{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:K4JYYSFUJVX4GI62Y2KVVNSH3Z","short_pith_number":"pith:K4JYYSFU","canonical_record":{"source":{"id":"2505.24158","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T03:04:28Z","cross_cats_sorted":[],"title_canon_sha256":"fa759392d35cb17dfd8fa4120a0f10cde6b70f47d9d5adeefa6566dce485c271","abstract_canon_sha256":"14616aac9df36c424667b39a434f363b29e74821d7b67ca6c2911ff866221b5b"},"schema_version":"1.0"},"canonical_sha256":"57138c48b44d6fc323dac6955ab647de7d96f142955fd2456f9f98b0b5091706","source":{"kind":"arxiv","id":"2505.24158","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24158","created_at":"2026-07-05T11:12:43Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24158v1","created_at":"2026-07-05T11:12:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24158","created_at":"2026-07-05T11:12:43Z"},{"alias_kind":"pith_short_12","alias_value":"K4JYYSFUJVX4","created_at":"2026-07-05T11:12:43Z"},{"alias_kind":"pith_short_16","alias_value":"K4JYYSFUJVX4GI62","created_at":"2026-07-05T11:12:43Z"},{"alias_kind":"pith_short_8","alias_value":"K4JYYSFU","created_at":"2026-07-05T11:12:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:K4JYYSFUJVX4GI62Y2KVVNSH3Z","target":"record","payload":{"canonical_record":{"source":{"id":"2505.24158","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T03:04:28Z","cross_cats_sorted":[],"title_canon_sha256":"fa759392d35cb17dfd8fa4120a0f10cde6b70f47d9d5adeefa6566dce485c271","abstract_canon_sha256":"14616aac9df36c424667b39a434f363b29e74821d7b67ca6c2911ff866221b5b"},"schema_version":"1.0"},"canonical_sha256":"57138c48b44d6fc323dac6955ab647de7d96f142955fd2456f9f98b0b5091706","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:43.104546Z","signature_b64":"/tbuCJMM65QO6ljQR0IWnaguivvc6spwb6oGLdKulpunHPaSU+Jq28oz/XACGh0YBdul+HvS7wzch7BMF8GCAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57138c48b44d6fc323dac6955ab647de7d96f142955fd2456f9f98b0b5091706","last_reissued_at":"2026-07-05T11:12:43.104047Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:43.104047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.24158","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":"2026-07-05T11:12:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nTvwnek3o3c5SI6ruEdIBtdkRtu7R+W0hMbpLf7UKRTvwON/hNR4U+G3ECJSMk/KQBts3F7aPGWZ5wsmh8WUAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T16:37:15.005331Z"},"content_sha256":"ce08d94444d37cd30c85c6e9aabab37f718a8d0e3c6c79100fe71e6bdaf5a4bf","schema_version":"1.0","event_id":"sha256:ce08d94444d37cd30c85c6e9aabab37f718a8d0e3c6c79100fe71e6bdaf5a4bf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:K4JYYSFUJVX4GI62Y2KVVNSH3Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Antoni B. Chan, Bo Fang, Qiangqiang Wu, Wenhao Wu, Yuxin Song","submitted_at":"2025-05-30T03:04:28Z","abstract_excerpt":"Employing Multimodal Large Language Models (MLLMs) for long video understanding remains a challenging problem due to the dilemma between the substantial number of video frames (i.e., visual tokens) versus the limited context length of language models. Traditional uniform sampling often leads to selection of irrelevant content, while post-training MLLMs on thousands of frames imposes a substantial computational burden. In this paper, we propose threading keyframes with narratives (Nar-KFC), a plug-and-play module to facilitate effective and efficient long video perception. Nar-KFC generally inv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24158","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/2505.24158/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":"2026-07-05T11:12:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZGYkkiXFRIzBm3MofVjiKf2mOPjQlcODJCr2FAVbz8clEWT17sCpvohDKtgGG3d8r6J62Im8OfPsvArUAyLqBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T16:37:15.006427Z"},"content_sha256":"b67b5b95b245f0d2646a96262b073770c9f4a0c5799af84ef9782325a875b7fd","schema_version":"1.0","event_id":"sha256:b67b5b95b245f0d2646a96262b073770c9f4a0c5799af84ef9782325a875b7fd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K4JYYSFUJVX4GI62Y2KVVNSH3Z/bundle.json","state_url":"https://pith.science/pith/K4JYYSFUJVX4GI62Y2KVVNSH3Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K4JYYSFUJVX4GI62Y2KVVNSH3Z/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":"2026-08-05T16:37:15Z","links":{"resolver":"https://pith.science/pith/K4JYYSFUJVX4GI62Y2KVVNSH3Z","bundle":"https://pith.science/pith/K4JYYSFUJVX4GI62Y2KVVNSH3Z/bundle.json","state":"https://pith.science/pith/K4JYYSFUJVX4GI62Y2KVVNSH3Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K4JYYSFUJVX4GI62Y2KVVNSH3Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:K4JYYSFUJVX4GI62Y2KVVNSH3Z","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":"14616aac9df36c424667b39a434f363b29e74821d7b67ca6c2911ff866221b5b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T03:04:28Z","title_canon_sha256":"fa759392d35cb17dfd8fa4120a0f10cde6b70f47d9d5adeefa6566dce485c271"},"schema_version":"1.0","source":{"id":"2505.24158","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24158","created_at":"2026-07-05T11:12:43Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24158v1","created_at":"2026-07-05T11:12:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24158","created_at":"2026-07-05T11:12:43Z"},{"alias_kind":"pith_short_12","alias_value":"K4JYYSFUJVX4","created_at":"2026-07-05T11:12:43Z"},{"alias_kind":"pith_short_16","alias_value":"K4JYYSFUJVX4GI62","created_at":"2026-07-05T11:12:43Z"},{"alias_kind":"pith_short_8","alias_value":"K4JYYSFU","created_at":"2026-07-05T11:12:43Z"}],"graph_snapshots":[{"event_id":"sha256:b67b5b95b245f0d2646a96262b073770c9f4a0c5799af84ef9782325a875b7fd","target":"graph","created_at":"2026-07-05T11:12:43Z","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/2505.24158/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Employing Multimodal Large Language Models (MLLMs) for long video understanding remains a challenging problem due to the dilemma between the substantial number of video frames (i.e., visual tokens) versus the limited context length of language models. Traditional uniform sampling often leads to selection of irrelevant content, while post-training MLLMs on thousands of frames imposes a substantial computational burden. In this paper, we propose threading keyframes with narratives (Nar-KFC), a plug-and-play module to facilitate effective and efficient long video perception. Nar-KFC generally inv","authors_text":"Antoni B. Chan, Bo Fang, Qiangqiang Wu, Wenhao Wu, Yuxin Song","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T03:04:28Z","title":"Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24158","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:ce08d94444d37cd30c85c6e9aabab37f718a8d0e3c6c79100fe71e6bdaf5a4bf","target":"record","created_at":"2026-07-05T11:12:43Z","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":"14616aac9df36c424667b39a434f363b29e74821d7b67ca6c2911ff866221b5b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T03:04:28Z","title_canon_sha256":"fa759392d35cb17dfd8fa4120a0f10cde6b70f47d9d5adeefa6566dce485c271"},"schema_version":"1.0","source":{"id":"2505.24158","kind":"arxiv","version":1}},"canonical_sha256":"57138c48b44d6fc323dac6955ab647de7d96f142955fd2456f9f98b0b5091706","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"57138c48b44d6fc323dac6955ab647de7d96f142955fd2456f9f98b0b5091706","first_computed_at":"2026-07-05T11:12:43.104047Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:43.104047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/tbuCJMM65QO6ljQR0IWnaguivvc6spwb6oGLdKulpunHPaSU+Jq28oz/XACGh0YBdul+HvS7wzch7BMF8GCAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:43.104546Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.24158","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce08d94444d37cd30c85c6e9aabab37f718a8d0e3c6c79100fe71e6bdaf5a4bf","sha256:b67b5b95b245f0d2646a96262b073770c9f4a0c5799af84ef9782325a875b7fd"],"state_sha256":"56d8af7e2f347cbc433545dab30eab2783942945984e3a3e10b31cce774529a3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vw6wuwSX0TtmmzoFDXsuRlF1xV/5kJTfUspd6YUMpH2BzIn/aCKszta94CyIhVyTuXkzNMg74VZ7ZAT/ehpODQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T16:37:15.013184Z","bundle_sha256":"f8bb9ca757c2f5b5a8c5c70fd48bfd19dfcb4d2d273566ce467044154b6913d8"}}