{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BUZ7W4MF2MBT2C65V4HB3BKU6K","short_pith_number":"pith:BUZ7W4MF","canonical_record":{"source":{"id":"2404.16994","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-25T19:29:55Z","cross_cats_sorted":[],"title_canon_sha256":"f6dc7cafb3ca23a25cca7272ff45a3eee92caa94cdd7e103c0d0d8552bddf719","abstract_canon_sha256":"00e0c64dde30021d2f834453a2d09e667f67fe7f2f1ae48439d07281cc292fe5"},"schema_version":"1.0"},"canonical_sha256":"0d33fb7185d3033d0bddaf0e1d8554f28a4ebede14e0f23f82c674abe7cb32e0","source":{"kind":"arxiv","id":"2404.16994","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.16994","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"arxiv_version","alias_value":"2404.16994v2","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.16994","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"pith_short_12","alias_value":"BUZ7W4MF2MBT","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"BUZ7W4MF2MBT2C65","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"BUZ7W4MF","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BUZ7W4MF2MBT2C65V4HB3BKU6K","target":"record","payload":{"canonical_record":{"source":{"id":"2404.16994","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-25T19:29:55Z","cross_cats_sorted":[],"title_canon_sha256":"f6dc7cafb3ca23a25cca7272ff45a3eee92caa94cdd7e103c0d0d8552bddf719","abstract_canon_sha256":"00e0c64dde30021d2f834453a2d09e667f67fe7f2f1ae48439d07281cc292fe5"},"schema_version":"1.0"},"canonical_sha256":"0d33fb7185d3033d0bddaf0e1d8554f28a4ebede14e0f23f82c674abe7cb32e0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:50.286985Z","signature_b64":"7BZmRL9cpIAqj+azgWjNLK9iOiMAQauMIhCl+lMdhPYYB7YQGe+ShETOZpoDp0EXINcjq4f1CmHN8u6TSqrgAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d33fb7185d3033d0bddaf0e1d8554f28a4ebede14e0f23f82c674abe7cb32e0","last_reissued_at":"2026-05-17T23:38:50.286434Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:50.286434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.16994","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":"2026-05-17T23:38:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xDVklhp3UnwM+4apxGBM1bv9MxLu4HOI+2WQ7OH16OrKEITdsdqa5LCINxz3FAWQPG6YbgD56tIssOmRxnW1Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T10:27:45.004281Z"},"content_sha256":"a78af9f6c93710189cddb3a4ff5784ada1831822af992faa4c02229e7070cd5e","schema_version":"1.0","event_id":"sha256:a78af9f6c93710189cddb3a4ff5784ada1831822af992faa4c02229e7070cd5e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BUZ7W4MF2MBT2C65V4HB3BKU6K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"A parameter-free temporal pooling strategy lets image-language models extend directly to video dense captioning and question answering without added parameters or heavy retraining.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daquan Zhou, Jiashi Feng, Lin Xu, See Kiong Ng, Yilin Zhao, Zhijie Lin","submitted_at":"2024-04-25T19:29:55Z","abstract_excerpt":"Vision-language pre-training has significantly elevated performance across a wide range of image-language applications. Yet, the pre-training process for video-related tasks demands exceptionally large computational and data resources, which hinders the progress of video-language models. This paper investigates a straight-forward, highly efficient, and resource-light approach to adapting an existing image-language pre-trained model for dense video understanding. Our preliminary experiments reveal that directly fine-tuning pre-trained image-language models with multiple frames as inputs on vide"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"PLLaVA achieves 3.48/5 on VideoChatGPT (9% above GPT-4V IG-VLM) and 58.1% on MVBench (14.5% above GPT-4V IG-VLM) by applying a parameter-free temporal pooling strategy that mitigates high-norm feature bias.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the performance drop when feeding multiple frames directly is caused primarily by high-norm visual feature bias rather than by other factors such as temporal modeling capacity or training data mismatch.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A temporal pooling layer added to LLaVA smooths video feature distributions and lifts performance on dense video captioning and QA to new SOTA levels without extra parameters.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A parameter-free temporal pooling strategy lets image-language models extend directly to video dense captioning and question answering without added parameters or heavy retraining.