{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:QDHZZSJOHQG35S5R3MTNAVGK4W","short_pith_number":"pith:QDHZZSJO","canonical_record":{"source":{"id":"2309.10783","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-19T17:32:21Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"ba629c179269b39c26650bcdb679d57cb1b2794f3292431d84435d713200b1b2","abstract_canon_sha256":"b211eda706055702c98255a6a603fab8d93e4f9d535f67c4bdabeb74682092e3"},"schema_version":"1.0"},"canonical_sha256":"80cf9cc92e3c0dbecbb1db26d054cae59c563f6f4ec11894de1c9bd5bedf090a","source":{"kind":"arxiv","id":"2309.10783","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.10783","created_at":"2026-07-05T06:52:17Z"},{"alias_kind":"arxiv_version","alias_value":"2309.10783v1","created_at":"2026-07-05T06:52:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.10783","created_at":"2026-07-05T06:52:17Z"},{"alias_kind":"pith_short_12","alias_value":"QDHZZSJOHQG3","created_at":"2026-07-05T06:52:17Z"},{"alias_kind":"pith_short_16","alias_value":"QDHZZSJOHQG35S5R","created_at":"2026-07-05T06:52:17Z"},{"alias_kind":"pith_short_8","alias_value":"QDHZZSJO","created_at":"2026-07-05T06:52:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:QDHZZSJOHQG35S5R3MTNAVGK4W","target":"record","payload":{"canonical_record":{"source":{"id":"2309.10783","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-19T17:32:21Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"ba629c179269b39c26650bcdb679d57cb1b2794f3292431d84435d713200b1b2","abstract_canon_sha256":"b211eda706055702c98255a6a603fab8d93e4f9d535f67c4bdabeb74682092e3"},"schema_version":"1.0"},"canonical_sha256":"80cf9cc92e3c0dbecbb1db26d054cae59c563f6f4ec11894de1c9bd5bedf090a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:52:17.145356Z","signature_b64":"XxQppi2XflndTp3n93vRhfllrwGVbyhaLuNDE2TVI2A7y69tPA0dOOaPHtvcKODynabdTLu2kyv12BkUAGmbAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80cf9cc92e3c0dbecbb1db26d054cae59c563f6f4ec11894de1c9bd5bedf090a","last_reissued_at":"2026-07-05T06:52:17.144886Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:52:17.144886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.10783","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":"2026-07-05T06:52:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QflkaVdbpyjhwOuE5jp/gM5WwIfV47J4rvNEfKafDbkuosTUAbhUdjYkmVOKIzmliMbeziu2kxyJmnebpVE7Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T23:42:56.272072Z"},"content_sha256":"e7dac83421360ce294f06d1da62c3bf73b6f60b169d4252b5dbb27659a170433","schema_version":"1.0","event_id":"sha256:e7dac83421360ce294f06d1da62c3bf73b6f60b169d4252b5dbb27659a170433"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:QDHZZSJOHQG35S5R3MTNAVGK4W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Language as the Medium: Multimodal Video Classification through text only","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Anita L. Ver\\H{o}, James Thewlis, Laura Hanu","submitted_at":"2023-09-19T17:32:21Z","abstract_excerpt":"Despite an exciting new wave of multimodal machine learning models, current approaches still struggle to interpret the complex contextual relationships between the different modalities present in videos. Going beyond existing methods that emphasize simple activities or objects, we propose a new model-agnostic approach for generating detailed textual descriptions that captures multimodal video information. Our method leverages the extensive knowledge learnt by large language models, such as GPT-3.5 or Llama2, to reason about textual descriptions of the visual and aural modalities, obtained from"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10783","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/2309.10783/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":"2026-07-05T06:52:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QBndkAonmwdCNGGhnCHwNRlA+FmORXBUEHgmEwhd4a/ZN8gzwmMZ/jxKYG2vSakz5MEiIa+SgH5CILx4SkzDAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T23:42:56.272970Z"},"content_sha256":"62d0cc7eb4672f21838e9331946a86b9af139f4f6f7c8f8831ffa8dc8d966788","schema_version":"1.0","event_id":"sha256:62d0cc7eb4672f21838e9331946a86b9af139f4f6f7c8f8831ffa8dc8d966788"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QDHZZSJOHQG35S5R3MTNAVGK4W/bundle.json","state_url":"