{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EZPHIONTL7C4EAWXGHT3EVP3OV","short_pith_number":"pith:EZPHIONT","canonical_record":{"source":{"id":"2412.10360","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-13T18:53:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f29365d62f90aee92569a0ec21d9f8b7bdda5160c8ed665b9a4a5fb193db1d5d","abstract_canon_sha256":"821047b9b08bce0833501f7266ff527ea7caeae7b685902999c56b7ab8ba7f32"},"schema_version":"1.0"},"canonical_sha256":"265e7439b35fc5c202d731e7b255fb755b050dbbea7d5cc17363a65740face3e","source":{"kind":"arxiv","id":"2412.10360","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.10360","created_at":"2026-07-05T09:48:56Z"},{"alias_kind":"arxiv_version","alias_value":"2412.10360v1","created_at":"2026-07-05T09:48:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10360","created_at":"2026-07-05T09:48:56Z"},{"alias_kind":"pith_short_12","alias_value":"EZPHIONTL7C4","created_at":"2026-07-05T09:48:56Z"},{"alias_kind":"pith_short_16","alias_value":"EZPHIONTL7C4EAWX","created_at":"2026-07-05T09:48:56Z"},{"alias_kind":"pith_short_8","alias_value":"EZPHIONT","created_at":"2026-07-05T09:48:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EZPHIONTL7C4EAWXGHT3EVP3OV","target":"record","payload":{"canonical_record":{"source":{"id":"2412.10360","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-13T18:53:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f29365d62f90aee92569a0ec21d9f8b7bdda5160c8ed665b9a4a5fb193db1d5d","abstract_canon_sha256":"821047b9b08bce0833501f7266ff527ea7caeae7b685902999c56b7ab8ba7f32"},"schema_version":"1.0"},"canonical_sha256":"265e7439b35fc5c202d731e7b255fb755b050dbbea7d5cc17363a65740face3e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:56.865940Z","signature_b64":"i64qftNpREffE5i5OUav6emtdP0MVTGcltybllfra77FnSobl/IPebE7b8RbIbRm4yVV8WEovzUW1VXoGVGaDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"265e7439b35fc5c202d731e7b255fb755b050dbbea7d5cc17363a65740face3e","last_reissued_at":"2026-07-05T09:48:56.865385Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:56.865385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.10360","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":"2026-07-05T09:48:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pp9u4UuUaKdwRpVQPgR6TIH1Exs4ZQJoFinCvydR1DToRZXCZheav+56X3OO4lSl1O1NSLwV0tzRce9WId9DAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:35:16.884052Z"},"content_sha256":"e5d36546975af847b2f7580da8f98148cfa1135581dd40d91676806fc1a47f36","schema_version":"1.0","event_id":"sha256:e5d36546975af847b2f7580da8f98148cfa1135581dd40d91676806fc1a47f36"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EZPHIONTL7C4EAWXGHT3EVP3OV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Apollo: An Exploration of Video Understanding in Large Multimodal Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Felix Juefei-Xu, Licheng Yu, Nikhil Mehta, Ning Zhang, Orr Zohar, Philippe Hansen-Estruch, Serena Yeung-Levy, Tong Xiao, Xiaofang Wang, Xiaohan Wang, Xide Xia, Yann Dubois","submitted_at":"2024-12-13T18:53:24Z","abstract_excerpt":"Despite the rapid integration of video perception capabilities into Large Multimodal Models (LMMs), the underlying mechanisms driving their video understanding remain poorly understood. Consequently, many design decisions in this domain are made without proper justification or analysis. The high computational cost of training and evaluating such models, coupled with limited open research, hinders the development of video-LMMs. To address this, we present a comprehensive study that helps uncover what effectively drives video understanding in LMMs.\n  We begin by critically examining the primary "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10360","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/2412.10360/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":"2026-07-05T09:48:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZayGiYqzV5Weo1BGHQut3u91CdmV8NJb+kchubNau2RUgFAuQp410OotaaS1J0EHub0/+cVE+JmolMii/RU8DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:35:16.885604Z"},"content_sha256":"a0c7eef09d36fd7231e9cbea8cd460490beb34e7956ab05725274d1a58579901","schema_version":"1.0","event_id":"sha256:a0c7eef09d36fd7231e9cbea8cd460490beb34e7956ab05725274d1a58579901"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EZPHIONTL7C4EAWXGHT3EVP3OV/bundle.json","state_url":"https://pith