{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:QPQYLUBIRTUWUQGZM34SZMKBRN","short_pith_number":"pith:QPQYLUBI","canonical_record":{"source":{"id":"2103.13915","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-25T15:25:17Z","cross_cats_sorted":[],"title_canon_sha256":"f0728c41a93c024dbdb9c737f1a3e16a58b08d0a0c27ddc3ef87f1a4e1353cea","abstract_canon_sha256":"270f47dfa5891e6582ef03342f3fecf843d3d693b6d2614d1465b22c8ffb27ba"},"schema_version":"1.0"},"canonical_sha256":"83e185d0288ce96a40d966f92cb1418b5bdc593a303d3068f47d0ae1cb6c5b4f","source":{"kind":"arxiv","id":"2103.13915","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.13915","created_at":"2026-07-05T02:43:54Z"},{"alias_kind":"arxiv_version","alias_value":"2103.13915v2","created_at":"2026-07-05T02:43:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.13915","created_at":"2026-07-05T02:43:54Z"},{"alias_kind":"pith_short_12","alias_value":"QPQYLUBIRTUW","created_at":"2026-07-05T02:43:54Z"},{"alias_kind":"pith_short_16","alias_value":"QPQYLUBIRTUWUQGZ","created_at":"2026-07-05T02:43:54Z"},{"alias_kind":"pith_short_8","alias_value":"QPQYLUBI","created_at":"2026-07-05T02:43:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:QPQYLUBIRTUWUQGZM34SZMKBRN","target":"record","payload":{"canonical_record":{"source":{"id":"2103.13915","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-25T15:25:17Z","cross_cats_sorted":[],"title_canon_sha256":"f0728c41a93c024dbdb9c737f1a3e16a58b08d0a0c27ddc3ef87f1a4e1353cea","abstract_canon_sha256":"270f47dfa5891e6582ef03342f3fecf843d3d693b6d2614d1465b22c8ffb27ba"},"schema_version":"1.0"},"canonical_sha256":"83e185d0288ce96a40d966f92cb1418b5bdc593a303d3068f47d0ae1cb6c5b4f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:43:54.351889Z","signature_b64":"U+S3xo5nBjtVajstK72O1J6g/pyQRxudojt8mk8HYQL6+q3xwgqr7O0kTiuU+KLtDxy3/3M2VoUgIXnIXP0EBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83e185d0288ce96a40d966f92cb1418b5bdc593a303d3068f47d0ae1cb6c5b4f","last_reissued_at":"2026-07-05T02:43:54.351342Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:43:54.351342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.13915","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":"2026-07-05T02:43:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tH6+Q+oo4G9SHgnu4XooKBhpYtj3MPXKaVPyRNAF0lVoNP3rGOpiR62KSiwrQdyvF2X2Qa0WnUmr/r+68bcQDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T21:12:34.234444Z"},"content_sha256":"e05133b524aa6be34b6a5c373120ab1efeab4fa7dd1487e18d6b3b98dea10f49","schema_version":"1.0","event_id":"sha256:e05133b524aa6be34b6a5c373120ab1efeab4fa7dd1487e18d6b3b98dea10f49"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:QPQYLUBIRTUWUQGZM34SZMKBRN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Image is Worth 16x16 Words, What is a Video Worth?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Asaf Noy, Gilad Sharir, Lihi Zelnik-Manor","submitted_at":"2021-03-25T15:25:17Z","abstract_excerpt":"Leading methods in the domain of action recognition try to distill information from both the spatial and temporal dimensions of an input video. Methods that reach State of the Art (SotA) accuracy, usually make use of 3D convolution layers as a way to abstract the temporal information from video frames. The use of such convolutions requires sampling short clips from the input video, where each clip is a collection of closely sampled frames. Since each short clip covers a small fraction of an input video, multiple clips are sampled at inference in order to cover the whole temporal length of the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.13915","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/2103.13915/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":"2026-07-05T02:43:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PnKMDldxFvLd3qazzpJsMO6Tj19WN4MnPCDAdqjyEVNl30wXneZNecEez87iRSBvO/MdUSYXj3LDeLVfoMkuCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T21:12:34.234958Z"},"content_sha256":"f3ce930f813a80db1e6188aaed5bef4b367423e3d0e32464d7bb712d0ccb8420","schema_version":"1.0","event_id":"sha256:f3ce930f813a80db1e6188aaed5bef4b367423e3d0e32464d7bb712d0ccb8420"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QPQYLUBIRTUWUQGZM34SZMKBRN/bundle.json","state_url":"https://pith.science/pith/QPQYLUBIRTUWUQGZM34SZMKBRN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QPQYLUBIRTUWUQGZM34SZMKBRN/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":"2026-08-16T21:12:34Z","links":{"resolver":"https://pith.science/pith/QPQYLUBIRTUWUQGZM34SZMKBRN","bundle":"https://pith.science/pith/QPQYLUBIRTUWUQGZM34SZMKBRN/bundle.json","state":"https://pith.science/pith/QPQYLUBIRTUWUQGZM34SZMKBRN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QPQYLUBIRTUWUQGZM34SZMKBRN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:QPQYLUBIRTUWUQGZM34SZMKBRN","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":"270f47dfa5891e6582ef03342f3fecf843d3d693b6d2614d1465b22c8ffb27ba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-25T15:25:17Z","title_canon_sha256":"f0728c41a93c024dbdb9c737f1a3e16a58b08d0a0c27ddc3ef87f1a4e1353cea"},"schema_version":"1.0","source":{"id":"2103.13915","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.13915","created_at":"2026-07-05T02:43:54Z"},{"alias_kind":"arxiv_version","alias_value":"2103.13915v2","created_at":"2026-07-05T02:43:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.13915","created_at":"2026-07-05T02:43:54Z"},{"alias_kind":"pith_short_12","alias_value":"QPQYLUBIRTUW","created_at":"2026-07-05T02:43:54Z"},{"alias_kind":"pith_short_16","alias_value":"QPQYLUBIRTUWUQGZ","created_at":"2026-07-05T02:43:54Z"},{"alias_kind":"pith_short_8","alias_value":"QPQYLUBI","created_at":"2026-07-05T02:43:54Z"}],"graph_snapshots":[{"event_id":"sha256:f3ce930f813a80db1e6188aaed5bef4b367423e3d0e32464d7bb712d0ccb8420","target":"graph","created_at":"2026-07-05T02:43:54Z","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/2103.13915/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Leading methods in the domain of action recognition try to distill information from both the spatial and temporal dimensions of an input video. Methods that reach State of the Art (SotA) accuracy, usually make use of 3D convolution layers as a way to abstract the temporal information from video frames. The use of such convolutions requires sampling short clips from the input video, where each clip is a collection of closely sampled frames. Since each short clip covers a small fraction of an input video, multiple clips are sampled at inference in order to cover the whole temporal length of the ","authors_text":"Asaf Noy, Gilad Sharir, Lihi Zelnik-Manor","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-25T15:25:17Z","title":"An Image is Worth 16x16 Words, What is a Video Worth?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.13915","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:e05133b524aa6be34b6a5c373120ab1efeab4fa7dd1487e18d6b3b98dea10f49","target":"record","created_at":"2026-07-05T02:43:54Z","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":"270f47dfa5891e6582ef03342f3fecf843d3d693b6d2614d1465b22c8ffb27ba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-25T15:25:17Z","title_canon_sha256":"f0728c41a93c024dbdb9c737f1a3e16a58b08d0a0c27ddc3ef87f1a4e1353cea"},"schema_version":"1.0","source":{"id":"2103.13915","kind":"arxiv","version":2}},"canonical_sha256":"83e185d0288ce96a40d966f92cb1418b5bdc593a303d3068f47d0ae1cb6c5b4f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83e185d0288ce96a40d966f92cb1418b5bdc593a303d3068f47d0ae1cb6c5b4f","first_computed_at":"2026-07-05T02:43:54.351342Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:43:54.351342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U+S3xo5nBjtVajstK72O1J6g/pyQRxudojt8mk8HYQL6+q3xwgqr7O0kTiuU+KLtDxy3/3M2VoUgIXnIXP0EBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:43:54.351889Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.13915","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e05133b524aa6be34b6a5c373120ab1efeab4fa7dd1487e18d6b3b98dea10f49","sha256:f3ce930f813a80db1e6188aaed5bef4b367423e3d0e32464d7bb712d0ccb8420"],"state_sha256":"54c25e6f83b824c8c345da1faae64f26c86141658aab12495df446856d257a3d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wkAgbwR4N3OPTUq+gVTfwjXurTjgCRaH/yej4XOUO5LoR86HrHokyjRcqvMErgW14NgsQwXf5ffmrMFQi9X2CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T21:12:34.238734Z","bundle_sha256":"c48351e1ad55d8eada5a18ea3d0981db0ba82f86b574d0df7c82850a9b364231"}}