{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:WDPS3ZM32Y7PF3TDV2BPLVE5GH","short_pith_number":"pith:WDPS3ZM3","canonical_record":{"source":{"id":"1507.06429","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-07-23T10:01:45Z","cross_cats_sorted":[],"title_canon_sha256":"f7b1ef048774527b4828bace84a63619a1f5b12524435d6ca5fe4b0f0ee44aa0","abstract_canon_sha256":"24c841facadd2a1e8fe13394558540344abfd4b6668585a7288defad97abf194"},"schema_version":"1.0"},"canonical_sha256":"b0df2de59bd63ef2ee63ae82f5d49d31d295c11813bbf745f7d86c667dcd725b","source":{"kind":"arxiv","id":"1507.06429","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.06429","created_at":"2026-05-18T01:36:24Z"},{"alias_kind":"arxiv_version","alias_value":"1507.06429v1","created_at":"2026-05-18T01:36:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.06429","created_at":"2026-05-18T01:36:24Z"},{"alias_kind":"pith_short_12","alias_value":"WDPS3ZM32Y7P","created_at":"2026-05-18T12:29:47Z"},{"alias_kind":"pith_short_16","alias_value":"WDPS3ZM32Y7PF3TD","created_at":"2026-05-18T12:29:47Z"},{"alias_kind":"pith_short_8","alias_value":"WDPS3ZM3","created_at":"2026-05-18T12:29:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:WDPS3ZM32Y7PF3TDV2BPLVE5GH","target":"record","payload":{"canonical_record":{"source":{"id":"1507.06429","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-07-23T10:01:45Z","cross_cats_sorted":[],"title_canon_sha256":"f7b1ef048774527b4828bace84a63619a1f5b12524435d6ca5fe4b0f0ee44aa0","abstract_canon_sha256":"24c841facadd2a1e8fe13394558540344abfd4b6668585a7288defad97abf194"},"schema_version":"1.0"},"canonical_sha256":"b0df2de59bd63ef2ee63ae82f5d49d31d295c11813bbf745f7d86c667dcd725b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:36:24.985499Z","signature_b64":"Jpjcz7uximxNpvZOdUMLXYZ8O87gTcBJ/TleyxL6XpI6r1dubT1zjmjjkY4mHDPmvTQHBJotdEiDGP9aaPkkBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0df2de59bd63ef2ee63ae82f5d49d31d295c11813bbf745f7d86c667dcd725b","last_reissued_at":"2026-05-18T01:36:24.984799Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:36:24.984799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1507.06429","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":"2026-05-18T01:36:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TKR9KJ0L409AGTcakgmkYN7NHZf5wTTx+zRx99l8cB8fcPi6KAWihxnNM0lNqKiVdhpiNJlomgKb42jQ2gouBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T01:29:47.667612Z"},"content_sha256":"b5459827a5244fefa08e8f2501b28f59ab31bf3e46dc339870541fd509255154","schema_version":"1.0","event_id":"sha256:b5459827a5244fefa08e8f2501b28f59ab31bf3e46dc339870541fd509255154"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:WDPS3ZM32Y7PF3TDV2BPLVE5GH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Fishing: Gradient Features from Deep Nets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adrien Gaidon, Albert Gordo, Florent Perronnin","submitted_at":"2015-07-23T10:01:45Z","abstract_excerpt":"Convolutional Networks (ConvNets) have recently improved image recognition performance thanks to end-to-end learning of deep feed-forward models from raw pixels. Deep learning is a marked departure from the previous state of the art, the Fisher Vector (FV), which relied on gradient-based encoding of local hand-crafted features. In this paper, we discuss a novel connection between these two approaches. First, we show that one can derive gradient representations from ConvNets in a similar fashion to the FV. Second, we show that this gradient representation actually corresponds to a structured ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.06429","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":"2026-05-18T01:36:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J6mgS3NsSdKQMxuF3G8QIzc+AshYYmYEpuZzYnJKR5FYIw6yLrVcmNm9r3mp63ui2H3VxWakGxz15xhPbVuXCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T01:29:47.673057Z"},"content_sha256":"98c302fc49e7be00d0221318d5f0a91ffe5808c2478406828f4426d58774c729","schema_version":"1.0","event_id":"sha256:98c302fc49e7be00d0221318d5f0a91ffe5808c2478406828f4426d58774c729"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WDPS3ZM32Y7PF3TDV2BPLVE5GH/bundle.json","state_url":"https://pith.science