{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:GAXHF5ZCGIWHVJWOFSXEZM7FSF","short_pith_number":"pith:GAXHF5ZC","canonical_record":{"source":{"id":"1702.02549","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-08T18:19:05Z","cross_cats_sorted":[],"title_canon_sha256":"11b7adaaf05bc9308bc21b2c372e3186d39f2fc0cce4a810b0c05ecd21b9d25c","abstract_canon_sha256":"a9e3896397d6cd0780c99c2514f0995ab2716422c8fc42a68e940582ec693b9a"},"schema_version":"1.0"},"canonical_sha256":"302e72f722322c7aa6ce2cae4cb3e591623f3f7619973225e40cbb2d1557db13","source":{"kind":"arxiv","id":"1702.02549","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.02549","created_at":"2026-05-18T00:51:05Z"},{"alias_kind":"arxiv_version","alias_value":"1702.02549v1","created_at":"2026-05-18T00:51:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.02549","created_at":"2026-05-18T00:51:05Z"},{"alias_kind":"pith_short_12","alias_value":"GAXHF5ZCGIWH","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"GAXHF5ZCGIWHVJWO","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"GAXHF5ZC","created_at":"2026-05-18T12:31:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:GAXHF5ZCGIWHVJWOFSXEZM7FSF","target":"record","payload":{"canonical_record":{"source":{"id":"1702.02549","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-08T18:19:05Z","cross_cats_sorted":[],"title_canon_sha256":"11b7adaaf05bc9308bc21b2c372e3186d39f2fc0cce4a810b0c05ecd21b9d25c","abstract_canon_sha256":"a9e3896397d6cd0780c99c2514f0995ab2716422c8fc42a68e940582ec693b9a"},"schema_version":"1.0"},"canonical_sha256":"302e72f722322c7aa6ce2cae4cb3e591623f3f7619973225e40cbb2d1557db13","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:51:05.749209Z","signature_b64":"iCtAToHwbRbnQDcDEs2UWTxNJ73E6Ruo79GP9VLZUPyNuhONIn53BQqTHZysH2kZdupvc4raBAcLq9FCje1qCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"302e72f722322c7aa6ce2cae4cb3e591623f3f7619973225e40cbb2d1557db13","last_reissued_at":"2026-05-18T00:51:05.748844Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:51:05.748844Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1702.02549","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":"2026-05-18T00:51:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VbwOkIOBzj2Vuhud8WkbfGo5liQG6ZqLOtE9VYRn1xQ+5oMA6sK9XlcF274VxeBqolj6LtFpM+Zb5rrL0n2oAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T09:38:40.278180Z"},"content_sha256":"52055978bf866b223d0c96b9de38e024335db86c80f458d626c472ae9f73272f","schema_version":"1.0","event_id":"sha256:52055978bf866b223d0c96b9de38e024335db86c80f458d626c472ae9f73272f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:GAXHF5ZCGIWHVJWOFSXEZM7FSF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Backpropagation Training for Fisher Vectors within Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fabian Groh, Hendrik P.A. Lensch, Patrick Wieschollek","submitted_at":"2017-02-08T18:19:05Z","abstract_excerpt":"Fisher-Vectors (FV) encode higher-order statistics of a set of multiple local descriptors like SIFT features. They already show good performance in combination with shallow learning architectures on visual recognitions tasks. Current methods using FV as a feature descriptor in deep architectures assume that all original input features are static. We propose a framework to jointly learn the representation of original features, FV parameters and parameters of the classifier in the style of traditional neural networks. Our proof of concept implementation improves the performance of FV on the Pasc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.02549","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":"2026-05-18T00:51:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fogI+P2n5Tp5jkCGULL9+6Xq6FPZxS/PMTz5YTM1AM7SG571l4s873eUArWTCRdbuOegOkINWX1pXFfBnUY6Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T09:38:40.278537Z"},"content_sha256":"d068cff9d44584c9545b3a2eadcd547eda33e97086158e2d44478475791d629e","schema_version":"1.0","event_id":"sha256:d068cff9d44584c9545b3a2eadcd547eda33e97086158e2d44478475791d629e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GAXHF5ZCGIWHVJWOFSXEZM7FSF/bundle.json","state_url":"https://pith.science