{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6EXQOVKHAUILKDTGLMFGT7PA3R","short_pith_number":"pith:6EXQOVKH","canonical_record":{"source":{"id":"2607.04559","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-06T00:19:42Z","cross_cats_sorted":[],"title_canon_sha256":"71329f53458560c2de531970bfb0b8e6ec505eb043c87bb92d2d2e01286d82e2","abstract_canon_sha256":"1826ee06d5832f93e4b40c0c817a3e99267023f438b02cdcdfa9ba0e63b4cedf"},"schema_version":"1.0"},"canonical_sha256":"f12f0755470510b50e665b0a69fde0dc58bfca78d45285c6c7ba04b2991952f5","source":{"kind":"arxiv","id":"2607.04559","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.04559","created_at":"2026-07-07T02:19:24Z"},{"alias_kind":"arxiv_version","alias_value":"2607.04559v1","created_at":"2026-07-07T02:19:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04559","created_at":"2026-07-07T02:19:24Z"},{"alias_kind":"pith_short_12","alias_value":"6EXQOVKHAUIL","created_at":"2026-07-07T02:19:24Z"},{"alias_kind":"pith_short_16","alias_value":"6EXQOVKHAUILKDTG","created_at":"2026-07-07T02:19:24Z"},{"alias_kind":"pith_short_8","alias_value":"6EXQOVKH","created_at":"2026-07-07T02:19:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6EXQOVKHAUILKDTGLMFGT7PA3R","target":"record","payload":{"canonical_record":{"source":{"id":"2607.04559","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-06T00:19:42Z","cross_cats_sorted":[],"title_canon_sha256":"71329f53458560c2de531970bfb0b8e6ec505eb043c87bb92d2d2e01286d82e2","abstract_canon_sha256":"1826ee06d5832f93e4b40c0c817a3e99267023f438b02cdcdfa9ba0e63b4cedf"},"schema_version":"1.0"},"canonical_sha256":"f12f0755470510b50e665b0a69fde0dc58bfca78d45285c6c7ba04b2991952f5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:19:24.970295Z","signature_b64":"IIOBx10ncAjNTsjgHk5Yk/maOk9j13jH4uACITsTI6rEvKctnITNHVFFiNk7ltKIRULCPEFT2Fn5RIG9NJ5VCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f12f0755470510b50e665b0a69fde0dc58bfca78d45285c6c7ba04b2991952f5","last_reissued_at":"2026-07-07T02:19:24.969600Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:19:24.969600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.04559","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":"2026-07-07T02:19:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MS8yPy+1ApGXGgQTsWYV0n/tlD5sALEpmIGm7DVJQF2EM/j05RfxX8oQhkRR7ztr5Mx0wKi5oQat6JX9tRPVBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:51:45.157304Z"},"content_sha256":"eefdb099855b98261779d6124725b285d5033191fcbfb321e8eba3f1bf99839d","schema_version":"1.0","event_id":"sha256:eefdb099855b98261779d6124725b285d5033191fcbfb321e8eba3f1bf99839d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6EXQOVKHAUILKDTGLMFGT7PA3R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"QSVideo: Query-Conditioned Semantic Temporal Retrieval for Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lan Wang, Vishnu Naresh Boddeti, Wei Ao","submitted_at":"2026-07-06T00:19:42Z","abstract_excerpt":"The performance of vision-language models (VLMs) in video understanding declines with increasing video duration, as video moments unrelated to the query confuse their language components. Multimodal retrieval has emerged as a critical component of video understanding, addressing this challenge by localizing key visual evidence. However, existing multimodal retrieval methods suffer from biased relevance estimation, limited diversity, and temporal collapse. In this paper, we propose QSVideo, a unified framework that systematically addresses relevance, diversity, and temporal modeling in video re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04559","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/2607.04559/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":"2026-07-07T02:19:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fmz1BWc1dZM3Qn0fsHqLqit93ojW+QvNC9TRCnr2McEmrB7MxaqcxK+XxcF3Z3t9CoSwND6Rf2qC1oaqK8jxBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:51:45.157815Z"},"content_sha256":"6f1b2c639429738bd2b13ab5459b646e2d606b47ea0b273b37d8add7f610db78","schema_version":"1.0","event_id":"sha256:6f1b2c639429738bd2b13ab5459b646e2d606b47ea0b273b37d8add7f610db78"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6EXQOVKHAUILKDTGLMFGT7PA3R/bundle.json","state_url":"https://pith.science