{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:DXT5ZRIDMAZEJDO2FOXUMQ2KZV","short_pith_number":"pith:DXT5ZRID","canonical_record":{"source":{"id":"2301.11507","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-01-27T03:00:43Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"c6472edd086086d5425a4dfd081bca43fcbfa6c3fdb55f65919f18144915db80","abstract_canon_sha256":"1d3a66a4231e15152f76e00ae7c83b4eaf4e9a0a15ea1217bdb2295542f75923"},"schema_version":"1.0"},"canonical_sha256":"1de7dcc5036032448dda2baf46434acd690fb940c798d73487c0f74e56ad7044","source":{"kind":"arxiv","id":"2301.11507","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.11507","created_at":"2026-07-05T05:36:22Z"},{"alias_kind":"arxiv_version","alias_value":"2301.11507v1","created_at":"2026-07-05T05:36:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.11507","created_at":"2026-07-05T05:36:22Z"},{"alias_kind":"pith_short_12","alias_value":"DXT5ZRIDMAZE","created_at":"2026-07-05T05:36:22Z"},{"alias_kind":"pith_short_16","alias_value":"DXT5ZRIDMAZEJDO2","created_at":"2026-07-05T05:36:22Z"},{"alias_kind":"pith_short_8","alias_value":"DXT5ZRID","created_at":"2026-07-05T05:36:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:DXT5ZRIDMAZEJDO2FOXUMQ2KZV","target":"record","payload":{"canonical_record":{"source":{"id":"2301.11507","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-01-27T03:00:43Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"c6472edd086086d5425a4dfd081bca43fcbfa6c3fdb55f65919f18144915db80","abstract_canon_sha256":"1d3a66a4231e15152f76e00ae7c83b4eaf4e9a0a15ea1217bdb2295542f75923"},"schema_version":"1.0"},"canonical_sha256":"1de7dcc5036032448dda2baf46434acd690fb940c798d73487c0f74e56ad7044","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:36:22.982584Z","signature_b64":"fGO02OMbmOgxzBKNTy4ki9nYGC9aL6VYUvQzjaGH00p0xGW8qI6c51j9oJbKQoxkqJaqf56CJrVW84mT9v1ECg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1de7dcc5036032448dda2baf46434acd690fb940c798d73487c0f74e56ad7044","last_reissued_at":"2026-07-05T05:36:22.982105Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:36:22.982105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.11507","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":"2026-07-05T05:36:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ANzIb0PNxqb5yasO+BaxKc96iLfF79GUpUQL7CSAzq9UGB5DWoBBit5ZAE4SBlGw1P2KYD7o1kvxkoyDhZOuCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T17:45:04.422079Z"},"content_sha256":"8013b577d81c11709838ba2f68fcb128a3ba5e099246a4c3d825dd330f19432c","schema_version":"1.0","event_id":"sha256:8013b577d81c11709838ba2f68fcb128a3ba5e099246a4c3d825dd330f19432c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:DXT5ZRIDMAZEJDO2FOXUMQ2KZV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Semi-Parametric Video-Grounded Text Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jin-Hwa Kim, Jiyoung Lee, Minjoon Seo, Sungdong Kim","submitted_at":"2023-01-27T03:00:43Z","abstract_excerpt":"Efficient video-language modeling should consider the computational cost because of a large, sometimes intractable, number of video frames. Parametric approaches such as the attention mechanism may not be ideal since its computational cost quadratically increases as the video length increases. Rather, previous studies have relied on offline feature extraction or frame sampling to represent the video efficiently, focusing on cross-modal modeling in short video clips. In this paper, we propose a semi-parametric video-grounded text generation model, SeViT, a novel perspective on scalable video-la"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.11507","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/2301.11507/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":"2026-07-05T05:36:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qB277YspBCVhYg0Aj6MMTyWlWzA0SRqzRVLbzcn0dkVfQWAIUZxCNHJffp8n5a0yPGcTrdWEYnpcWZAZme3zCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T17:45:04.422611Z"},"content_sha256":"adb618af587661032c7725b49752e5a4c52ba561853c765b6c32eedfd270c5bc","schema_version":"1.0","event_id":"sha256:adb618af587661032c7725b49752e5a4c52ba561853c765b6c32eedfd270c5bc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DXT5ZRIDMAZEJDO2FOXUMQ2KZV/bundle.json","state_url":"https://pith