{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:TWW6AUWTV6F7FG5WONYSD4MZ5F","short_pith_number":"pith:TWW6AUWT","canonical_record":{"source":{"id":"2312.11897","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-19T06:42:47Z","cross_cats_sorted":[],"title_canon_sha256":"95e3382a7c6d27832666f28cb855e22c4900e18b4abed5721c9729c10664d69d","abstract_canon_sha256":"02ea099064fde002a4e11b80e61e9beb0e74a4e32fac7bf3fb6739a81a62025e"},"schema_version":"1.0"},"canonical_sha256":"9dade052d3af8bf29bb6737121f199e96c52ff2770a1aab1d5b1c659081f8fb0","source":{"kind":"arxiv","id":"2312.11897","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.11897","created_at":"2026-07-05T08:56:16Z"},{"alias_kind":"arxiv_version","alias_value":"2312.11897v3","created_at":"2026-07-05T08:56:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.11897","created_at":"2026-07-05T08:56:16Z"},{"alias_kind":"pith_short_12","alias_value":"TWW6AUWTV6F7","created_at":"2026-07-05T08:56:16Z"},{"alias_kind":"pith_short_16","alias_value":"TWW6AUWTV6F7FG5W","created_at":"2026-07-05T08:56:16Z"},{"alias_kind":"pith_short_8","alias_value":"TWW6AUWT","created_at":"2026-07-05T08:56:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:TWW6AUWTV6F7FG5WONYSD4MZ5F","target":"record","payload":{"canonical_record":{"source":{"id":"2312.11897","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-19T06:42:47Z","cross_cats_sorted":[],"title_canon_sha256":"95e3382a7c6d27832666f28cb855e22c4900e18b4abed5721c9729c10664d69d","abstract_canon_sha256":"02ea099064fde002a4e11b80e61e9beb0e74a4e32fac7bf3fb6739a81a62025e"},"schema_version":"1.0"},"canonical_sha256":"9dade052d3af8bf29bb6737121f199e96c52ff2770a1aab1d5b1c659081f8fb0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:16.043329Z","signature_b64":"E2Wk4FKzVwOLBGrYneBfga+UEGGTz1dXcl8SxEyrPWRaP9SHbksiQ1j9qjIITQbpQtf/BuuMS3tkgIeSx7yqBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9dade052d3af8bf29bb6737121f199e96c52ff2770a1aab1d5b1c659081f8fb0","last_reissued_at":"2026-07-05T08:56:16.042977Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:16.042977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.11897","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:56:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZjlLbEgv0bls/+2iXjXGDY26G4Tfl+kv1B3JGXdjPEnbqgbXyNJ/onYoL/oVhGnNwRGdd8tzlemNDaoynPOIAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T17:28:59.069173Z"},"content_sha256":"9bb7937462deea41dd602c8965d33cd0919d499de25622b65563ac57d9d3d314","schema_version":"1.0","event_id":"sha256:9bb7937462deea41dd602c8965d33cd0919d499de25622b65563ac57d9d3d314"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:TWW6AUWTV6F7FG5WONYSD4MZ5F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Text-Conditioned Resampler For Long Form Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alessio Tonioni, Andrew Zisserman, Bruno Korbar, Federico Tombari, Yongqin Xian","submitted_at":"2023-12-19T06:42:47Z","abstract_excerpt":"In this paper we present a text-conditioned video resampler (TCR) module that uses a pre-trained and frozen visual encoder and large language model (LLM) to process long video sequences for a task. TCR localises relevant visual features from the video given a text condition and provides them to a LLM to generate a text response. Due to its lightweight design and use of cross-attention, TCR can process more than 100 frames at a time with plain attention and without optimised implementations. We make the following contributions: (i) we design a transformer-based sampling architecture that can pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.11897","kind":"arxiv","version":3},"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/2312.11897/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":"2026-07-05T08:56:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ercxhDrpDHFaRFBuCQ1jmQhGust62pkfhpsEE8nXuxnIqNhwTVaFJYJXPpF3PWNixgDC76TqqmuYHbQfLsnKAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T17:28:59.069674Z"},"content_sha256":"012fbcbf421e9704e887548033047a1b0bed9c16beb3757c6f4e9efb49f66880","schema_version":"1.0","event_id":"sha256:012fbcbf421e9704e887548033047a1b0bed9c16beb3757c6f4e9efb49f66880"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TWW6AUWTV6F7FG5WONYSD4MZ5F/bundle.json","state_url":"https://pith.science