{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PN5X6HEZA3YUD3LLRZEIQ5YS5Q","short_pith_number":"pith:PN5X6HEZ","canonical_record":{"source":{"id":"2405.13911","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-22T18:35:10Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"585be91f9f2334859b1047e564507dc95af547dd847086a70e78a2a16ff69119","abstract_canon_sha256":"ebed90ab08b3e988204d4a5f34f9dc8aec01fda1c51369066c33b16088798972"},"schema_version":"1.0"},"canonical_sha256":"7b7b7f1c9906f141ed6b8e48887712ec05a29eaab4b5a0ecd138f626698dd9c9","source":{"kind":"arxiv","id":"2405.13911","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.13911","created_at":"2026-07-05T09:30:14Z"},{"alias_kind":"arxiv_version","alias_value":"2405.13911v2","created_at":"2026-07-05T09:30:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.13911","created_at":"2026-07-05T09:30:14Z"},{"alias_kind":"pith_short_12","alias_value":"PN5X6HEZA3YU","created_at":"2026-07-05T09:30:14Z"},{"alias_kind":"pith_short_16","alias_value":"PN5X6HEZA3YUD3LL","created_at":"2026-07-05T09:30:14Z"},{"alias_kind":"pith_short_8","alias_value":"PN5X6HEZ","created_at":"2026-07-05T09:30:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PN5X6HEZA3YUD3LLRZEIQ5YS5Q","target":"record","payload":{"canonical_record":{"source":{"id":"2405.13911","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-22T18:35:10Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"585be91f9f2334859b1047e564507dc95af547dd847086a70e78a2a16ff69119","abstract_canon_sha256":"ebed90ab08b3e988204d4a5f34f9dc8aec01fda1c51369066c33b16088798972"},"schema_version":"1.0"},"canonical_sha256":"7b7b7f1c9906f141ed6b8e48887712ec05a29eaab4b5a0ecd138f626698dd9c9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:14.389006Z","signature_b64":"GtN9hFmEvG+ueuyd5L+q4/T/h46MsqEg1nr4e61gKz/8xSSY76MkytYojUGS90AGF6mZgFBIeQeUpZw/OBMhBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b7b7f1c9906f141ed6b8e48887712ec05a29eaab4b5a0ecd138f626698dd9c9","last_reissued_at":"2026-07-05T09:30:14.388516Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:14.388516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.13911","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":"2026-07-05T09:30:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5Kg6EASAPJdnCaW08pOx5/6A/EalzfKOAtgdu4mXhT2vS68cj5HS9uuVBmzdakYjOJ0wv45qF9I8GdvmYJH4Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T04:52:45.359613Z"},"content_sha256":"b3086c55cc2f6d580393c6133a5e4e91c69bb07420b53e885cfa2eb3ee58d71f","schema_version":"1.0","event_id":"sha256:b3086c55cc2f6d580393c6133a5e4e91c69bb07420b53e885cfa2eb3ee58d71f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PN5X6HEZA3YUD3LLRZEIQ5YS5Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Hehe Fan, Mohan Kankanhalli, Wei Li, Yi Yang, Yongkang Wong","submitted_at":"2024-05-22T18:35:10Z","abstract_excerpt":"Recent advancements in image understanding have benefited from the extensive use of web image-text pairs. However, video understanding remains a challenge despite the availability of substantial web video-text data. This difficulty primarily arises from the inherent complexity of videos and the inefficient language supervision in recent web-collected video-text datasets. In this paper, we introduce Text-Only Pre-Alignment (TOPA), a novel approach to extend large language models (LLMs) for video understanding, without the need for pre-training on real video data. Specifically, we first employ a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.13911","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/2405.13911/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":"2026-07-05T09:30:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3gMu7vY5tcS6S6cBociMHQtdE9EZRkG7DaXEyXPijIkREd4JCaVChne4j5nQiwKPHe/WNdNU7Ggsg+6In4NsBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T04:52:45.360131Z"},"content_sha256":"3aba016ee9e55925b0ba9de9c30550615484dbd26dafd98e7dcdd2eeab0b14ec","schema_version":"1.0","event_id":"sha256:3aba016ee9e55925b0ba9de9c30550615484dbd26dafd98e7dcdd2eeab0b14ec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PN5X6HEZA3YUD3LLRZEIQ5YS5Q/bundle.json","state_url":"https://pith.science/pith/