{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JQTXDIQ5HW6ZFS7DCXE3VDVQVL","short_pith_number":"pith:JQTXDIQ5","canonical_record":{"source":{"id":"2404.00973","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-01T07:44:24Z","cross_cats_sorted":[],"title_canon_sha256":"397d4c7d08e79abd3cce2e6a340f396a9881a290ba27169eafa238f0ccbba5e5","abstract_canon_sha256":"3d6fb106c6260cb927c8097cd3c00d32fbd94657b8b8168ae758fe9ae9a48df5"},"schema_version":"1.0"},"canonical_sha256":"4c2771a21d3dbd92cbe315c9ba8eb0aad3b6e5a8a8b61c21e65146c369eb17d0","source":{"kind":"arxiv","id":"2404.00973","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.00973","created_at":"2026-07-05T08:02:59Z"},{"alias_kind":"arxiv_version","alias_value":"2404.00973v1","created_at":"2026-07-05T08:02:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00973","created_at":"2026-07-05T08:02:59Z"},{"alias_kind":"pith_short_12","alias_value":"JQTXDIQ5HW6Z","created_at":"2026-07-05T08:02:59Z"},{"alias_kind":"pith_short_16","alias_value":"JQTXDIQ5HW6ZFS7D","created_at":"2026-07-05T08:02:59Z"},{"alias_kind":"pith_short_8","alias_value":"JQTXDIQ5","created_at":"2026-07-05T08:02:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JQTXDIQ5HW6ZFS7DCXE3VDVQVL","target":"record","payload":{"canonical_record":{"source":{"id":"2404.00973","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-01T07:44:24Z","cross_cats_sorted":[],"title_canon_sha256":"397d4c7d08e79abd3cce2e6a340f396a9881a290ba27169eafa238f0ccbba5e5","abstract_canon_sha256":"3d6fb106c6260cb927c8097cd3c00d32fbd94657b8b8168ae758fe9ae9a48df5"},"schema_version":"1.0"},"canonical_sha256":"4c2771a21d3dbd92cbe315c9ba8eb0aad3b6e5a8a8b61c21e65146c369eb17d0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:59.438170Z","signature_b64":"K0BNCnheV8c7Rsf2DsgYt8g6gheXYawdjMymcKl68oAGudqizkPCw06BJNdmZUnauaIxZiapiWVVqhk00rPFAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c2771a21d3dbd92cbe315c9ba8eb0aad3b6e5a8a8b61c21e65146c369eb17d0","last_reissued_at":"2026-07-05T08:02:59.437637Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:59.437637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.00973","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":"2026-07-05T08:02:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0JBopP3k+RdeqaCaVPWlAnj+4HyMgrw8OWb/+q+lmbk/g3GWvX08o5mPIrPt/CMXrW/NZZbgC5agXM01I/khAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T05:33:14.829356Z"},"content_sha256":"1481691530478d0f65c387e27ebe227fefa39c90d87598c7d6d4bfc86a664472","schema_version":"1.0","event_id":"sha256:1481691530478d0f65c387e27ebe227fefa39c90d87598c7d6d4bfc86a664472"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JQTXDIQ5HW6ZFS7DCXE3VDVQVL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VideoDistill: Language-aware Vision Distillation for Video Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Zou, Chao Yang, Chengbin Quan, Youjian Zhao, Yu Qiao","submitted_at":"2024-04-01T07:44:24Z","abstract_excerpt":"Significant advancements in video question answering (VideoQA) have been made thanks to thriving large image-language pretraining frameworks. Although these image-language models can efficiently represent both video and language branches, they typically employ a goal-free vision perception process and do not interact vision with language well during the answer generation, thus omitting crucial visual cues. In this paper, we are inspired by the human recognition and learning pattern and propose VideoDistill, a framework with language-aware (i.e., goal-driven) behavior in both vision perception "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00973","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/2404.00973/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":"2026-07-05T08:02:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cckj9QzvR3NYw+tL2QZzQjerZuCjgS05aXXEDpB+hEv5UHUjNxjcuy2CBIunPPNYpo2MTmDvMK7Q7b34CxlfBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T05:33:14.829870Z"},"content_sha256":"d2f2f15ed268abfaf87a3be9d23ba9aac2a655ec7faba04fac6d8e03b63a34bf","schema_version":"1.0","event_id":"sha256:d2f2f15ed268abfaf87a3be9d23ba9aac2a655ec7faba04fac6d8e03b63a34bf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JQTXDIQ5HW6ZFS7DCXE3VDVQVL/bundle.json","state_url":"https://pith.science