{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FFW334MDOOQ6T7V7AEIKBZNXUW","short_pith_number":"pith:FFW334MD","canonical_record":{"source":{"id":"2408.14023","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-26T05:27:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"48629f159ad2e1dc8527f12e636bca9df51167e6077ea5e9f4f1f1959fb633fd","abstract_canon_sha256":"93a7f5d03a9a8fdf49041af1da15703e7527883d4e2840ed05baea3b6dcb68d3"},"schema_version":"1.0"},"canonical_sha256":"296dbdf18373a1e9febf0110a0e5b7a584a35e89015b1b53e3ec3d7eb64054e0","source":{"kind":"arxiv","id":"2408.14023","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.14023","created_at":"2026-07-05T08:59:15Z"},{"alias_kind":"arxiv_version","alias_value":"2408.14023v1","created_at":"2026-07-05T08:59:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.14023","created_at":"2026-07-05T08:59:15Z"},{"alias_kind":"pith_short_12","alias_value":"FFW334MDOOQ6","created_at":"2026-07-05T08:59:15Z"},{"alias_kind":"pith_short_16","alias_value":"FFW334MDOOQ6T7V7","created_at":"2026-07-05T08:59:15Z"},{"alias_kind":"pith_short_8","alias_value":"FFW334MD","created_at":"2026-07-05T08:59:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FFW334MDOOQ6T7V7AEIKBZNXUW","target":"record","payload":{"canonical_record":{"source":{"id":"2408.14023","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-26T05:27:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"48629f159ad2e1dc8527f12e636bca9df51167e6077ea5e9f4f1f1959fb633fd","abstract_canon_sha256":"93a7f5d03a9a8fdf49041af1da15703e7527883d4e2840ed05baea3b6dcb68d3"},"schema_version":"1.0"},"canonical_sha256":"296dbdf18373a1e9febf0110a0e5b7a584a35e89015b1b53e3ec3d7eb64054e0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:59:15.064376Z","signature_b64":"ZBcJ+dVhZWpsnEeu+j+paAz65COKEcroxxHg8/cFJT61uFDYK4Qf5UfB5CDPji642gWfbeVLq3GUG4tG1mt3Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"296dbdf18373a1e9febf0110a0e5b7a584a35e89015b1b53e3ec3d7eb64054e0","last_reissued_at":"2026-07-05T08:59:15.063892Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:59:15.063892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.14023","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":"2026-07-05T08:59:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/7sm7iOG7pkGQeHD0ad73BprGaNWQn6zCNe2WiZJNUH/A3zmPXRxveRRiHO8E5/Bed6fi6dI8qVifi+3FQRXDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T05:05:01.098626Z"},"content_sha256":"acb4fef561540be6e535747c50b0a19a2f26821ec72f2e938fa578c0f92749ba","schema_version":"1.0","event_id":"sha256:acb4fef561540be6e535747c50b0a19a2f26821ec72f2e938fa578c0f92749ba"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FFW334MDOOQ6T7V7AEIKBZNXUW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Video-CCAM: Enhancing Video-Language Understanding with Causal Cross-Attention Masks for Short and Long Videos","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dian Li, Gang Liu, Hui Wang, Jiajun Fei, Zekun Wang, Zhidong Deng","submitted_at":"2024-08-26T05:27:14Z","abstract_excerpt":"Multi-modal large language models (MLLMs) have demonstrated considerable potential across various downstream tasks that require cross-domain knowledge. MLLMs capable of processing videos, known as Video-MLLMs, have attracted broad interest in video-language understanding. However, videos, especially long videos, contain more visual tokens than images, making them difficult for LLMs to process. Existing works either downsample visual features or extend the LLM context size, risking the loss of high-resolution information or slowing down inference speed. To address these limitations, we apply cr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.14023","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/2408.14023/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":"2026-07-05T08:59:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NyU4BS9PMK+A2tr3+kH4PNtHxzd6c8aIKUYhKoWh+Bc7fIX5+Spec3meSc6WcWqRYDFBq7Py9uCeK6rmzusgBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T05:05:01.099527Z"},"content_sha256":"3d9491c79b5467502781039e15ac38cf63cf7524c5d4e5c57918aedca20e9084","schema_version":"1.0","event_id":"sha256:3d9491c79b5467502781039e15ac38cf63cf7524c5d4e5c57918aedca20e9084"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FFW334MDOOQ6T7V7AEIKBZNXUW/bundle.json","state_url":"https://pith.science/pith/FFW334MDOOQ6T7V7AEIKBZNXUW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FFW334MDOOQ6T7V7AEIKBZNXUW/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":"2026-08-05T05:05:01Z","links":{"resolver":"https://pith.science/pith/FFW334MDOOQ6T7V7AEIKBZNXUW","bundle":"https://pith.science/pith/FFW334MDOOQ6T7V7AEIKBZNXUW/bundle.json","state":"https://pith.science/pith/FFW334MDOOQ6T7V7AEIKBZNXUW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FFW334MDOOQ6T7V7AEIKBZNXUW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FFW334MDOOQ6T7V7AEIKBZNXUW","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":"93a7f5d03a9a8fdf49041af1da15703e7527883d4e2840ed05baea3b6dcb68d3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-26T05:27:14Z","title_canon_sha256":"48629f159ad2e1dc8527f12e636bca9df51167e6077ea5e9f4f1f1959fb633fd"},"schema_version":"1.0","source":{"id":"2408.14023","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.14023","created_at":"2026-07-05T08:59:15Z"},{"alias_kind":"arxiv_version","alias_value":"2408.14023v1","created_at":"2026-07-05T08:59:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.14023","created_at":"2026-07-05T08:59:15Z"},{"alias_kind":"pith_short_12","alias_value":"FFW334MDOOQ6","created_at":"2026-07-05T08:59:15Z"},{"alias_kind":"pith_short_16","alias_value":"FFW334MDOOQ6T7V7","created_at":"2026-07-05T08:59:15Z"},{"alias_kind":"pith_short_8","alias_value":"FFW334MD","created_at":"2026-07-05T08:59:15Z"}],"graph_snapshots":[{"event_id":"sha256:3d9491c79b5467502781039e15ac38cf63cf7524c5d4e5c57918aedca20e9084","target":"graph","created_at":"2026-07-05T08:59:15Z","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/2408.14023/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modal large language models (MLLMs) have demonstrated considerable potential across various downstream tasks that require cross-domain knowledge. MLLMs capable of processing videos, known as Video-MLLMs, have attracted broad interest in video-language understanding. However, videos, especially long videos, contain more visual tokens than images, making them difficult for LLMs to process. Existing works either downsample visual features or extend the LLM context size, risking the loss of high-resolution information or slowing down inference speed. To address these limitations, we apply cr","authors_text":"Dian Li, Gang Liu, Hui Wang, Jiajun Fei, Zekun Wang, Zhidong Deng","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-26T05:27:14Z","title":"Video-CCAM: Enhancing Video-Language Understanding with Causal Cross-Attention Masks for Short and Long Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.14023","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:acb4fef561540be6e535747c50b0a19a2f26821ec72f2e938fa578c0f92749ba","target":"record","created_at":"2026-07-05T08:59:15Z","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":"93a7f5d03a9a8fdf49041af1da15703e7527883d4e2840ed05baea3b6dcb68d3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-26T05:27:14Z","title_canon_sha256":"48629f159ad2e1dc8527f12e636bca9df51167e6077ea5e9f4f1f1959fb633fd"},"schema_version":"1.0","source":{"id":"2408.14023","kind":"arxiv","version":1}},"canonical_sha256":"296dbdf18373a1e9febf0110a0e5b7a584a35e89015b1b53e3ec3d7eb64054e0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"296dbdf18373a1e9febf0110a0e5b7a584a35e89015b1b53e3ec3d7eb64054e0","first_computed_at":"2026-07-05T08:59:15.063892Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:59:15.063892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZBcJ+dVhZWpsnEeu+j+paAz65COKEcroxxHg8/cFJT61uFDYK4Qf5UfB5CDPji642gWfbeVLq3GUG4tG1mt3Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:59:15.064376Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.14023","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:acb4fef561540be6e535747c50b0a19a2f26821ec72f2e938fa578c0f92749ba","sha256:3d9491c79b5467502781039e15ac38cf63cf7524c5d4e5c57918aedca20e9084"],"state_sha256":"94d4e3962aeabfa89e4c44b14eeaa9a53dd63722746ac0b6fd9b01168b8258d1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mTtGfeKGNObk2EUztU/CxKUMEO5KHMWpkIQf9Lt/qDVbE2e49x5OE4ZnpzqXm7oUhKoKnC48twZoYQVxZOmjBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T05:05:01.106704Z","bundle_sha256":"15d40ca17fb1ef372d78c16625386c8642a58dca604808d745d6e624bf03f2ad"}}