328v1","created_at":"2026-07-05T10:43:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.01328","created_at":"2026-07-05T10:43:13Z"},{"alias_kind":"pith_short_12","alias_value":"G3HZWKGES57Y","created_at":"2026-07-05T10:43:13Z"},{"alias_kind":"pith_short_16","alias_value":"G3HZWKGES57YTPYT","created_at":"2026-07-05T10:43:13Z"},{"alias_kind":"pith_short_8","alias_value":"G3HZWKGE","created_at":"2026-07-05T10:43:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:G3HZWKGES57YTPYT3DOBWHXCEJ","target":"record","payload":{"canonical_record":{"source":{"id":"2504.01328","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-02T03:24:58Z","cross_cats_sorted":[],"title_canon_sha256":"671ced2c663cffe6af5eba633748fa9b9389e80b1adc104878d49142c11448c3","abstract_canon_sha256":"925d8332a22a39ec0f19b1d32312dc9a2307f54dfa5c4b3aece3288ae595f737"},"schema_version":"1.0"},"canonical_sha256":"36cf9b28c4977f89bf13d8dc1b1ee22271ba77f2817854329c587b5a2c78d133","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:13.069099Z","signature_b64":"FWBjM0+TkFLtDHKWIgo2vAriEoSY/RPE4L939/2vHxAX02HmKPxD4Dxuzdq9/l8ivDMLKPgV0ZdIWjiuZQX2DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36cf9b28c4977f89bf13d8dc1b1ee22271ba77f2817854329c587b5a2c78d133","last_reissued_at":"2026-07-05T10:43:13.068635Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:13.068635Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.01328","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":"2026-07-05T10:43:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gR+VbmC5k6C9YeyUfrtN6ZKzM5B3VTPVwoP0dauR+x/Q9Ljx1nGVvUgAjmWWFVbQUSIkYU8YkP/qa4k2Zmf5Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T07:19:40.345823Z"},"content_sha256":"ac3b12f357060fe2b7ad638be8d5462accb0133665e1b6310545b56833222e5d","schema_version":"1.0","event_id":"sha256:ac3b12f357060fe2b7ad638be8d5462accb0133665e1b6310545b56833222e5d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:G3HZWKGES57YTPYT3DOBWHXCEJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Slow-Fast Architecture for Video Multi-Modal Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chieh-Yun Chen, Guilin Liu, Humphrey Shi, Jitesh Jain, Junjun Xiong, Kai Wang, Min Shi, Shihao Wang, Zhiding Yu","submitted_at":"2025-04-02T03:24:58Z","abstract_excerpt":"Balancing temporal resolution and spatial detail under limited compute budget remains a key challenge for video-based multi-modal large language models (MLLMs). Existing methods typically compress video representations using predefined rules before feeding them into the LLM, resulting in irreversible information loss and often ignoring input instructions. To address this, we propose a novel slow-fast architecture that naturally circumvents this trade-off, enabling the use of more input frames while preserving spatial details. Inspired by how humans first skim a video before focusing on relevan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.01328","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/2504.01328/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":"2026-07-05T10:43:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8jrWo/QsukncLtweYVoOaalQOyoT+9pAXlfigzGBYVOWhs/zIWhHvFJFqRt9WDfo403jXnPHVYgV/x9NoyhGDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T07:19:40.346725Z"},"content_sha256":"2e321cba8ef12341e8c5b840d42c28a0b3a36b5d78dd57fef5165789b3469fd4","schema_version":"1.0","event_id":"sha256:2e321cba8ef12341e8c5b840d42c28a0b3a36b5d78dd57fef5165789b3469fd4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G3HZWKGES57YTPYT3DOBWHXCEJ/bundle.json","state_url":"https://pith.science/pith/G3HZWKGES57YTPYT3DOBWHXCEJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G3HZWKGES57YTPYT3DOBWHXCEJ/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":"2026-08-11T07:19:40Z","links":{"resolver":"https://pith.science/pith/G3HZWKGES57YTPYT3DOBWHXCEJ","bundle":"https://pith.science/pith/G3HZWKGES57YTPYT3DOBWHXCEJ/bundle.json","state":"https://pith.science