{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:RIQCBDK4SB4TNZ25GRDE72EQA2","short_pith_number":"pith:RIQCBDK4","canonical_record":{"source":{"id":"2208.01753","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-08-02T21:03:48Z","cross_cats_sorted":["cs.LG","cs.MM"],"title_canon_sha256":"e70c861aab85812169a21b2290352fec8500c0e7918a52127a0993926be3f602","abstract_canon_sha256":"93a8400759f67097d17eb19a39a26d5d95811964e395125a636c7dd2df5298c5"},"schema_version":"1.0"},"canonical_sha256":"8a20208d5c907936e75d34464fe890069728c1b827683fffedc5f57ffdf77617","source":{"kind":"arxiv","id":"2208.01753","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.01753","created_at":"2026-07-05T04:45:39Z"},{"alias_kind":"arxiv_version","alias_value":"2208.01753v1","created_at":"2026-07-05T04:45:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.01753","created_at":"2026-07-05T04:45:39Z"},{"alias_kind":"pith_short_12","alias_value":"RIQCBDK4SB4T","created_at":"2026-07-05T04:45:39Z"},{"alias_kind":"pith_short_16","alias_value":"RIQCBDK4SB4TNZ25","created_at":"2026-07-05T04:45:39Z"},{"alias_kind":"pith_short_8","alias_value":"RIQCBDK4","created_at":"2026-07-05T04:45:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:RIQCBDK4SB4TNZ25GRDE72EQA2","target":"record","payload":{"canonical_record":{"source":{"id":"2208.01753","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-08-02T21:03:48Z","cross_cats_sorted":["cs.LG","cs.MM"],"title_canon_sha256":"e70c861aab85812169a21b2290352fec8500c0e7918a52127a0993926be3f602","abstract_canon_sha256":"93a8400759f67097d17eb19a39a26d5d95811964e395125a636c7dd2df5298c5"},"schema_version":"1.0"},"canonical_sha256":"8a20208d5c907936e75d34464fe890069728c1b827683fffedc5f57ffdf77617","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:45:39.918337Z","signature_b64":"Afg9i72CLBiOgU03w0xIiAWTPahvWoUixPaY3Y1wcJMOnGLIeoRkJoQxy5FBAzNMZkkLdJRqUOaC4lQQ6CDtAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a20208d5c907936e75d34464fe890069728c1b827683fffedc5f57ffdf77617","last_reissued_at":"2026-07-05T04:45:39.917985Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:45:39.917985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2208.01753","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:45:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yERFGxW0QFfIkxMnEZFu76XheYMQ7HLx9xlcJljYpDbp+BJk/GV7s3GysuidvlcFwCq3m34R/sIEdhxXEK2tBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T01:14:03.604088Z"},"content_sha256":"0d6493fc2fa3ca4a7cf2bc608f3c29e0de63dd5fc9eb9971c404db75dd28a5b3","schema_version":"1.0","event_id":"sha256:0d6493fc2fa3ca4a7cf2bc608f3c29e0de63dd5fc9eb9971c404db75dd28a5b3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:RIQCBDK4SB4TNZ25GRDE72EQA2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Two-Stream Transformer Architecture for Long Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Andrew Gilbert, Edward Fish, Jon Weinbren","submitted_at":"2022-08-02T21:03:48Z","abstract_excerpt":"Pure vision transformer architectures are highly effective for short video classification and action recognition tasks. However, due to the quadratic complexity of self attention and lack of inductive bias, transformers are resource intensive and suffer from data inefficiencies. Long form video understanding tasks amplify data and memory efficiency problems in transformers making current approaches unfeasible to implement on data or memory restricted domains. This paper introduces an efficient Spatio-Temporal Attention Network (STAN) which uses a two-stream transformer architecture to model de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.01753","kind":"arxiv","version":1},"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/2208.01753/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":"2026-07-05T04:45:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EqZatVZPqdhQJsrE6jw0Mm3Q+pN+J4c4UZlugDm++0fguBBcjmKFAnBrcdAGXKxA9noe6UFqlO7Kw7xMl1IsDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T01:14:03.611261Z"},"content_sha256":"afeb72b1734db687cf16ee9b67e4fc42c23fe2264a663ae922c624a6e310f5ef","schema_version":"1.0","event_id":"sha256:afeb72b1734db687cf16ee9b67e4fc42c23fe2264a663ae922c624a6e310f5ef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RIQCBDK4SB4TNZ25GRDE72EQA2/bundle.json","state_url":"https://pith.science/pith/RIQCBDK4SB4TNZ25