.science/pith/DXT5ZRIDMAZEJDO2FOXUMQ2KZV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DXT5ZRIDMAZEJDO2FOXUMQ2KZV/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":"2026-08-11T17:45:04Z","links":{"resolver":"https://pith.science/pith/DXT5ZRIDMAZEJDO2FOXUMQ2KZV","bundle":"https://pith.science/pith/DXT5ZRIDMAZEJDO2FOXUMQ2KZV/bundle.json","state":"https://pith.science/pith/DXT5ZRIDMAZEJDO2FOXUMQ2KZV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DXT5ZRIDMAZEJDO2FOXUMQ2KZV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DXT5ZRIDMAZEJDO2FOXUMQ2KZV","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":"1d3a66a4231e15152f76e00ae7c83b4eaf4e9a0a15ea1217bdb2295542f75923","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-01-27T03:00:43Z","title_canon_sha256":"c6472edd086086d5425a4dfd081bca43fcbfa6c3fdb55f65919f18144915db80"},"schema_version":"1.0","source":{"id":"2301.11507","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.11507","created_at":"2026-07-05T05:36:22Z"},{"alias_kind":"arxiv_version","alias_value":"2301.11507v1","created_at":"2026-07-05T05:36:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.11507","created_at":"2026-07-05T05:36:22Z"},{"alias_kind":"pith_short_12","alias_value":"DXT5ZRIDMAZE","created_at":"2026-07-05T05:36:22Z"},{"alias_kind":"pith_short_16","alias_value":"DXT5ZRIDMAZEJDO2","created_at":"2026-07-05T05:36:22Z"},{"alias_kind":"pith_short_8","alias_value":"DXT5ZRID","created_at":"2026-07-05T05:36:22Z"}],"graph_snapshots":[{"event_id":"sha256:adb618af587661032c7725b49752e5a4c52ba561853c765b6c32eedfd270c5bc","target":"graph","created_at":"2026-07-05T05:36:22Z","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/2301.11507/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Efficient video-language modeling should consider the computational cost because of a large, sometimes intractable, number of video frames. Parametric approaches such as the attention mechanism may not be ideal since its computational cost quadratically increases as the video length increases. Rather, previous studies have relied on offline feature extraction or frame sampling to represent the video efficiently, focusing on cross-modal modeling in short video clips. In this paper, we propose a semi-parametric video-grounded text generation model, SeViT, a novel perspective on scalable video-la","authors_text":"Jin-Hwa Kim, Jiyoung Lee, Minjoon Seo, Sungdong Kim","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-01-27T03:00:43Z","title":"Semi-Parametric Video-Grounded Text Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.11507","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":"sha256:8013b577d81c11709838ba2f68fcb128a3ba5e099246a4c3d825dd330f19432c","target":"record","created_at":"2026-07-05T05:36:22Z","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":"1d3a66a4231e15152f76e00ae7c83b4eaf4e9a0a15ea1217bdb2295542f75923","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-01-27T03:00:43Z","title_canon_sha256":"c6472edd086086d5425a4dfd081bca43fcbfa6c3fdb55f65919f18144915db80"},"schema_version":"1.0","source":{"id":"2301.11507","kind":"arxiv","version":1}},"canonical_sha256":"1de7dcc5036032448dda2baf46434acd690fb940c798d73487c0f74e56ad7044","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1de7dcc5036032448dda2baf46434acd690fb940c798d73487c0f74e56ad7044","first_computed_at":"2026-07-05T05:36:22.982105Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:36:22.982105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fGO02OMbmOgxzBKNTy4ki9nYGC9aL6VYUvQzjaGH00p0xGW8qI6c51j9oJbKQoxkqJaqf56CJrVW84mT9v1ECg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:36:22.982584Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.11507","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8013b577d81c11709838ba2f68fcb128a3ba5e099246a4c3d825dd330f19432c","sha256:adb618af587661032c7725b49752e5a4c52ba561853c765b6c32eedfd270c5bc"],"state_sha256":"ed85080488954361bb21bc1adaa289a20d8469f267f4bbf5aad7e77ccf4596b8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JkLtnJHgj1snLeXDeYyALJQZbjPnVSYoTYUPTdNpPUI0+QY6kzI0RZsw8xFYe2w9FCSirdbTgAfoRwtybGvSCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T17:45:04.428137Z","bundle_sha256":"afe51534146ba837810f42255623c887a6fb20d1622ccaedbc8b2ed7af0daffb"}}