{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:DNTULYCQAPZB6LAMJJTE2TH74L","short_pith_number":"pith:DNTULYCQ","canonical_record":{"source":{"id":"2503.08585","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-11T16:21:23Z","cross_cats_sorted":[],"title_canon_sha256":"16c56d651f39fd6025fc16fd3e0dc46daa2620c66583b4a0d0c28fcca09075e2","abstract_canon_sha256":"d56e9e6c21b511d548af8bd38bbcec82c831133d6a23f0296d40120398aded09"},"schema_version":"1.0"},"canonical_sha256":"1b6745e05003f21f2c0c4a664d4cffe2d9a2eb102458ff7048d7ce4510b77fa5","source":{"kind":"arxiv","id":"2503.08585","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.08585","created_at":"2026-07-05T10:53:39Z"},{"alias_kind":"arxiv_version","alias_value":"2503.08585v2","created_at":"2026-07-05T10:53:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.08585","created_at":"2026-07-05T10:53:39Z"},{"alias_kind":"pith_short_12","alias_value":"DNTULYCQAPZB","created_at":"2026-07-05T10:53:39Z"},{"alias_kind":"pith_short_16","alias_value":"DNTULYCQAPZB6LAM","created_at":"2026-07-05T10:53:39Z"},{"alias_kind":"pith_short_8","alias_value":"DNTULYCQ","created_at":"2026-07-05T10:53:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:DNTULYCQAPZB6LAMJJTE2TH74L","target":"record","payload":{"canonical_record":{"source":{"id":"2503.08585","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-11T16:21:23Z","cross_cats_sorted":[],"title_canon_sha256":"16c56d651f39fd6025fc16fd3e0dc46daa2620c66583b4a0d0c28fcca09075e2","abstract_canon_sha256":"d56e9e6c21b511d548af8bd38bbcec82c831133d6a23f0296d40120398aded09"},"schema_version":"1.0"},"canonical_sha256":"1b6745e05003f21f2c0c4a664d4cffe2d9a2eb102458ff7048d7ce4510b77fa5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:39.422772Z","signature_b64":"dnSgifDQdp3IVMf0vJ9rmyo+3aKXsGiOpm697+cU2UxD11XilQSbXxLiDCvJYE89j36FUtvOvC5vecN7Xk92Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b6745e05003f21f2c0c4a664d4cffe2d9a2eb102458ff7048d7ce4510b77fa5","last_reissued_at":"2026-07-05T10:53:39.422300Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:39.422300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.08585","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":"2026-07-05T10:53:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eTAoQmDKM4UZGBcpipPSS5MdJ8K670sbb1U5uwGi8f8jtdW176JNe6p/MjjFjri4dVLPHETT4lT729bVHLlHCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:23:24.838128Z"},"content_sha256":"b2e8e7baeb9cd108c8cd9e5d664cb8a0d58f1c4a6601a18ff34122ae09e67c8f","schema_version":"1.0","event_id":"sha256:b2e8e7baeb9cd108c8cd9e5d664cb8a0d58f1c4a6601a18ff34122ae09e67c8f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:DNTULYCQAPZB6LAMJJTE2TH74L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HierarQ: Task-Aware Hierarchical Q-Former for Enhanced Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Shehreen Azad, Vibhav Vineet, Yogesh Singh Rawat","submitted_at":"2025-03-11T16:21:23Z","abstract_excerpt":"Despite advancements in multimodal large language models (MLLMs), current approaches struggle in medium-to-long video understanding due to frame and context length limitations. As a result, these models often depend on frame sampling, which risks missing key information over time and lacks task-specific relevance. To address these challenges, we introduce HierarQ, a task-aware hierarchical Q-Former based framework that sequentially processes frames to bypass the need for frame sampling, while avoiding LLM's context length limitations. We introduce a lightweight two-stream language-guided featu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.08585","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/2503.08585/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":"2026-07-05T10:53:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QBzEl1jP7EipqczwOqHgOMMkV4wWCPM6PpMlBWm+j4bBeF5ITme/wkgORbukI/gv5pIyiryYLYWmFDjY6J5bAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:23:24.838643Z"},"content_sha256":"d8c6b7cba1383180eeebcee9b932937e8ff740da497bab43b1065ee5d6dab718","schema_version":"1.0","event_id":"sha256:d8c6b7cba1383180eeebcee9b932937e8ff740da497bab43b1065ee5d6dab718"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DNTULYCQAPZB6LAMJJTE2TH74L/bundle.json","state_url":"https://pith.science