/pith/WDPS3ZM32Y7PF3TDV2BPLVE5GH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WDPS3ZM32Y7PF3TDV2BPLVE5GH/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":"2026-06-04T01:29:47Z","links":{"resolver":"https://pith.science/pith/WDPS3ZM32Y7PF3TDV2BPLVE5GH","bundle":"https://pith.science/pith/WDPS3ZM32Y7PF3TDV2BPLVE5GH/bundle.json","state":"https://pith.science/pith/WDPS3ZM32Y7PF3TDV2BPLVE5GH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WDPS3ZM32Y7PF3TDV2BPLVE5GH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:WDPS3ZM32Y7PF3TDV2BPLVE5GH","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":"24c841facadd2a1e8fe13394558540344abfd4b6668585a7288defad97abf194","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-07-23T10:01:45Z","title_canon_sha256":"f7b1ef048774527b4828bace84a63619a1f5b12524435d6ca5fe4b0f0ee44aa0"},"schema_version":"1.0","source":{"id":"1507.06429","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.06429","created_at":"2026-05-18T01:36:24Z"},{"alias_kind":"arxiv_version","alias_value":"1507.06429v1","created_at":"2026-05-18T01:36:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.06429","created_at":"2026-05-18T01:36:24Z"},{"alias_kind":"pith_short_12","alias_value":"WDPS3ZM32Y7P","created_at":"2026-05-18T12:29:47Z"},{"alias_kind":"pith_short_16","alias_value":"WDPS3ZM32Y7PF3TD","created_at":"2026-05-18T12:29:47Z"},{"alias_kind":"pith_short_8","alias_value":"WDPS3ZM3","created_at":"2026-05-18T12:29:47Z"}],"graph_snapshots":[{"event_id":"sha256:98c302fc49e7be00d0221318d5f0a91ffe5808c2478406828f4426d58774c729","target":"graph","created_at":"2026-05-18T01:36:24Z","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":"Convolutional Networks (ConvNets) have recently improved image recognition performance thanks to end-to-end learning of deep feed-forward models from raw pixels. Deep learning is a marked departure from the previous state of the art, the Fisher Vector (FV), which relied on gradient-based encoding of local hand-crafted features. In this paper, we discuss a novel connection between these two approaches. First, we show that one can derive gradient representations from ConvNets in a similar fashion to the FV. Second, we show that this gradient representation actually corresponds to a structured ma","authors_text":"Adrien Gaidon, Albert Gordo, Florent Perronnin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-07-23T10:01:45Z","title":"Deep Fishing: Gradient Features from Deep Nets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.06429","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:b5459827a5244fefa08e8f2501b28f59ab31bf3e46dc339870541fd509255154","target":"record","created_at":"2026-05-18T01:36:24Z","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":"24c841facadd2a1e8fe13394558540344abfd4b6668585a7288defad97abf194","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-07-23T10:01:45Z","title_canon_sha256":"f7b1ef048774527b4828bace84a63619a1f5b12524435d6ca5fe4b0f0ee44aa0"},"schema_version":"1.0","source":{"id":"1507.06429","kind":"arxiv","version":1}},"canonical_sha256":"b0df2de59bd63ef2ee63ae82f5d49d31d295c11813bbf745f7d86c667dcd725b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b0df2de59bd63ef2ee63ae82f5d49d31d295c11813bbf745f7d86c667dcd725b","first_computed_at":"2026-05-18T01:36:24.984799Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:36:24.984799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Jpjcz7uximxNpvZOdUMLXYZ8O87gTcBJ/TleyxL6XpI6r1dubT1zjmjjkY4mHDPmvTQHBJotdEiDGP9aaPkkBg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:36:24.985499Z","signed_message":"canonical_sha256_bytes"},"source_id":"1507.06429","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5459827a5244fefa08e8f2501b28f59ab31bf3e46dc339870541fd509255154","sha256:98c302fc49e7be00d0221318d5f0a91ffe5808c2478406828f4426d58774c729"],"state_sha256":"701276c7dea489de443cdb9c684e127f5b228df2618f0d8f72f17d3c640a2904"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lO5hkGpPg9C6aPEbjLP17beODq3zi4ZsZ8s8geaDvGilUHdm2OHyyRtW5RBxfNSU5tF7jfw8w3Rl+iXp7zu8Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T01:29:47.675189Z","bundle_sha256":"fb986e40c91928ca0cba1c0acbaea3d92638dec62231f48a38d21255a5062bab"}}