/pith/JQTXDIQ5HW6ZFS7DCXE3VDVQVL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JQTXDIQ5HW6ZFS7DCXE3VDVQVL/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":"2026-08-15T05:33:14Z","links":{"resolver":"https://pith.science/pith/JQTXDIQ5HW6ZFS7DCXE3VDVQVL","bundle":"https://pith.science/pith/JQTXDIQ5HW6ZFS7DCXE3VDVQVL/bundle.json","state":"https://pith.science/pith/JQTXDIQ5HW6ZFS7DCXE3VDVQVL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JQTXDIQ5HW6ZFS7DCXE3VDVQVL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JQTXDIQ5HW6ZFS7DCXE3VDVQVL","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":"3d6fb106c6260cb927c8097cd3c00d32fbd94657b8b8168ae758fe9ae9a48df5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-01T07:44:24Z","title_canon_sha256":"397d4c7d08e79abd3cce2e6a340f396a9881a290ba27169eafa238f0ccbba5e5"},"schema_version":"1.0","source":{"id":"2404.00973","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.00973","created_at":"2026-07-05T08:02:59Z"},{"alias_kind":"arxiv_version","alias_value":"2404.00973v1","created_at":"2026-07-05T08:02:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00973","created_at":"2026-07-05T08:02:59Z"},{"alias_kind":"pith_short_12","alias_value":"JQTXDIQ5HW6Z","created_at":"2026-07-05T08:02:59Z"},{"alias_kind":"pith_short_16","alias_value":"JQTXDIQ5HW6ZFS7D","created_at":"2026-07-05T08:02:59Z"},{"alias_kind":"pith_short_8","alias_value":"JQTXDIQ5","created_at":"2026-07-05T08:02:59Z"}],"graph_snapshots":[{"event_id":"sha256:d2f2f15ed268abfaf87a3be9d23ba9aac2a655ec7faba04fac6d8e03b63a34bf","target":"graph","created_at":"2026-07-05T08:02:59Z","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/2404.00973/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Significant advancements in video question answering (VideoQA) have been made thanks to thriving large image-language pretraining frameworks. Although these image-language models can efficiently represent both video and language branches, they typically employ a goal-free vision perception process and do not interact vision with language well during the answer generation, thus omitting crucial visual cues. In this paper, we are inspired by the human recognition and learning pattern and propose VideoDistill, a framework with language-aware (i.e., goal-driven) behavior in both vision perception ","authors_text":"Bo Zou, Chao Yang, Chengbin Quan, Youjian Zhao, Yu Qiao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-01T07:44:24Z","title":"VideoDistill: Language-aware Vision Distillation for Video Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00973","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":"sha256:1481691530478d0f65c387e27ebe227fefa39c90d87598c7d6d4bfc86a664472","target":"record","created_at":"2026-07-05T08:02:59Z","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":"3d6fb106c6260cb927c8097cd3c00d32fbd94657b8b8168ae758fe9ae9a48df5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-01T07:44:24Z","title_canon_sha256":"397d4c7d08e79abd3cce2e6a340f396a9881a290ba27169eafa238f0ccbba5e5"},"schema_version":"1.0","source":{"id":"2404.00973","kind":"arxiv","version":1}},"canonical_sha256":"4c2771a21d3dbd92cbe315c9ba8eb0aad3b6e5a8a8b61c21e65146c369eb17d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c2771a21d3dbd92cbe315c9ba8eb0aad3b6e5a8a8b61c21e65146c369eb17d0","first_computed_at":"2026-07-05T08:02:59.437637Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:02:59.437637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K0BNCnheV8c7Rsf2DsgYt8g6gheXYawdjMymcKl68oAGudqizkPCw06BJNdmZUnauaIxZiapiWVVqhk00rPFAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:02:59.438170Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.00973","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1481691530478d0f65c387e27ebe227fefa39c90d87598c7d6d4bfc86a664472","sha256:d2f2f15ed268abfaf87a3be9d23ba9aac2a655ec7faba04fac6d8e03b63a34bf"],"state_sha256":"0455d2678a2485ec831515e7bf57ad73e91551b71beb29823e2ec7d059211e6d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e5C/MzkLEeENq0tBBbsZei0n6PlnYxQAxC181pli6ieoDYh0pBv8nVdAaVgamsyMlZRrlVSUI4waA5vcaVZGBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T05:33:14.834781Z","bundle_sha256":"4c2a2ed4e5fa2240138cedbf8e401ca20fbd0a7c5d110697e169f15595dfdb13"}}