{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:7AOC2LOTXAHNLTOBB4JC4VOM43","short_pith_number":"pith:7AOC2LOT","canonical_record":{"source":{"id":"2312.07395","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-12T16:10:19Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"426faf8a2ca3fe6804cb675a1e9213360f161167aab8f6111900dfa10a25d355","abstract_canon_sha256":"4ad2bf4a6d515d5dd2fa7959776446def580639ea9857c2f52e02a262289b93b"},"schema_version":"1.0"},"canonical_sha256":"f81c2d2dd3b80ed5cdc10f122e55cce6cf7f6c5ff054d63aeb8a2c50b78e4532","source":{"kind":"arxiv","id":"2312.07395","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.07395","created_at":"2026-07-05T09:55:07Z"},{"alias_kind":"arxiv_version","alias_value":"2312.07395v2","created_at":"2026-07-05T09:55:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.07395","created_at":"2026-07-05T09:55:07Z"},{"alias_kind":"pith_short_12","alias_value":"7AOC2LOTXAHN","created_at":"2026-07-05T09:55:07Z"},{"alias_kind":"pith_short_16","alias_value":"7AOC2LOTXAHNLTOB","created_at":"2026-07-05T09:55:07Z"},{"alias_kind":"pith_short_8","alias_value":"7AOC2LOT","created_at":"2026-07-05T09:55:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:7AOC2LOTXAHNLTOBB4JC4VOM43","target":"record","payload":{"canonical_record":{"source":{"id":"2312.07395","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-12T16:10:19Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"426faf8a2ca3fe6804cb675a1e9213360f161167aab8f6111900dfa10a25d355","abstract_canon_sha256":"4ad2bf4a6d515d5dd2fa7959776446def580639ea9857c2f52e02a262289b93b"},"schema_version":"1.0"},"canonical_sha256":"f81c2d2dd3b80ed5cdc10f122e55cce6cf7f6c5ff054d63aeb8a2c50b78e4532","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:07.498811Z","signature_b64":"GH8rdWNuG0aYV8ccadXHi8YdTOL7xIupwrC/XBCaaWK22Da0wZzY6Tvm5hULCoUfSyUVR0KTx57gzWRikZ9JAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f81c2d2dd3b80ed5cdc10f122e55cce6cf7f6c5ff054d63aeb8a2c50b78e4532","last_reissued_at":"2026-07-05T09:55:07.498233Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:07.498233Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.07395","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":"2026-07-05T09:55:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iAiDEyzjeVN0oyr+voxvO3Wj4KoPfoEu+OAMf5uWXQgacJGB6o9kKX1WmU210/nqHiPUkke/2COrcgikb5Z9AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-20T09:12:53.274765Z"},"content_sha256":"d5520af0ff21fa30f9d05865379284c31e438ff1a6b7f81007341f1d6ce39d4c","schema_version":"1.0","event_id":"sha256:d5520af0ff21fa30f9d05865379284c31e438ff1a6b7f81007341f1d6ce39d4c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:7AOC2LOTXAHNLTOBB4JC4VOM43","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Simple Recipe for Contrastively Pre-training Video-First Encoders Beyond 16 Frames","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Aida Nematzadeh, Andrew Zisserman, Antoine Miech, Jiajun Shen, Joe Heyward, Justin Chiu, Pinelopi Papalampidi, Shreya Pathak, Skanda Koppula, Viorica Patraucean","submitted_at":"2023-12-12T16:10:19Z","abstract_excerpt":"Understanding long, real-world videos requires modeling of long-range visual dependencies. To this end, we explore video-first architectures, building on the common paradigm of transferring large-scale, image--text models to video via shallow temporal fusion. However, we expose two limitations to the approach: (1) decreased spatial capabilities, likely due to poor video--language alignment in standard video datasets, and (2) higher memory consumption, bottlenecking the number of frames that can be processed. To mitigate the memory bottleneck, we systematically analyze the memory/accuracy trade"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.07395","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/2312.07395/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":"2026-07-05T09:55:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5OXCd5+zKFx8PtVExkZRf/X22fb96d9NBvXVUZoxsDvlug/Am7lrvmgqeJA6csd82G1Hrlubz17isdtL3SVCCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-20T09:12:53.275128Z"},"content_sha256":"e0eef41829d24603a7b8a689ece63e1af8c02115fd21fc8b2241e5173bbbe5f1","schema_version":"1.0","event_id":"sha256:e0eef41829d24603a7b8a689ece63e1af8c02115fd21fc8b2241e5173bbbe5f1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7AOC2LOTXAHNLTOBB4JC4VOM43/bundle.json","state_url":"