PN5X6HEZA3YUD3LLRZEIQ5YS5Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PN5X6HEZA3YUD3LLRZEIQ5YS5Q/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":"2026-08-11T04:52:45Z","links":{"resolver":"https://pith.science/pith/PN5X6HEZA3YUD3LLRZEIQ5YS5Q","bundle":"https://pith.science/pith/PN5X6HEZA3YUD3LLRZEIQ5YS5Q/bundle.json","state":"https://pith.science/pith/PN5X6HEZA3YUD3LLRZEIQ5YS5Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PN5X6HEZA3YUD3LLRZEIQ5YS5Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PN5X6HEZA3YUD3LLRZEIQ5YS5Q","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":"ebed90ab08b3e988204d4a5f34f9dc8aec01fda1c51369066c33b16088798972","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-22T18:35:10Z","title_canon_sha256":"585be91f9f2334859b1047e564507dc95af547dd847086a70e78a2a16ff69119"},"schema_version":"1.0","source":{"id":"2405.13911","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.13911","created_at":"2026-07-05T09:30:14Z"},{"alias_kind":"arxiv_version","alias_value":"2405.13911v2","created_at":"2026-07-05T09:30:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.13911","created_at":"2026-07-05T09:30:14Z"},{"alias_kind":"pith_short_12","alias_value":"PN5X6HEZA3YU","created_at":"2026-07-05T09:30:14Z"},{"alias_kind":"pith_short_16","alias_value":"PN5X6HEZA3YUD3LL","created_at":"2026-07-05T09:30:14Z"},{"alias_kind":"pith_short_8","alias_value":"PN5X6HEZ","created_at":"2026-07-05T09:30:14Z"}],"graph_snapshots":[{"event_id":"sha256:3aba016ee9e55925b0ba9de9c30550615484dbd26dafd98e7dcdd2eeab0b14ec","target":"graph","created_at":"2026-07-05T09:30:14Z","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/2405.13911/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in image understanding have benefited from the extensive use of web image-text pairs. However, video understanding remains a challenge despite the availability of substantial web video-text data. This difficulty primarily arises from the inherent complexity of videos and the inefficient language supervision in recent web-collected video-text datasets. In this paper, we introduce Text-Only Pre-Alignment (TOPA), a novel approach to extend large language models (LLMs) for video understanding, without the need for pre-training on real video data. Specifically, we first employ a","authors_text":"Hehe Fan, Mohan Kankanhalli, Wei Li, Yi Yang, Yongkang Wong","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-22T18:35:10Z","title":"TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.13911","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:b3086c55cc2f6d580393c6133a5e4e91c69bb07420b53e885cfa2eb3ee58d71f","target":"record","created_at":"2026-07-05T09:30:14Z","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":"ebed90ab08b3e988204d4a5f34f9dc8aec01fda1c51369066c33b16088798972","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-22T18:35:10Z","title_canon_sha256":"585be91f9f2334859b1047e564507dc95af547dd847086a70e78a2a16ff69119"},"schema_version":"1.0","source":{"id":"2405.13911","kind":"arxiv","version":2}},"canonical_sha256":"7b7b7f1c9906f141ed6b8e48887712ec05a29eaab4b5a0ecd138f626698dd9c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b7b7f1c9906f141ed6b8e48887712ec05a29eaab4b5a0ecd138f626698dd9c9","first_computed_at":"2026-07-05T09:30:14.388516Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:30:14.388516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GtN9hFmEvG+ueuyd5L+q4/T/h46MsqEg1nr4e61gKz/8xSSY76MkytYojUGS90AGF6mZgFBIeQeUpZw/OBMhBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:30:14.389006Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.13911","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b3086c55cc2f6d580393c6133a5e4e91c69bb07420b53e885cfa2eb3ee58d71f","sha256:3aba016ee9e55925b0ba9de9c30550615484dbd26dafd98e7dcdd2eeab0b14ec"],"state_sha256":"9133bdef6bbcf437c8de33ac7dcf6cd0c112bbd43693e0b851accd3034037465"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YD8mdsAEnWn5bRWYwlFF2oTQYEz0pM7zcG1Bgxea+aUHZXZe0sDeUTqqYOxMRu05g1deZz7ywQ7xgSCvrjMpDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T04:52:45.364152Z","bundle_sha256":"442784058d37492724461aa21387eac6ff96b91bd7c713650fd0a258cc6b45af"}}