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"8a4a1585ddad7ccb6a1212c7f6ee77426fcbbde33839b6d7d1f901555d7a0dba"},"source":{"id":"2404.16994","kind":"arxiv","version":2},"verdict":{"id":"0ab945e4-32d6-48c8-a134-bce6542669c1","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T20:18:37.088390Z","strongest_claim":"PLLaVA achieves 3.48/5 on VideoChatGPT (9% above GPT-4V IG-VLM) and 58.1% on MVBench (14.5% above GPT-4V IG-VLM) by applying a parameter-free temporal pooling strategy that mitigates high-norm feature bias.","one_line_summary":"A temporal pooling layer added to LLaVA smooths video feature distributions and lifts performance on dense video captioning and QA to new SOTA levels without extra parameters.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the performance drop when feeding multiple frames directly is caused primarily by high-norm visual feature bias rather than by other factors such as temporal modeling capacity or training data mismatch.","pith_extraction_headline":"A parameter-free temporal pooling strategy lets image-language models extend directly to video dense captioning and question answering without added parameters or heavy retraining."},"references":{"count":53,"sample":[{"doi":"","year":2023,"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","ref_index":1,"cited_arxiv_id":"2303.08774","is_internal_anchor":true},{"doi":"","year":2021,"title":"Frozen in time: A joint video and image encoder for end-to-end retrieval","work_id":"2a136f10-92cd-4a8d-96ba-7aa9ab74f8d3","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Videollm: Modeling video sequence with large language models","work_id":"b2dab7c7-a0c3-46e2-99e3-b19a08e2436b","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","ref_index":4,"cited_arxiv_id":"2107.03374","is_internal_anchor":true},{"doi":"","year":2023,"title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality","work_id":"61034f5e-003f-4ba2-b05e-f332bf79c5d5","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":53,"snapshot_sha256":"835ef22f9bfc629c0781e381327ee441ddf0421407bcaf20da4642a10abe07dc","internal_anchors":9},"formal_canon":{"evidence_count":1,"snapshot_sha256":"ac4edc97a35346b99dd1c7e90cd9aca510e25c658d24c49337c19bcc59f27eb0"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"0ab945e4-32d6-48c8-a134-bce6542669c1"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o5rVnzwhfIq8ajyTVY2k5Mwtq6QAX4Rxi+SvxJotanWWpnESZszn+dEqbH8J/JCZ7DckKLkRF7k+H1mrmZi8Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T10:27:45.005296Z"},"content_sha256":"cef52ab4a9a703301ee3c776cb43d4ed8d689b9a8df202847ae75aa2ee0c99e8","schema_version":"1.0","event_id":"sha256:cef52ab4a9a703301ee3c776cb43d4ed8d689b9a8df202847ae75aa2ee0c99e8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BUZ7W4MF2MBT2C65V4HB3BKU6K/bundle.json","state_url":"https://pith.science/pith/BUZ7W4MF2MBT2C65V4HB3BKU6K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BUZ7W4MF2MBT2C65V4HB3BKU6K/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":"2026-06-10T10:27:45Z","links":{"resolver":"https://pith.science/pith/BUZ7W4MF2MBT2C65V4HB3BKU6K","bundle":"https://pith.science/pith/BUZ7W4MF2MBT2C65V4HB3BKU6K/bundle.json","state":"https://pith.science/pith/BUZ7W4MF2MBT2C65V4HB3BKU6K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BUZ7W4MF2MBT2C65V4HB3BKU6K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BUZ7W4MF2MBT2C65V4HB3BKU6K","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":"00e0c64dde30021d2f834453a2d09e667f67fe7f2f1ae48439d07281cc292fe5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-25T19:29:55Z","title_canon_sha256":"f6dc7cafb3ca23a25cca7272ff45a3eee92caa94cdd7e103c0d0d8552bddf719"},"schema_version":"1.0","source":{"id":"2404.16994","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.16994","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"arxiv_version","alias_value":"2404.16994v2","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.16994","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"pith_short_12","alias_value":"BUZ7W4MF2MBT","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"BUZ7W4MF2MBT2C65","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"BUZ7W4MF","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:cef52ab4a9a703301ee3c776cb43d4ed8d689b9a8df202847ae75aa2ee0c99e8","target":"graph","created_at":"2026-05-17T23:38:50Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"PLLaVA achieves 3.48/5 on VideoChatGPT (9% above GPT-4V IG-VLM) and 58.1% on MVBench (14.5% above GPT-4V IG-VLM) by applying a parameter-free temporal pooling strategy that mitigates high-norm feature bias."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the performance drop when feeding multiple frames directly is caused primarily by high-norm visual feature bias rather than by other factors such as temporal modeling capacity or training data mismatch."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A temporal pooling layer added to LLaVA smooths video feature distributions and lifts performance on dense video captioning and QA to new SOTA levels without extra parameters."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A parameter-free temporal pooling strategy lets image-language models extend directly to video dense captioning and question answering without added parameters or heavy retraining."