/pith/TWW6AUWTV6F7FG5WONYSD4MZ5F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TWW6AUWTV6F7FG5WONYSD4MZ5F/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":"2026-08-11T17:28:59Z","links":{"resolver":"https://pith.science/pith/TWW6AUWTV6F7FG5WONYSD4MZ5F","bundle":"https://pith.science/pith/TWW6AUWTV6F7FG5WONYSD4MZ5F/bundle.json","state":"https://pith.science/pith/TWW6AUWTV6F7FG5WONYSD4MZ5F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TWW6AUWTV6F7FG5WONYSD4MZ5F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TWW6AUWTV6F7FG5WONYSD4MZ5F","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":"02ea099064fde002a4e11b80e61e9beb0e74a4e32fac7bf3fb6739a81a62025e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-19T06:42:47Z","title_canon_sha256":"95e3382a7c6d27832666f28cb855e22c4900e18b4abed5721c9729c10664d69d"},"schema_version":"1.0","source":{"id":"2312.11897","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.11897","created_at":"2026-07-05T08:56:16Z"},{"alias_kind":"arxiv_version","alias_value":"2312.11897v3","created_at":"2026-07-05T08:56:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.11897","created_at":"2026-07-05T08:56:16Z"},{"alias_kind":"pith_short_12","alias_value":"TWW6AUWTV6F7","created_at":"2026-07-05T08:56:16Z"},{"alias_kind":"pith_short_16","alias_value":"TWW6AUWTV6F7FG5W","created_at":"2026-07-05T08:56:16Z"},{"alias_kind":"pith_short_8","alias_value":"TWW6AUWT","created_at":"2026-07-05T08:56:16Z"}],"graph_snapshots":[{"event_id":"sha256:012fbcbf421e9704e887548033047a1b0bed9c16beb3757c6f4e9efb49f66880","target":"graph","created_at":"2026-07-05T08:56:16Z","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/2312.11897/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper we present a text-conditioned video resampler (TCR) module that uses a pre-trained and frozen visual encoder and large language model (LLM) to process long video sequences for a task. TCR localises relevant visual features from the video given a text condition and provides them to a LLM to generate a text response. Due to its lightweight design and use of cross-attention, TCR can process more than 100 frames at a time with plain attention and without optimised implementations. We make the following contributions: (i) we design a transformer-based sampling architecture that can pr","authors_text":"Alessio Tonioni, Andrew Zisserman, Bruno Korbar, Federico Tombari, Yongqin Xian","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-19T06:42:47Z","title":"Text-Conditioned Resampler For Long Form Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.11897","kind":"arxiv","version":3},"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":"sha256:9bb7937462deea41dd602c8965d33cd0919d499de25622b65563ac57d9d3d314","target":"record","created_at":"2026-07-05T08:56:16Z","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":"02ea099064fde002a4e11b80e61e9beb0e74a4e32fac7bf3fb6739a81a62025e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-19T06:42:47Z","title_canon_sha256":"95e3382a7c6d27832666f28cb855e22c4900e18b4abed5721c9729c10664d69d"},"schema_version":"1.0","source":{"id":"2312.11897","kind":"arxiv","version":3}},"canonical_sha256":"9dade052d3af8bf29bb6737121f199e96c52ff2770a1aab1d5b1c659081f8fb0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9dade052d3af8bf29bb6737121f199e96c52ff2770a1aab1d5b1c659081f8fb0","first_computed_at":"2026-07-05T08:56:16.042977Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:56:16.042977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"E2Wk4FKzVwOLBGrYneBfga+UEGGTz1dXcl8SxEyrPWRaP9SHbksiQ1j9qjIITQbpQtf/BuuMS3tkgIeSx7yqBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:56:16.043329Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.11897","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9bb7937462deea41dd602c8965d33cd0919d499de25622b65563ac57d9d3d314","sha256:012fbcbf421e9704e887548033047a1b0bed9c16beb3757c6f4e9efb49f66880"],"state_sha256":"853b8181057912793b0462d59c22a230c7a0c57bb8bc7a6eca2c4c5fd2cfd8fb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dTNhiJ++kzaUa++nPspeJY8vtqTgb54LxLa3URF9jFda57CatbIS/LbAeLfM4Vae+qMejiAuoCtoHOi0y606Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T17:28:59.073782Z","bundle_sha256":"9a5a3c1d5bfef505d770eea7eef7f7a52aabe5f616e0b8747807456a079bf9ef"}}