/pith/G3HZWKGES57YTPYT3DOBWHXCEJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G3HZWKGES57YTPYT3DOBWHXCEJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:G3HZWKGES57YTPYT3DOBWHXCEJ","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":"925d8332a22a39ec0f19b1d32312dc9a2307f54dfa5c4b3aece3288ae595f737","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-02T03:24:58Z","title_canon_sha256":"671ced2c663cffe6af5eba633748fa9b9389e80b1adc104878d49142c11448c3"},"schema_version":"1.0","source":{"id":"2504.01328","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.01328","created_at":"2026-07-05T10:43:13Z"},{"alias_kind":"arxiv_version","alias_value":"2504.01328v1","created_at":"2026-07-05T10:43:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.01328","created_at":"2026-07-05T10:43:13Z"},{"alias_kind":"pith_short_12","alias_value":"G3HZWKGES57Y","created_at":"2026-07-05T10:43:13Z"},{"alias_kind":"pith_short_16","alias_value":"G3HZWKGES57YTPYT","created_at":"2026-07-05T10:43:13Z"},{"alias_kind":"pith_short_8","alias_value":"G3HZWKGE","created_at":"2026-07-05T10:43:13Z"}],"graph_snapshots":[{"event_id":"sha256:2e321cba8ef12341e8c5b840d42c28a0b3a36b5d78dd57fef5165789b3469fd4","target":"graph","created_at":"2026-07-05T10:43:13Z","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/2504.01328/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Balancing temporal resolution and spatial detail under limited compute budget remains a key challenge for video-based multi-modal large language models (MLLMs). Existing methods typically compress video representations using predefined rules before feeding them into the LLM, resulting in irreversible information loss and often ignoring input instructions. To address this, we propose a novel slow-fast architecture that naturally circumvents this trade-off, enabling the use of more input frames while preserving spatial details. Inspired by how humans first skim a video before focusing on relevan","authors_text":"Chieh-Yun Chen, Guilin Liu, Humphrey Shi, Jitesh Jain, Junjun Xiong, Kai Wang, Min Shi, Shihao Wang, Zhiding Yu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-02T03:24:58Z","title":"Slow-Fast Architecture for Video Multi-Modal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.01328","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:ac3b12f357060fe2b7ad638be8d5462accb0133665e1b6310545b56833222e5d","target":"record","created_at":"2026-07-05T10:43:13Z","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":"925d8332a22a39ec0f19b1d32312dc9a2307f54dfa5c4b3aece3288ae595f737","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-02T03:24:58Z","title_canon_sha256":"671ced2c663cffe6af5eba633748fa9b9389e80b1adc104878d49142c11448c3"},"schema_version":"1.0","source":{"id":"2504.01328","kind":"arxiv","version":1}},"canonical_sha256":"36cf9b28c4977f89bf13d8dc1b1ee22271ba77f2817854329c587b5a2c78d133","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"36cf9b28c4977f89bf13d8dc1b1ee22271ba77f2817854329c587b5a2c78d133","first_computed_at":"2026-07-05T10:43:13.068635Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:43:13.068635Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FWBjM0+TkFLtDHKWIgo2vAriEoSY/RPE4L939/2vHxAX02HmKPxD4Dxuzdq9/l8ivDMLKPgV0ZdIWjiuZQX2DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:43:13.069099Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.01328","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac3b12f357060fe2b7ad638be8d5462accb0133665e1b6310545b56833222e5d","sha256:2e321cba8ef12341e8c5b840d42c28a0b3a36b5d78dd57fef5165789b3469fd4"],"state_sha256":"08bcf1080621f841663c931b6cb4fd2f694d6a20f6fb5d8b9b37f6f51323fb23"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4GD9FJNGfeD5d9zjJs8R0/6iaxkbn978PvoiQ9WN2wfR4BgDDX1Qt3bhinQX2pdIqMzAyfOUmKMVfZZWkfEgDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T07:19:40.354804Z","bundle_sha256":"67eb87332befa5c6d24551be6a43cf3966f14c1c0816edf5885580c46cd05a95"}}