{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:7FRTENPCVZEPTQT44S62JPIPFF","short_pith_number":"pith:7FRTENPC","canonical_record":{"source":{"id":"1708.07335","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2017-08-24T09:40:29Z","cross_cats_sorted":[],"title_canon_sha256":"d87ece9b481506c8e71dfb115d4721c775bc915f75d978d34934058afa5525e0","abstract_canon_sha256":"16aea1efcf8b8ea9bb39e5821645c47d2c3fb71c5cef510d881264dcf8aeeb7e"},"schema_version":"1.0"},"canonical_sha256":"f9633235e2ae48f9c27ce4bda4bd0f294f733a6feb6bea25f6e251be56c1ac1c","source":{"kind":"arxiv","id":"1708.07335","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.07335","created_at":"2026-05-18T00:36:46Z"},{"alias_kind":"arxiv_version","alias_value":"1708.07335v1","created_at":"2026-05-18T00:36:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.07335","created_at":"2026-05-18T00:36:46Z"},{"alias_kind":"pith_short_12","alias_value":"7FRTENPCVZEP","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"7FRTENPCVZEPTQT4","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"7FRTENPC","created_at":"2026-05-18T12:31:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:7FRTENPCVZEPTQT44S62JPIPFF","target":"record","payload":{"canonical_record":{"source":{"id":"1708.07335","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2017-08-24T09:40:29Z","cross_cats_sorted":[],"title_canon_sha256":"d87ece9b481506c8e71dfb115d4721c775bc915f75d978d34934058afa5525e0","abstract_canon_sha256":"16aea1efcf8b8ea9bb39e5821645c47d2c3fb71c5cef510d881264dcf8aeeb7e"},"schema_version":"1.0"},"canonical_sha256":"f9633235e2ae48f9c27ce4bda4bd0f294f733a6feb6bea25f6e251be56c1ac1c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:36:46.529226Z","signature_b64":"YWeV0Q3JUHy5pwHBlQtR0HhIQHE3GO4OhDfHoK+e7DYRteMq2DRb9McrA5Rwt5UmRTy6rdMT7iM3EMf7V9eYAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9633235e2ae48f9c27ce4bda4bd0f294f733a6feb6bea25f6e251be56c1ac1c","last_reissued_at":"2026-05-18T00:36:46.528597Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:36:46.528597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1708.07335","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":"2026-05-18T00:36:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mku4a1QJCfrRd0uUjmoAe7LP81XS3EoE61E9BMLxLtgQjniKlysyQbGgeZ8dw7Vzpl4tBhYs5cS1H9q+Pr+wAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T07:26:05.065707Z"},"content_sha256":"ded1b794b68dc89d5d56164c1aa83d451894dd0967282900d3fb6576a674dd00","schema_version":"1.0","event_id":"sha256:ded1b794b68dc89d5d56164c1aa83d451894dd0967282900d3fb6576a674dd00"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:7FRTENPCVZEPTQT44S62JPIPFF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Relaxed Spatio-Temporal Deep Feature Aggregation for Real-Fake Expression Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gozde Bozdagi Akar, Savas Ozkan","submitted_at":"2017-08-24T09:40:29Z","abstract_excerpt":"Frame-level visual features are generally aggregated in time with the techniques such as LSTM, Fisher Vectors, NetVLAD etc. to produce a robust video-level representation. We here introduce a learnable aggregation technique whose primary objective is to retain short-time temporal structure between frame-level features and their spatial interdependencies in the representation. Also, it can be easily adapted to the cases where there have very scarce training samples. We evaluate the method on a real-fake expression prediction dataset to demonstrate its superiority. Our method obtains 65% score o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.07335","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":""},"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":"2026-05-18T00:36:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G+86L3Q1X7aH+z5Ej7fgOq10uzdmlRF+aKhynrCaMdR5SHYzYIKwJTUlAZdaw++HkeaYGIwf1WLqsJhj7bsTDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T07:26:05.066055Z"},"content_sha256":"b34b161c4b72ab148c0f29634ce70325933b8deac4c23e1eac5e419918afcfc4","schema_version":"1.0","event_id":"sha256:b34b161c4b72ab148c0f29634ce70325933b8deac4c23e1eac5e419918afcfc4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7FRTENPCVZEPTQT44S62JPIPFF/bundle.json","state_url":