GRDE72EQA2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RIQCBDK4SB4TNZ25GRDE72EQA2/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":"2026-08-15T01:14:03Z","links":{"resolver":"https://pith.science/pith/RIQCBDK4SB4TNZ25GRDE72EQA2","bundle":"https://pith.science/pith/RIQCBDK4SB4TNZ25GRDE72EQA2/bundle.json","state":"https://pith.science/pith/RIQCBDK4SB4TNZ25GRDE72EQA2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RIQCBDK4SB4TNZ25GRDE72EQA2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:RIQCBDK4SB4TNZ25GRDE72EQA2","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":"93a8400759f67097d17eb19a39a26d5d95811964e395125a636c7dd2df5298c5","cross_cats_sorted":["cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-08-02T21:03:48Z","title_canon_sha256":"e70c861aab85812169a21b2290352fec8500c0e7918a52127a0993926be3f602"},"schema_version":"1.0","source":{"id":"2208.01753","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.01753","created_at":"2026-07-05T04:45:39Z"},{"alias_kind":"arxiv_version","alias_value":"2208.01753v1","created_at":"2026-07-05T04:45:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.01753","created_at":"2026-07-05T04:45:39Z"},{"alias_kind":"pith_short_12","alias_value":"RIQCBDK4SB4T","created_at":"2026-07-05T04:45:39Z"},{"alias_kind":"pith_short_16","alias_value":"RIQCBDK4SB4TNZ25","created_at":"2026-07-05T04:45:39Z"},{"alias_kind":"pith_short_8","alias_value":"RIQCBDK4","created_at":"2026-07-05T04:45:39Z"}],"graph_snapshots":[{"event_id":"sha256:afeb72b1734db687cf16ee9b67e4fc42c23fe2264a663ae922c624a6e310f5ef","target":"graph","created_at":"2026-07-05T04:45:39Z","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/2208.01753/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pure vision transformer architectures are highly effective for short video classification and action recognition tasks. However, due to the quadratic complexity of self attention and lack of inductive bias, transformers are resource intensive and suffer from data inefficiencies. Long form video understanding tasks amplify data and memory efficiency problems in transformers making current approaches unfeasible to implement on data or memory restricted domains. This paper introduces an efficient Spatio-Temporal Attention Network (STAN) which uses a two-stream transformer architecture to model de","authors_text":"Andrew Gilbert, Edward Fish, Jon Weinbren","cross_cats":["cs.LG","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-08-02T21:03:48Z","title":"Two-Stream Transformer Architecture for Long Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.01753","kind":"arxiv","version":1},"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":"sha256:0d6493fc2fa3ca4a7cf2bc608f3c29e0de63dd5fc9eb9971c404db75dd28a5b3","target":"record","created_at":"2026-07-05T04:45:39Z","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":"93a8400759f67097d17eb19a39a26d5d95811964e395125a636c7dd2df5298c5","cross_cats_sorted":["cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-08-02T21:03:48Z","title_canon_sha256":"e70c861aab85812169a21b2290352fec8500c0e7918a52127a0993926be3f602"},"schema_version":"1.0","source":{"id":"2208.01753","kind":"arxiv","version":1}},"canonical_sha256":"8a20208d5c907936e75d34464fe890069728c1b827683fffedc5f57ffdf77617","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a20208d5c907936e75d34464fe890069728c1b827683fffedc5f57ffdf77617","first_computed_at":"2026-07-05T04:45:39.917985Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:45:39.917985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Afg9i72CLBiOgU03w0xIiAWTPahvWoUixPaY3Y1wcJMOnGLIeoRkJoQxy5FBAzNMZkkLdJRqUOaC4lQQ6CDtAA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:45:39.918337Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.01753","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0d6493fc2fa3ca4a7cf2bc608f3c29e0de63dd5fc9eb9971c404db75dd28a5b3","sha256:afeb72b1734db687cf16ee9b67e4fc42c23fe2264a663ae922c624a6e310f5ef"],"state_sha256":"723d749c0a3a6980957855133af2b949a3c022323f515ab471e91ecc9514b619"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4QujMwkRl74wXN172EQ/De370loe5zBq4xWtMGxsv3GehiVrgv3F+yfn/D2yWPbDWyTJfvAyBlPyTxi4eqpRCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T01:14:03.618202Z","bundle_sha256":"401628e37bc25c1286e526426b08e678f5488a6bb718c0b7f480ba987d9a87e3"}}