}],"snapshot_sha256":"8a4a1585ddad7ccb6a1212c7f6ee77426fcbbde33839b6d7d1f901555d7a0dba"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"ac4edc97a35346b99dd1c7e90cd9aca510e25c658d24c49337c19bcc59f27eb0"},"paper":{"abstract_excerpt":"Vision-language pre-training has significantly elevated performance across a wide range of image-language applications. Yet, the pre-training process for video-related tasks demands exceptionally large computational and data resources, which hinders the progress of video-language models. This paper investigates a straight-forward, highly efficient, and resource-light approach to adapting an existing image-language pre-trained model for dense video understanding. Our preliminary experiments reveal that directly fine-tuning pre-trained image-language models with multiple frames as inputs on vide","authors_text":"Daquan Zhou, Jiashi Feng, Lin Xu, See Kiong Ng, Yilin Zhao, Zhijie Lin","cross_cats":[],"headline":"A parameter-free temporal pooling strategy lets image-language models extend directly to video dense captioning and question answering without added parameters or heavy retraining.","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-25T19:29:55Z","title":"PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning"},"references":{"count":53,"internal_anchors":9,"resolved_work":53,"sample":[{"cited_arxiv_id":"2303.08774","doi":"","is_internal_anchor":true,"ref_index":1,"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Frozen in time: A joint video and image encoder for end-to-end retrieval","work_id":"2a136f10-92cd-4a8d-96ba-7aa9ab74f8d3","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Videollm: Modeling video sequence with large language models","work_id":"b2dab7c7-a0c3-46e2-99e3-b19a08e2436b","year":2023},{"cited_arxiv_id":"2107.03374","doi":"","is_internal_anchor":true,"ref_index":4,"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality","work_id":"61034f5e-003f-4ba2-b05e-f332bf79c5d5","year":2023}],"snapshot_sha256":"835ef22f9bfc629c0781e381327ee441ddf0421407bcaf20da4642a10abe07dc"},"source":{"id":"2404.16994","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-15T20:18:37.088390Z","id":"0ab945e4-32d6-48c8-a134-bce6542669c1","model_set":{"reader":"grok-4.3"},"one_line_summary":"A temporal pooling layer added to LLaVA smooths video feature distributions and lifts performance on dense video captioning and QA to new SOTA levels without extra parameters.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A parameter-free temporal pooling strategy lets image-language models extend directly to video dense captioning and question answering without added parameters or heavy retraining.","strongest_claim":"PLLaVA achieves 3.48/5 on VideoChatGPT (9% above GPT-4V IG-VLM) and 58.1% on MVBench (14.5% above GPT-4V IG-VLM) by applying a parameter-free temporal pooling strategy that mitigates high-norm feature bias.","weakest_assumption":"That the performance drop when feeding multiple frames directly is caused primarily by high-norm visual feature bias rather than by other factors such as temporal modeling capacity or training data mismatch."}},"verdict_id":"0ab945e4-32d6-48c8-a134-bce6542669c1"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a78af9f6c93710189cddb3a4ff5784ada1831822af992faa4c02229e7070cd5e","target":"record","created_at":"2026-05-17T23:38:50Z","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":"00e0c64dde30021d2f834453a2d09e667f67fe7f2f1ae48439d07281cc292fe5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-25T19:29:55Z","title_canon_sha256":"f6dc7cafb3ca23a25cca7272ff45a3eee92caa94cdd7e103c0d0d8552bddf719"},"schema_version":"1.0","source":{"id":"2404.16994","kind":"arxiv","version":2}},"canonical_sha256":"0d33fb7185d3033d0bddaf0e1d8554f28a4ebede14e0f23f82c674abe7cb32e0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d33fb7185d3033d0bddaf0e1d8554f28a4ebede14e0f23f82c674abe7cb32e0","first_computed_at":"2026-05-17T23:38:50.286434Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:50.286434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7BZmRL9cpIAqj+azgWjNLK9iOiMAQauMIhCl+lMdhPYYB7YQGe+ShETOZpoDp0EXINcjq4f1CmHN8u6TSqrgAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:50.286985Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.16994","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a78af9f6c93710189cddb3a4ff5784ada1831822af992faa4c02229e7070cd5e","sha256:cef52ab4a9a703301ee3c776cb43d4ed8d689b9a8df202847ae75aa2ee0c99e8"],"state_sha256":"01358feee86dbcfca0ac0cd9929d26d80d77f324304239e2a94395803e320139"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G2QFL8LpKvQ083fdxYC5qwUbBBkZrq9gR5YZi/bAa4d/IN7PhjOeYgZVCzD3DsiagI3+MoR7RCEMflH8AeaoBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T10:27:45.010993Z","bundle_sha256":"a6bea0294559a5fc251aec75b4ecfd36d917f44cc86fe0e095693467d9df8561"}}