https://pith.science/pith/7AOC2LOTXAHNLTOBB4JC4VOM43/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7AOC2LOTXAHNLTOBB4JC4VOM43/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":"2026-07-20T09:12:53Z","links":{"resolver":"https://pith.science/pith/7AOC2LOTXAHNLTOBB4JC4VOM43","bundle":"https://pith.science/pith/7AOC2LOTXAHNLTOBB4JC4VOM43/bundle.json","state":"https://pith.science/pith/7AOC2LOTXAHNLTOBB4JC4VOM43/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7AOC2LOTXAHNLTOBB4JC4VOM43/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7AOC2LOTXAHNLTOBB4JC4VOM43","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":"4ad2bf4a6d515d5dd2fa7959776446def580639ea9857c2f52e02a262289b93b","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-12T16:10:19Z","title_canon_sha256":"426faf8a2ca3fe6804cb675a1e9213360f161167aab8f6111900dfa10a25d355"},"schema_version":"1.0","source":{"id":"2312.07395","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.07395","created_at":"2026-07-05T09:55:07Z"},{"alias_kind":"arxiv_version","alias_value":"2312.07395v2","created_at":"2026-07-05T09:55:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.07395","created_at":"2026-07-05T09:55:07Z"},{"alias_kind":"pith_short_12","alias_value":"7AOC2LOTXAHN","created_at":"2026-07-05T09:55:07Z"},{"alias_kind":"pith_short_16","alias_value":"7AOC2LOTXAHNLTOB","created_at":"2026-07-05T09:55:07Z"},{"alias_kind":"pith_short_8","alias_value":"7AOC2LOT","created_at":"2026-07-05T09:55:07Z"}],"graph_snapshots":[{"event_id":"sha256:e0eef41829d24603a7b8a689ece63e1af8c02115fd21fc8b2241e5173bbbe5f1","target":"graph","created_at":"2026-07-05T09:55:07Z","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/2312.07395/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding long, real-world videos requires modeling of long-range visual dependencies. To this end, we explore video-first architectures, building on the common paradigm of transferring large-scale, image--text models to video via shallow temporal fusion. However, we expose two limitations to the approach: (1) decreased spatial capabilities, likely due to poor video--language alignment in standard video datasets, and (2) higher memory consumption, bottlenecking the number of frames that can be processed. To mitigate the memory bottleneck, we systematically analyze the memory/accuracy trade","authors_text":"Aida Nematzadeh, Andrew Zisserman, Antoine Miech, Jiajun Shen, Joe Heyward, Justin Chiu, Pinelopi Papalampidi, Shreya Pathak, Skanda Koppula, Viorica Patraucean","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-12T16:10:19Z","title":"A Simple Recipe for Contrastively Pre-training Video-First Encoders Beyond 16 Frames"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.07395","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:d5520af0ff21fa30f9d05865379284c31e438ff1a6b7f81007341f1d6ce39d4c","target":"record","created_at":"2026-07-05T09:55:07Z","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":"4ad2bf4a6d515d5dd2fa7959776446def580639ea9857c2f52e02a262289b93b","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-12T16:10:19Z","title_canon_sha256":"426faf8a2ca3fe6804cb675a1e9213360f161167aab8f6111900dfa10a25d355"},"schema_version":"1.0","source":{"id":"2312.07395","kind":"arxiv","version":2}},"canonical_sha256":"f81c2d2dd3b80ed5cdc10f122e55cce6cf7f6c5ff054d63aeb8a2c50b78e4532","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f81c2d2dd3b80ed5cdc10f122e55cce6cf7f6c5ff054d63aeb8a2c50b78e4532","first_computed_at":"2026-07-05T09:55:07.498233Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:55:07.498233Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GH8rdWNuG0aYV8ccadXHi8YdTOL7xIupwrC/XBCaaWK22Da0wZzY6Tvm5hULCoUfSyUVR0KTx57gzWRikZ9JAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:55:07.498811Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.07395","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d5520af0ff21fa30f9d05865379284c31e438ff1a6b7f81007341f1d6ce39d4c","sha256:e0eef41829d24603a7b8a689ece63e1af8c02115fd21fc8b2241e5173bbbe5f1"],"state_sha256":"0be87b9263633f0b2f3c7d44fed3b058af634d4af29b827ace2c194e2be8797a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rapLVgW4ig2QhOO/RpIFzx4xdSh/yGSogMFaCVIFCCRMrMxd0WeCcYyJFn+1Cg93z98i2NF2h9a/fm6C8ov7Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-20T09:12:53.277277Z","bundle_sha256":"b985e71e4074d1afb4210cf5a8f21add88a3fb302a9c8f2fba227cc1dd249e55"}}