/pith/DNTULYCQAPZB6LAMJJTE2TH74L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DNTULYCQAPZB6LAMJJTE2TH74L/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":"2026-08-08T20:23:24Z","links":{"resolver":"https://pith.science/pith/DNTULYCQAPZB6LAMJJTE2TH74L","bundle":"https://pith.science/pith/DNTULYCQAPZB6LAMJJTE2TH74L/bundle.json","state":"https://pith.science/pith/DNTULYCQAPZB6LAMJJTE2TH74L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DNTULYCQAPZB6LAMJJTE2TH74L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DNTULYCQAPZB6LAMJJTE2TH74L","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":"d56e9e6c21b511d548af8bd38bbcec82c831133d6a23f0296d40120398aded09","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-11T16:21:23Z","title_canon_sha256":"16c56d651f39fd6025fc16fd3e0dc46daa2620c66583b4a0d0c28fcca09075e2"},"schema_version":"1.0","source":{"id":"2503.08585","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.08585","created_at":"2026-07-05T10:53:39Z"},{"alias_kind":"arxiv_version","alias_value":"2503.08585v2","created_at":"2026-07-05T10:53:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.08585","created_at":"2026-07-05T10:53:39Z"},{"alias_kind":"pith_short_12","alias_value":"DNTULYCQAPZB","created_at":"2026-07-05T10:53:39Z"},{"alias_kind":"pith_short_16","alias_value":"DNTULYCQAPZB6LAM","created_at":"2026-07-05T10:53:39Z"},{"alias_kind":"pith_short_8","alias_value":"DNTULYCQ","created_at":"2026-07-05T10:53:39Z"}],"graph_snapshots":[{"event_id":"sha256:d8c6b7cba1383180eeebcee9b932937e8ff740da497bab43b1065ee5d6dab718","target":"graph","created_at":"2026-07-05T10:53:39Z","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/2503.08585/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite advancements in multimodal large language models (MLLMs), current approaches struggle in medium-to-long video understanding due to frame and context length limitations. As a result, these models often depend on frame sampling, which risks missing key information over time and lacks task-specific relevance. To address these challenges, we introduce HierarQ, a task-aware hierarchical Q-Former based framework that sequentially processes frames to bypass the need for frame sampling, while avoiding LLM's context length limitations. We introduce a lightweight two-stream language-guided featu","authors_text":"Shehreen Azad, Vibhav Vineet, Yogesh Singh Rawat","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-11T16:21:23Z","title":"HierarQ: Task-Aware Hierarchical Q-Former for Enhanced Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.08585","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:b2e8e7baeb9cd108c8cd9e5d664cb8a0d58f1c4a6601a18ff34122ae09e67c8f","target":"record","created_at":"2026-07-05T10:53:39Z","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":"d56e9e6c21b511d548af8bd38bbcec82c831133d6a23f0296d40120398aded09","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-11T16:21:23Z","title_canon_sha256":"16c56d651f39fd6025fc16fd3e0dc46daa2620c66583b4a0d0c28fcca09075e2"},"schema_version":"1.0","source":{"id":"2503.08585","kind":"arxiv","version":2}},"canonical_sha256":"1b6745e05003f21f2c0c4a664d4cffe2d9a2eb102458ff7048d7ce4510b77fa5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1b6745e05003f21f2c0c4a664d4cffe2d9a2eb102458ff7048d7ce4510b77fa5","first_computed_at":"2026-07-05T10:53:39.422300Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:53:39.422300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dnSgifDQdp3IVMf0vJ9rmyo+3aKXsGiOpm697+cU2UxD11XilQSbXxLiDCvJYE89j36FUtvOvC5vecN7Xk92Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:53:39.422772Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.08585","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2e8e7baeb9cd108c8cd9e5d664cb8a0d58f1c4a6601a18ff34122ae09e67c8f","sha256:d8c6b7cba1383180eeebcee9b932937e8ff740da497bab43b1065ee5d6dab718"],"state_sha256":"e6f27aff6c318ebcb432be31bbf349fd3dc23ec201ee2ee737e83d8793010dcf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sLc67jimXZ0kM9VwnRbU0w6gpcMPFa8YbIK9+8z6xDx3P35cBTvls13oZCmD5hnUea0X6JpM/fLE0xVKVtekCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T20:23:24.843207Z","bundle_sha256":"90ced293bb6e4de412de3ab85cc5366e1199c22797127127101be7dabaefb39e"}}