"https://pith.science/pith/7FRTENPCVZEPTQT44S62JPIPFF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7FRTENPCVZEPTQT44S62JPIPFF/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":"2026-06-03T07:26:05Z","links":{"resolver":"https://pith.science/pith/7FRTENPCVZEPTQT44S62JPIPFF","bundle":"https://pith.science/pith/7FRTENPCVZEPTQT44S62JPIPFF/bundle.json","state":"https://pith.science/pith/7FRTENPCVZEPTQT44S62JPIPFF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7FRTENPCVZEPTQT44S62JPIPFF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:7FRTENPCVZEPTQT44S62JPIPFF","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":"16aea1efcf8b8ea9bb39e5821645c47d2c3fb71c5cef510d881264dcf8aeeb7e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2017-08-24T09:40:29Z","title_canon_sha256":"d87ece9b481506c8e71dfb115d4721c775bc915f75d978d34934058afa5525e0"},"schema_version":"1.0","source":{"id":"1708.07335","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.07335","created_at":"2026-05-18T00:36:46Z"},{"alias_kind":"arxiv_version","alias_value":"1708.07335v1","created_at":"2026-05-18T00:36:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.07335","created_at":"2026-05-18T00:36:46Z"},{"alias_kind":"pith_short_12","alias_value":"7FRTENPCVZEP","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"7FRTENPCVZEPTQT4","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"7FRTENPC","created_at":"2026-05-18T12:31:05Z"}],"graph_snapshots":[{"event_id":"sha256:b34b161c4b72ab148c0f29634ce70325933b8deac4c23e1eac5e419918afcfc4","target":"graph","created_at":"2026-05-18T00:36:46Z","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"},"paper":{"abstract_excerpt":"Frame-level visual features are generally aggregated in time with the techniques such as LSTM, Fisher Vectors, NetVLAD etc. to produce a robust video-level representation. We here introduce a learnable aggregation technique whose primary objective is to retain short-time temporal structure between frame-level features and their spatial interdependencies in the representation. Also, it can be easily adapted to the cases where there have very scarce training samples. We evaluate the method on a real-fake expression prediction dataset to demonstrate its superiority. Our method obtains 65% score o","authors_text":"Gozde Bozdagi Akar, Savas Ozkan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2017-08-24T09:40:29Z","title":"Relaxed Spatio-Temporal Deep Feature Aggregation for Real-Fake Expression Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.07335","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:ded1b794b68dc89d5d56164c1aa83d451894dd0967282900d3fb6576a674dd00","target":"record","created_at":"2026-05-18T00:36:46Z","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":"16aea1efcf8b8ea9bb39e5821645c47d2c3fb71c5cef510d881264dcf8aeeb7e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2017-08-24T09:40:29Z","title_canon_sha256":"d87ece9b481506c8e71dfb115d4721c775bc915f75d978d34934058afa5525e0"},"schema_version":"1.0","source":{"id":"1708.07335","kind":"arxiv","version":1}},"canonical_sha256":"f9633235e2ae48f9c27ce4bda4bd0f294f733a6feb6bea25f6e251be56c1ac1c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f9633235e2ae48f9c27ce4bda4bd0f294f733a6feb6bea25f6e251be56c1ac1c","first_computed_at":"2026-05-18T00:36:46.528597Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:36:46.528597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YWeV0Q3JUHy5pwHBlQtR0HhIQHE3GO4OhDfHoK+e7DYRteMq2DRb9McrA5Rwt5UmRTy6rdMT7iM3EMf7V9eYAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:36:46.529226Z","signed_message":"canonical_sha256_bytes"},"source_id":"1708.07335","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ded1b794b68dc89d5d56164c1aa83d451894dd0967282900d3fb6576a674dd00","sha256:b34b161c4b72ab148c0f29634ce70325933b8deac4c23e1eac5e419918afcfc4"],"state_sha256":"987c6359b5473311c9cd23f3e920e0a1a6cc8dfd6d0cd0c01845221e7fd7a53c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ANZX4ggZ2MM/hCVeDlmB3QksCjdMylfSgckpjOsDeO4EX1FNKdqIA9pmqcd3HV3QLiRRMFwe4pEy/dpENvrRCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T07:26:05.068016Z","bundle_sha256":"e7593b6ba504325fee95b2a486438ee624a4e926df76b197f2d9fbada692c897"}}