.science/pith/EZPHIONTL7C4EAWXGHT3EVP3OV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EZPHIONTL7C4EAWXGHT3EVP3OV/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":"2026-08-07T17:35:16Z","links":{"resolver":"https://pith.science/pith/EZPHIONTL7C4EAWXGHT3EVP3OV","bundle":"https://pith.science/pith/EZPHIONTL7C4EAWXGHT3EVP3OV/bundle.json","state":"https://pith.science/pith/EZPHIONTL7C4EAWXGHT3EVP3OV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EZPHIONTL7C4EAWXGHT3EVP3OV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EZPHIONTL7C4EAWXGHT3EVP3OV","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":"821047b9b08bce0833501f7266ff527ea7caeae7b685902999c56b7ab8ba7f32","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-13T18:53:24Z","title_canon_sha256":"f29365d62f90aee92569a0ec21d9f8b7bdda5160c8ed665b9a4a5fb193db1d5d"},"schema_version":"1.0","source":{"id":"2412.10360","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.10360","created_at":"2026-07-05T09:48:56Z"},{"alias_kind":"arxiv_version","alias_value":"2412.10360v1","created_at":"2026-07-05T09:48:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10360","created_at":"2026-07-05T09:48:56Z"},{"alias_kind":"pith_short_12","alias_value":"EZPHIONTL7C4","created_at":"2026-07-05T09:48:56Z"},{"alias_kind":"pith_short_16","alias_value":"EZPHIONTL7C4EAWX","created_at":"2026-07-05T09:48:56Z"},{"alias_kind":"pith_short_8","alias_value":"EZPHIONT","created_at":"2026-07-05T09:48:56Z"}],"graph_snapshots":[{"event_id":"sha256:a0c7eef09d36fd7231e9cbea8cd460490beb34e7956ab05725274d1a58579901","target":"graph","created_at":"2026-07-05T09:48:56Z","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/2412.10360/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the rapid integration of video perception capabilities into Large Multimodal Models (LMMs), the underlying mechanisms driving their video understanding remain poorly understood. Consequently, many design decisions in this domain are made without proper justification or analysis. The high computational cost of training and evaluating such models, coupled with limited open research, hinders the development of video-LMMs. To address this, we present a comprehensive study that helps uncover what effectively drives video understanding in LMMs.\n  We begin by critically examining the primary ","authors_text":"Felix Juefei-Xu, Licheng Yu, Nikhil Mehta, Ning Zhang, Orr Zohar, Philippe Hansen-Estruch, Serena Yeung-Levy, Tong Xiao, Xiaofang Wang, Xiaohan Wang, Xide Xia, Yann Dubois","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-13T18:53:24Z","title":"Apollo: An Exploration of Video Understanding in Large Multimodal Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10360","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:e5d36546975af847b2f7580da8f98148cfa1135581dd40d91676806fc1a47f36","target":"record","created_at":"2026-07-05T09:48:56Z","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":"821047b9b08bce0833501f7266ff527ea7caeae7b685902999c56b7ab8ba7f32","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-13T18:53:24Z","title_canon_sha256":"f29365d62f90aee92569a0ec21d9f8b7bdda5160c8ed665b9a4a5fb193db1d5d"},"schema_version":"1.0","source":{"id":"2412.10360","kind":"arxiv","version":1}},"canonical_sha256":"265e7439b35fc5c202d731e7b255fb755b050dbbea7d5cc17363a65740face3e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"265e7439b35fc5c202d731e7b255fb755b050dbbea7d5cc17363a65740face3e","first_computed_at":"2026-07-05T09:48:56.865385Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:48:56.865385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i64qftNpREffE5i5OUav6emtdP0MVTGcltybllfra77FnSobl/IPebE7b8RbIbRm4yVV8WEovzUW1VXoGVGaDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:48:56.865940Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.10360","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e5d36546975af847b2f7580da8f98148cfa1135581dd40d91676806fc1a47f36","sha256:a0c7eef09d36fd7231e9cbea8cd460490beb34e7956ab05725274d1a58579901"],"state_sha256":"a56bc670d24e5df3f63c4615abeafc03a1177be1bf5dcd10dd3bfb69840db0dd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XqjlYz113I5Nrf21UX0Wv3b+IvIxEF4koj6YnvhrspkVtTXAfXPDFv0HwAuio4GraknBemYFGttdSX8EagPgCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T17:35:16.892829Z","bundle_sha256":"7074231e5bbb78e139460a9c5d890697a2ac00a79926049945ee1fd333021cc8"}}