/pith/GAXHF5ZCGIWHVJWOFSXEZM7FSF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GAXHF5ZCGIWHVJWOFSXEZM7FSF/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":"2026-06-03T09:38:40Z","links":{"resolver":"https://pith.science/pith/GAXHF5ZCGIWHVJWOFSXEZM7FSF","bundle":"https://pith.science/pith/GAXHF5ZCGIWHVJWOFSXEZM7FSF/bundle.json","state":"https://pith.science/pith/GAXHF5ZCGIWHVJWOFSXEZM7FSF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GAXHF5ZCGIWHVJWOFSXEZM7FSF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:GAXHF5ZCGIWHVJWOFSXEZM7FSF","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":"a9e3896397d6cd0780c99c2514f0995ab2716422c8fc42a68e940582ec693b9a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-08T18:19:05Z","title_canon_sha256":"11b7adaaf05bc9308bc21b2c372e3186d39f2fc0cce4a810b0c05ecd21b9d25c"},"schema_version":"1.0","source":{"id":"1702.02549","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.02549","created_at":"2026-05-18T00:51:05Z"},{"alias_kind":"arxiv_version","alias_value":"1702.02549v1","created_at":"2026-05-18T00:51:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.02549","created_at":"2026-05-18T00:51:05Z"},{"alias_kind":"pith_short_12","alias_value":"GAXHF5ZCGIWH","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"GAXHF5ZCGIWHVJWO","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"GAXHF5ZC","created_at":"2026-05-18T12:31:15Z"}],"graph_snapshots":[{"event_id":"sha256:d068cff9d44584c9545b3a2eadcd547eda33e97086158e2d44478475791d629e","target":"graph","created_at":"2026-05-18T00:51:05Z","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":"Fisher-Vectors (FV) encode higher-order statistics of a set of multiple local descriptors like SIFT features. They already show good performance in combination with shallow learning architectures on visual recognitions tasks. Current methods using FV as a feature descriptor in deep architectures assume that all original input features are static. We propose a framework to jointly learn the representation of original features, FV parameters and parameters of the classifier in the style of traditional neural networks. Our proof of concept implementation improves the performance of FV on the Pasc","authors_text":"Fabian Groh, Hendrik P.A. Lensch, Patrick Wieschollek","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-08T18:19:05Z","title":"Backpropagation Training for Fisher Vectors within Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.02549","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":"sha256:52055978bf866b223d0c96b9de38e024335db86c80f458d626c472ae9f73272f","target":"record","created_at":"2026-05-18T00:51:05Z","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":"a9e3896397d6cd0780c99c2514f0995ab2716422c8fc42a68e940582ec693b9a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-02-08T18:19:05Z","title_canon_sha256":"11b7adaaf05bc9308bc21b2c372e3186d39f2fc0cce4a810b0c05ecd21b9d25c"},"schema_version":"1.0","source":{"id":"1702.02549","kind":"arxiv","version":1}},"canonical_sha256":"302e72f722322c7aa6ce2cae4cb3e591623f3f7619973225e40cbb2d1557db13","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"302e72f722322c7aa6ce2cae4cb3e591623f3f7619973225e40cbb2d1557db13","first_computed_at":"2026-05-18T00:51:05.748844Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:51:05.748844Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iCtAToHwbRbnQDcDEs2UWTxNJ73E6Ruo79GP9VLZUPyNuhONIn53BQqTHZysH2kZdupvc4raBAcLq9FCje1qCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:51:05.749209Z","signed_message":"canonical_sha256_bytes"},"source_id":"1702.02549","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:52055978bf866b223d0c96b9de38e024335db86c80f458d626c472ae9f73272f","sha256:d068cff9d44584c9545b3a2eadcd547eda33e97086158e2d44478475791d629e"],"state_sha256":"73869ac11803940180410a404a7bc2944ad90376755959ba9d99dc9c65fc729f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YojCP0HS8zvOO0RMEG8uXsHEld52OlpuKy5YvLKt7973seXlb/BHnh6oMYA8tufyUToUCr49vB3J81Hlhj5sCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T09:38:40.280570Z","bundle_sha256":"154b3a942366d3c9124943d415edbf16d1bdba6082d92ce61b3a5f5288e24181"}}