{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZCPX23ENLOZEGE2HOPHBGDRIUX","short_pith_number":"pith:ZCPX23EN","canonical_record":{"source":{"id":"2411.15798","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2024-11-24T11:56:59Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e131579cdaa455f5482789adcf71cdeb537a8e18d8d3115b2b7ff0430aa217ae","abstract_canon_sha256":"eb64fe2161c6166a2eae57d41290580b1c1518c1c8d41c555bb64cb581e8e9cf"},"schema_version":"1.0"},"canonical_sha256":"c89f7d6c8d5bb243134773ce130e28a5c0de54a564136a56a0c5600379fa9724","source":{"kind":"arxiv","id":"2411.15798","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.15798","created_at":"2026-07-05T09:54:05Z"},{"alias_kind":"arxiv_version","alias_value":"2411.15798v2","created_at":"2026-07-05T09:54:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15798","created_at":"2026-07-05T09:54:05Z"},{"alias_kind":"pith_short_12","alias_value":"ZCPX23ENLOZE","created_at":"2026-07-05T09:54:05Z"},{"alias_kind":"pith_short_16","alias_value":"ZCPX23ENLOZEGE2H","created_at":"2026-07-05T09:54:05Z"},{"alias_kind":"pith_short_8","alias_value":"ZCPX23EN","created_at":"2026-07-05T09:54:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZCPX23ENLOZEGE2HOPHBGDRIUX","target":"record","payload":{"canonical_record":{"source":{"id":"2411.15798","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2024-11-24T11:56:59Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e131579cdaa455f5482789adcf71cdeb537a8e18d8d3115b2b7ff0430aa217ae","abstract_canon_sha256":"eb64fe2161c6166a2eae57d41290580b1c1518c1c8d41c555bb64cb581e8e9cf"},"schema_version":"1.0"},"canonical_sha256":"c89f7d6c8d5bb243134773ce130e28a5c0de54a564136a56a0c5600379fa9724","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:05.944065Z","signature_b64":"ID9jZzBTIPZClgaZk3RmbFUZ4NvPQbGQf55Cm9hwvYAzI3n2wBIcK6QtniLd0orEXCKHgwpONxOjo75EFFG6Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c89f7d6c8d5bb243134773ce130e28a5c0de54a564136a56a0c5600379fa9724","last_reissued_at":"2026-07-05T09:54:05.943585Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:05.943585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.15798","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:54:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Dh40m5o+bAUo7B/EvyZbHUoFL88pbl+mx3YlPlBnUmzC4ChhWfSXGxt77e80xen/Vq2dTWJR/3GfLqntjOInCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T04:17:58.098528Z"},"content_sha256":"33e49ef765a93e6788d9458e44d9e6b291c97f1d07b47350cea0781a84b9138e","schema_version":"1.0","event_id":"sha256:33e49ef765a93e6788d9458e44d9e6b291c97f1d07b47350cea0781a84b9138e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZCPX23ENLOZEGE2HOPHBGDRIUX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"M3-CVC: Controllable Video Compression with Multimodal Generative Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Qi Zheng, Rui Wan, Yibo Fan","submitted_at":"2024-11-24T11:56:59Z","abstract_excerpt":"Traditional and neural video codecs commonly encounter limitations in controllability and generality under ultra-low-bitrate coding scenarios. To overcome these challenges, we propose M3-CVC, a controllable video compression framework incorporating multimodal generative models. The framework utilizes a semantic-motion composite strategy for keyframe selection to retain critical information. For each keyframe and its corresponding video clip, a dialogue-based large multimodal model (LMM) approach extracts hierarchical spatiotemporal details, enabling both inter-frame and intra-frame representat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15798","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/2411.15798/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":"2026-07-05T09:54:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LYxwUoWlX+eZXMmGI2zFwvDWWPXWS8xKKa7xCQTrq26fo0UDbpf9wrr6HlVGDsBm0m5ODjzTxdEiNbBxw392BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T04:17:58.098906Z"},"content_sha256":"80e9fbe279b8166052de67f2f6107277c2d71845690673f89e7748f181667eb0","schema_version":"1.0","event_id":"sha256:80e9fbe279b8166052de67f2f6107277c2d71845690673f89e7748f181667eb0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZCPX23ENLOZEGE2HOPHBGDRIUX/bundle.json","state_url":"https://pith.science/pith/ZCPX23ENLOZEGE2HOPHBGDRIUX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZCPX23ENLOZEGE2HOPHBGDRIUX/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":"2026-08-13T04:17:58Z","links":{"resolver":"https://pith.science/pith/ZCPX23ENLOZEGE2HOPHBGDRIUX","bundle":"https://pith.science/pith/ZCPX23ENLOZEGE2HOPHBGDRIUX/bundle.json","state":"https://pith.science/pith/ZCPX23ENLOZEGE2HOPHBGDRIUX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZCPX23ENLOZEGE2HOPHBGDRIUX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZCPX23ENLOZEGE2HOPHBGDRIUX","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":"eb64fe2161c6166a2eae57d41290580b1c1518c1c8d41c555bb64cb581e8e9cf","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2024-11-24T11:56:59Z","title_canon_sha256":"e131579cdaa455f5482789adcf71cdeb537a8e18d8d3115b2b7ff0430aa217ae"},"schema_version":"1.0","source":{"id":"2411.15798","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.15798","created_at":"2026-07-05T09:54:05Z"},{"alias_kind":"arxiv_version","alias_value":"2411.15798v2","created_at":"2026-07-05T09:54:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15798","created_at":"2026-07-05T09:54:05Z"},{"alias_kind":"pith_short_12","alias_value":"ZCPX23ENLOZE","created_at":"2026-07-05T09:54:05Z"},{"alias_kind":"pith_short_16","alias_value":"ZCPX23ENLOZEGE2H","created_at":"2026-07-05T09:54:05Z"},{"alias_kind":"pith_short_8","alias_value":"ZCPX23EN","created_at":"2026-07-05T09:54:05Z"}],"graph_snapshots":[{"event_id":"sha256:80e9fbe279b8166052de67f2f6107277c2d71845690673f89e7748f181667eb0","target":"graph","created_at":"2026-07-05T09:54:05Z","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/2411.15798/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Traditional and neural video codecs commonly encounter limitations in controllability and generality under ultra-low-bitrate coding scenarios. To overcome these challenges, we propose M3-CVC, a controllable video compression framework incorporating multimodal generative models. The framework utilizes a semantic-motion composite strategy for keyframe selection to retain critical information. For each keyframe and its corresponding video clip, a dialogue-based large multimodal model (LMM) approach extracts hierarchical spatiotemporal details, enabling both inter-frame and intra-frame representat","authors_text":"Qi Zheng, Rui Wan, Yibo Fan","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2024-11-24T11:56:59Z","title":"M3-CVC: Controllable Video Compression with Multimodal Generative Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15798","kind":"arxiv","version":2},"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":"sha256:33e49ef765a93e6788d9458e44d9e6b291c97f1d07b47350cea0781a84b9138e","target":"record","created_at":"2026-07-05T09:54:05Z","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":"eb64fe2161c6166a2eae57d41290580b1c1518c1c8d41c555bb64cb581e8e9cf","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2024-11-24T11:56:59Z","title_canon_sha256":"e131579cdaa455f5482789adcf71cdeb537a8e18d8d3115b2b7ff0430aa217ae"},"schema_version":"1.0","source":{"id":"2411.15798","kind":"arxiv","version":2}},"canonical_sha256":"c89f7d6c8d5bb243134773ce130e28a5c0de54a564136a56a0c5600379fa9724","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c89f7d6c8d5bb243134773ce130e28a5c0de54a564136a56a0c5600379fa9724","first_computed_at":"2026-07-05T09:54:05.943585Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:05.943585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ID9jZzBTIPZClgaZk3RmbFUZ4NvPQbGQf55Cm9hwvYAzI3n2wBIcK6QtniLd0orEXCKHgwpONxOjo75EFFG6Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:05.944065Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.15798","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:33e49ef765a93e6788d9458e44d9e6b291c97f1d07b47350cea0781a84b9138e","sha256:80e9fbe279b8166052de67f2f6107277c2d71845690673f89e7748f181667eb0"],"state_sha256":"da426c49123f35431d94ad2653cca2a4822ebfb64e1e0295b7a469ba5a3ae878"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fHyBpWjdEhP3P9kryeB2HOYY2RDbzJWy02tJEkPRah18Be6AgpK0iOahpB/W+Q8gyjm34N37Y+6hhTvk9ESlCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T04:17:58.101395Z","bundle_sha256":"bdcfed6b1a80b2b836ac7a7b9dd230ae1f3ae7fd874460d775a661d907df5b6d"}}