{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:X2WTM6VYHUOOIWBHZA5QB4F52U","short_pith_number":"pith:X2WTM6VY","canonical_record":{"source":{"id":"2304.02560","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-05T16:30:36Z","cross_cats_sorted":[],"title_canon_sha256":"d8bd9d07d095bed28a60a0d05b43a3e2b52a5101b6e190701ec959bbd0604c43","abstract_canon_sha256":"acc172e0fca61ad531c56d63fc946b1f855c53396a0bfe3d78c0dd01e8e8dca4"},"schema_version":"1.0"},"canonical_sha256":"bead367ab83d1ce45827c83b00f0bdd519c855d9853b65492b02810662014522","source":{"kind":"arxiv","id":"2304.02560","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.02560","created_at":"2026-07-05T08:01:58Z"},{"alias_kind":"arxiv_version","alias_value":"2304.02560v2","created_at":"2026-07-05T08:01:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.02560","created_at":"2026-07-05T08:01:58Z"},{"alias_kind":"pith_short_12","alias_value":"X2WTM6VYHUOO","created_at":"2026-07-05T08:01:58Z"},{"alias_kind":"pith_short_16","alias_value":"X2WTM6VYHUOOIWBH","created_at":"2026-07-05T08:01:58Z"},{"alias_kind":"pith_short_8","alias_value":"X2WTM6VY","created_at":"2026-07-05T08:01:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:X2WTM6VYHUOOIWBHZA5QB4F52U","target":"record","payload":{"canonical_record":{"source":{"id":"2304.02560","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-05T16:30:36Z","cross_cats_sorted":[],"title_canon_sha256":"d8bd9d07d095bed28a60a0d05b43a3e2b52a5101b6e190701ec959bbd0604c43","abstract_canon_sha256":"acc172e0fca61ad531c56d63fc946b1f855c53396a0bfe3d78c0dd01e8e8dca4"},"schema_version":"1.0"},"canonical_sha256":"bead367ab83d1ce45827c83b00f0bdd519c855d9853b65492b02810662014522","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:01:58.810676Z","signature_b64":"kFYjyHVSiYDJ1kllWFhBMK0IPujoHAlIil/va0rYvWHc/z+6HeUs1SWPBnYtJ1+Wou+7ynBM0XgoU2P9rPhBDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bead367ab83d1ce45827c83b00f0bdd519c855d9853b65492b02810662014522","last_reissued_at":"2026-07-05T08:01:58.810292Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:01:58.810292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.02560","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":"2026-07-05T08:01:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u9BaSsl/RoEYFeSwgBhvaQDGXkONj4G5RmFnlWykF24eKnbybiI5rx1RJSJPlGmgN9RBcbe1TSrQofyGO8qJDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T13:51:01.175382Z"},"content_sha256":"27828289618f304d45ff60993630d6a6ae3240d2249d195c45147e7dece9843d","schema_version":"1.0","event_id":"sha256:27828289618f304d45ff60993630d6a6ae3240d2249d195c45147e7dece9843d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:X2WTM6VYHUOOIWBHZA5QB4F52U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VicTR: Video-conditioned Text Representations for Activity Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anurag Arnab, Arsha Nagrani, Kumara Kahatapitiya, Michael S. Ryoo","submitted_at":"2023-04-05T16:30:36Z","abstract_excerpt":"Vision-Language models (VLMs) have excelled in the image-domain -- especially in zero-shot settings -- thanks to the availability of vast pretraining data (i.e., paired image-text samples). However for videos, such paired data is not as abundant. Therefore, video-VLMs are usually designed by adapting pretrained image-VLMs to the video-domain, instead of training from scratch. All such recipes rely on augmenting visual embeddings with temporal information (i.e., image $\\rightarrow$ video), often keeping text embeddings unchanged or even being discarded. In this paper, we argue the contrary, tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.02560","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/2304.02560/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":"2026-07-05T08:01:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hjnicCQc3McyAe8+cU3Jiw/0cfYPoFBQd6GgZIxaWLCbl+Gqp3wQ97slkInuwoswe64hT9NHtNxoEL7CqhKLBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T13:51:01.175984Z"},"content_sha256":"8b9a4a8adb015cf3b65c0f0539ece755727d1d3fc54dca6c074e40b639f6e741","schema_version":"1.0","event_id":"sha256:8b9a4a8adb015cf3b65c0f0539ece755727d1d3fc54dca6c074e40b639f6e741"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X2WTM6VYHUOOIWBHZA5QB4F52U/bundle.json","state_url":"https://pith.science/pith/X2WTM6VYHUOOIWBHZA5QB4F52U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X2WTM6VYHUOOIWBHZA5QB4F52U/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":"2026-08-13T13:51:01Z","links":{"resolver":"https://pith.science/pith/X2WTM6VYHUOOIWBHZA5QB4F52U","bundle":"https://pith.science/pith/X2WTM6VYHUOOIWBHZA5QB4F52U/bundle.json","state":"https://pith.science/pith/X2WTM6VYHUOOIWBHZA5QB4F52U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X2WTM6VYHUOOIWBHZA5QB4F52U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:X2WTM6VYHUOOIWBHZA5QB4F52U","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":"acc172e0fca61ad531c56d63fc946b1f855c53396a0bfe3d78c0dd01e8e8dca4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-05T16:30:36Z","title_canon_sha256":"d8bd9d07d095bed28a60a0d05b43a3e2b52a5101b6e190701ec959bbd0604c43"},"schema_version":"1.0","source":{"id":"2304.02560","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.02560","created_at":"2026-07-05T08:01:58Z"},{"alias_kind":"arxiv_version","alias_value":"2304.02560v2","created_at":"2026-07-05T08:01:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.02560","created_at":"2026-07-05T08:01:58Z"},{"alias_kind":"pith_short_12","alias_value":"X2WTM6VYHUOO","created_at":"2026-07-05T08:01:58Z"},{"alias_kind":"pith_short_16","alias_value":"X2WTM6VYHUOOIWBH","created_at":"2026-07-05T08:01:58Z"},{"alias_kind":"pith_short_8","alias_value":"X2WTM6VY","created_at":"2026-07-05T08:01:58Z"}],"graph_snapshots":[{"event_id":"sha256:8b9a4a8adb015cf3b65c0f0539ece755727d1d3fc54dca6c074e40b639f6e741","target":"graph","created_at":"2026-07-05T08:01:58Z","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/2304.02560/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language models (VLMs) have excelled in the image-domain -- especially in zero-shot settings -- thanks to the availability of vast pretraining data (i.e., paired image-text samples). However for videos, such paired data is not as abundant. Therefore, video-VLMs are usually designed by adapting pretrained image-VLMs to the video-domain, instead of training from scratch. All such recipes rely on augmenting visual embeddings with temporal information (i.e., image $\\rightarrow$ video), often keeping text embeddings unchanged or even being discarded. In this paper, we argue the contrary, tha","authors_text":"Anurag Arnab, Arsha Nagrani, Kumara Kahatapitiya, Michael S. Ryoo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-05T16:30:36Z","title":"VicTR: Video-conditioned Text Representations for Activity Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.02560","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":"sha256:27828289618f304d45ff60993630d6a6ae3240d2249d195c45147e7dece9843d","target":"record","created_at":"2026-07-05T08:01:58Z","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":"acc172e0fca61ad531c56d63fc946b1f855c53396a0bfe3d78c0dd01e8e8dca4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-05T16:30:36Z","title_canon_sha256":"d8bd9d07d095bed28a60a0d05b43a3e2b52a5101b6e190701ec959bbd0604c43"},"schema_version":"1.0","source":{"id":"2304.02560","kind":"arxiv","version":2}},"canonical_sha256":"bead367ab83d1ce45827c83b00f0bdd519c855d9853b65492b02810662014522","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bead367ab83d1ce45827c83b00f0bdd519c855d9853b65492b02810662014522","first_computed_at":"2026-07-05T08:01:58.810292Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:01:58.810292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kFYjyHVSiYDJ1kllWFhBMK0IPujoHAlIil/va0rYvWHc/z+6HeUs1SWPBnYtJ1+Wou+7ynBM0XgoU2P9rPhBDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:01:58.810676Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.02560","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:27828289618f304d45ff60993630d6a6ae3240d2249d195c45147e7dece9843d","sha256:8b9a4a8adb015cf3b65c0f0539ece755727d1d3fc54dca6c074e40b639f6e741"],"state_sha256":"fca6650afafdefc2896bef459e2d2f0fe96b38878b2820861c1a812db4133915"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Uhb1zH/bTW0IF4IN6NuF2zUZa9ZRPk8F7j4FTxG1EIRxrcxYlyI7TIJN/f59oF1ji4tNSQYl0PVh+Rhcw1tlAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T13:51:01.181463Z","bundle_sha256":"d882086fcf3d7da047f25eb873bc75a33c145714d46301604b45623767fd46b0"}}