https://pith.science/pith/QDHZZSJOHQG35S5R3MTNAVGK4W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QDHZZSJOHQG35S5R3MTNAVGK4W/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":"2026-08-19T23:42:56Z","links":{"resolver":"https://pith.science/pith/QDHZZSJOHQG35S5R3MTNAVGK4W","bundle":"https://pith.science/pith/QDHZZSJOHQG35S5R3MTNAVGK4W/bundle.json","state":"https://pith.science/pith/QDHZZSJOHQG35S5R3MTNAVGK4W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QDHZZSJOHQG35S5R3MTNAVGK4W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QDHZZSJOHQG35S5R3MTNAVGK4W","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":"b211eda706055702c98255a6a603fab8d93e4f9d535f67c4bdabeb74682092e3","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-19T17:32:21Z","title_canon_sha256":"ba629c179269b39c26650bcdb679d57cb1b2794f3292431d84435d713200b1b2"},"schema_version":"1.0","source":{"id":"2309.10783","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.10783","created_at":"2026-07-05T06:52:17Z"},{"alias_kind":"arxiv_version","alias_value":"2309.10783v1","created_at":"2026-07-05T06:52:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.10783","created_at":"2026-07-05T06:52:17Z"},{"alias_kind":"pith_short_12","alias_value":"QDHZZSJOHQG3","created_at":"2026-07-05T06:52:17Z"},{"alias_kind":"pith_short_16","alias_value":"QDHZZSJOHQG35S5R","created_at":"2026-07-05T06:52:17Z"},{"alias_kind":"pith_short_8","alias_value":"QDHZZSJO","created_at":"2026-07-05T06:52:17Z"}],"graph_snapshots":[{"event_id":"sha256:62d0cc7eb4672f21838e9331946a86b9af139f4f6f7c8f8831ffa8dc8d966788","target":"graph","created_at":"2026-07-05T06:52:17Z","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/2309.10783/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite an exciting new wave of multimodal machine learning models, current approaches still struggle to interpret the complex contextual relationships between the different modalities present in videos. Going beyond existing methods that emphasize simple activities or objects, we propose a new model-agnostic approach for generating detailed textual descriptions that captures multimodal video information. Our method leverages the extensive knowledge learnt by large language models, such as GPT-3.5 or Llama2, to reason about textual descriptions of the visual and aural modalities, obtained from","authors_text":"Anita L. Ver\\H{o}, James Thewlis, Laura Hanu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-19T17:32:21Z","title":"Language as the Medium: Multimodal Video Classification through text only"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10783","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:e7dac83421360ce294f06d1da62c3bf73b6f60b169d4252b5dbb27659a170433","target":"record","created_at":"2026-07-05T06:52:17Z","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":"b211eda706055702c98255a6a603fab8d93e4f9d535f67c4bdabeb74682092e3","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-19T17:32:21Z","title_canon_sha256":"ba629c179269b39c26650bcdb679d57cb1b2794f3292431d84435d713200b1b2"},"schema_version":"1.0","source":{"id":"2309.10783","kind":"arxiv","version":1}},"canonical_sha256":"80cf9cc92e3c0dbecbb1db26d054cae59c563f6f4ec11894de1c9bd5bedf090a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80cf9cc92e3c0dbecbb1db26d054cae59c563f6f4ec11894de1c9bd5bedf090a","first_computed_at":"2026-07-05T06:52:17.144886Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:52:17.144886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XxQppi2XflndTp3n93vRhfllrwGVbyhaLuNDE2TVI2A7y69tPA0dOOaPHtvcKODynabdTLu2kyv12BkUAGmbAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:52:17.145356Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.10783","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e7dac83421360ce294f06d1da62c3bf73b6f60b169d4252b5dbb27659a170433","sha256:62d0cc7eb4672f21838e9331946a86b9af139f4f6f7c8f8831ffa8dc8d966788"],"state_sha256":"c332007fd6a2b3b48d5395c8b571266673a51878511a22d0ebfc464e60945113"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eayiSf1mPXeW57H7z4LDH9aYfQ69wUVaq8FSQ22xAnvJr0bFJGp/+TuJZYunNAuTY6kn++0xUU7OgUpGUO8VBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T23:42:56.277762Z","bundle_sha256":"99462ec7758d4684170a4e468f48869c8792b13b88b2e9043664c4258ffdb46e"}}