/pith/6EXQOVKHAUILKDTGLMFGT7PA3R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6EXQOVKHAUILKDTGLMFGT7PA3R/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":"2026-08-06T01:51:45Z","links":{"resolver":"https://pith.science/pith/6EXQOVKHAUILKDTGLMFGT7PA3R","bundle":"https://pith.science/pith/6EXQOVKHAUILKDTGLMFGT7PA3R/bundle.json","state":"https://pith.science/pith/6EXQOVKHAUILKDTGLMFGT7PA3R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6EXQOVKHAUILKDTGLMFGT7PA3R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6EXQOVKHAUILKDTGLMFGT7PA3R","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":"1826ee06d5832f93e4b40c0c817a3e99267023f438b02cdcdfa9ba0e63b4cedf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-06T00:19:42Z","title_canon_sha256":"71329f53458560c2de531970bfb0b8e6ec505eb043c87bb92d2d2e01286d82e2"},"schema_version":"1.0","source":{"id":"2607.04559","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.04559","created_at":"2026-07-07T02:19:24Z"},{"alias_kind":"arxiv_version","alias_value":"2607.04559v1","created_at":"2026-07-07T02:19:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04559","created_at":"2026-07-07T02:19:24Z"},{"alias_kind":"pith_short_12","alias_value":"6EXQOVKHAUIL","created_at":"2026-07-07T02:19:24Z"},{"alias_kind":"pith_short_16","alias_value":"6EXQOVKHAUILKDTG","created_at":"2026-07-07T02:19:24Z"},{"alias_kind":"pith_short_8","alias_value":"6EXQOVKH","created_at":"2026-07-07T02:19:24Z"}],"graph_snapshots":[{"event_id":"sha256:6f1b2c639429738bd2b13ab5459b646e2d606b47ea0b273b37d8add7f610db78","target":"graph","created_at":"2026-07-07T02:19:24Z","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/2607.04559/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The performance of vision-language models (VLMs) in video understanding declines with increasing video duration, as video moments unrelated to the query confuse their language components. Multimodal retrieval has emerged as a critical component of video understanding, addressing this challenge by localizing key visual evidence. However, existing multimodal retrieval methods suffer from biased relevance estimation, limited diversity, and temporal collapse. In this paper, we propose QSVideo, a unified framework that systematically addresses relevance, diversity, and temporal modeling in video re","authors_text":"Lan Wang, Vishnu Naresh Boddeti, Wei Ao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-06T00:19:42Z","title":"QSVideo: Query-Conditioned Semantic Temporal Retrieval for Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04559","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:eefdb099855b98261779d6124725b285d5033191fcbfb321e8eba3f1bf99839d","target":"record","created_at":"2026-07-07T02:19:24Z","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":"1826ee06d5832f93e4b40c0c817a3e99267023f438b02cdcdfa9ba0e63b4cedf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-06T00:19:42Z","title_canon_sha256":"71329f53458560c2de531970bfb0b8e6ec505eb043c87bb92d2d2e01286d82e2"},"schema_version":"1.0","source":{"id":"2607.04559","kind":"arxiv","version":1}},"canonical_sha256":"f12f0755470510b50e665b0a69fde0dc58bfca78d45285c6c7ba04b2991952f5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f12f0755470510b50e665b0a69fde0dc58bfca78d45285c6c7ba04b2991952f5","first_computed_at":"2026-07-07T02:19:24.969600Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:19:24.969600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IIOBx10ncAjNTsjgHk5Yk/maOk9j13jH4uACITsTI6rEvKctnITNHVFFiNk7ltKIRULCPEFT2Fn5RIG9NJ5VCw==","signature_status":"signed_v1","signed_at":"2026-07-07T02:19:24.970295Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.04559","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eefdb099855b98261779d6124725b285d5033191fcbfb321e8eba3f1bf99839d","sha256:6f1b2c639429738bd2b13ab5459b646e2d606b47ea0b273b37d8add7f610db78"],"state_sha256":"a53b365caa595582dc2c9831c0bbcc6e3bb646ce7ff5e2f05cfa774a7cf55da6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"enPvZRR5CI6AkC+rZiWp/JJs3C5u61W/fCoYq3AzqdhopXkU/YHgtplXmRF9lZbhk+8HAf8Ss4txbdKaYRdXDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T01:51:45.163262Z","bundle_sha256":"81216a9416778f721ac59115854392dbec0a24215cda6af71cf8a7a3da59798a"}}