{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:XRD27ZI3DD5ORJZE35AWNJWYSO","short_pith_number":"pith:XRD27ZI3","canonical_record":{"source":{"id":"1406.6247","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-06-24T14:16:56Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"b5f82e925cfd0bb4e0c5329f474e925ced6ad4ea003a1c9b76ce2934518d6c6e","abstract_canon_sha256":"d7ed6575fcec28deb0f1504d2b4743bae5d1ef895b264ca424bda50ac0b36e24"},"schema_version":"1.0"},"canonical_sha256":"bc47afe51b18fae8a724df4166a6d8939ad542f34dd30b63d5d8fde3c3e9ff93","source":{"kind":"arxiv","id":"1406.6247","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1406.6247","created_at":"2026-05-18T02:49:03Z"},{"alias_kind":"arxiv_version","alias_value":"1406.6247v1","created_at":"2026-05-18T02:49:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1406.6247","created_at":"2026-05-18T02:49:03Z"},{"alias_kind":"pith_short_12","alias_value":"XRD27ZI3DD5O","created_at":"2026-05-18T12:28:57Z"},{"alias_kind":"pith_short_16","alias_value":"XRD27ZI3DD5ORJZE","created_at":"2026-05-18T12:28:57Z"},{"alias_kind":"pith_short_8","alias_value":"XRD27ZI3","created_at":"2026-05-18T12:28:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:XRD27ZI3DD5ORJZE35AWNJWYSO","target":"record","payload":{"canonical_record":{"source":{"id":"1406.6247","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-06-24T14:16:56Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"b5f82e925cfd0bb4e0c5329f474e925ced6ad4ea003a1c9b76ce2934518d6c6e","abstract_canon_sha256":"d7ed6575fcec28deb0f1504d2b4743bae5d1ef895b264ca424bda50ac0b36e24"},"schema_version":"1.0"},"canonical_sha256":"bc47afe51b18fae8a724df4166a6d8939ad542f34dd30b63d5d8fde3c3e9ff93","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:49:03.791792Z","signature_b64":"D084CnLqTpTWxrOW+Wl88ORksUSUxo62O9VrXkzmCdv8f1rJsN/ayuhqPOMIJZQyZTNCz5K7GOjARe7OKzxLAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc47afe51b18fae8a724df4166a6d8939ad542f34dd30b63d5d8fde3c3e9ff93","last_reissued_at":"2026-05-18T02:49:03.791346Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:49:03.791346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1406.6247","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":"2026-05-18T02:49:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4kmLfHXLat7NqgUBZKiQ/oOz8Tp87mHhT/bQUkhlhoVLMlCMojC1wDqVJEDP1d3MCVUFqn4OfR7m4404OPwMCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T04:42:39.928075Z"},"content_sha256":"8781e12d4861553b1e231544dd12ea9040ab91f3ef8819a959f66277db3967af","schema_version":"1.0","event_id":"sha256:8781e12d4861553b1e231544dd12ea9040ab91f3ef8819a959f66277db3967af"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:XRD27ZI3DD5ORJZE35AWNJWYSO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Recurrent Models of Visual Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Graves, Koray Kavukcuoglu, Nicolas Heess, Volodymyr Mnih","submitted_at":"2014-06-24T14:16:56Z","abstract_excerpt":"Applying convolutional neural networks to large images is computationally expensive because the amount of computation scales linearly with the number of image pixels. We present a novel recurrent neural network model that is capable of extracting information from an image or video by adaptively selecting a sequence of regions or locations and only processing the selected regions at high resolution. Like convolutional neural networks, the proposed model has a degree of translation invariance built-in, but the amount of computation it performs can be controlled independently of the input image s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1406.6247","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":"2026-05-18T02:49:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YkMcIIevI50vRvM+Kpv2pMmRolLZepiktSCtAy4bbaisldT6hORg9CkoSIGF/Z2DiyptmLRem9512XSTwNu/Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T04:42:39.928442Z"},"content_sha256":"217ab19c8f36600b50ddeef9dc577a8ed89c9ac3670a9b1db03bc88486c0c208","schema_version":"1.0","event_id":"sha256:217ab19c8f36600b50ddeef9dc577a8ed89c9ac3670a9b1db03bc88486c0c208"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XRD27ZI3DD5ORJZE35AWNJWYSO/bundle.json","state_url":"https://pith.science/pith/XRD27ZI3DD5ORJZE35AWNJWYSO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XRD27ZI3DD5ORJZE35AWNJWYSO/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":"2026-05-28T04:42:39Z","links":{"resolver":"https://pith.science/pith/XRD27ZI3DD5ORJZE35AWNJWYSO","bundle":"https://pith.science/pith/XRD27ZI3DD5ORJZE35AWNJWYSO/bundle.json","state":"https://pith.science/pith/XRD27ZI3DD5ORJZE35AWNJWYSO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XRD27ZI3DD5ORJZE35AWNJWYSO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:XRD27ZI3DD5ORJZE35AWNJWYSO","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":"d7ed6575fcec28deb0f1504d2b4743bae5d1ef895b264ca424bda50ac0b36e24","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-06-24T14:16:56Z","title_canon_sha256":"b5f82e925cfd0bb4e0c5329f474e925ced6ad4ea003a1c9b76ce2934518d6c6e"},"schema_version":"1.0","source":{"id":"1406.6247","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1406.6247","created_at":"2026-05-18T02:49:03Z"},{"alias_kind":"arxiv_version","alias_value":"1406.6247v1","created_at":"2026-05-18T02:49:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1406.6247","created_at":"2026-05-18T02:49:03Z"},{"alias_kind":"pith_short_12","alias_value":"XRD27ZI3DD5O","created_at":"2026-05-18T12:28:57Z"},{"alias_kind":"pith_short_16","alias_value":"XRD27ZI3DD5ORJZE","created_at":"2026-05-18T12:28:57Z"},{"alias_kind":"pith_short_8","alias_value":"XRD27ZI3","created_at":"2026-05-18T12:28:57Z"}],"graph_snapshots":[{"event_id":"sha256:217ab19c8f36600b50ddeef9dc577a8ed89c9ac3670a9b1db03bc88486c0c208","target":"graph","created_at":"2026-05-18T02:49:03Z","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":"Applying convolutional neural networks to large images is computationally expensive because the amount of computation scales linearly with the number of image pixels. We present a novel recurrent neural network model that is capable of extracting information from an image or video by adaptively selecting a sequence of regions or locations and only processing the selected regions at high resolution. Like convolutional neural networks, the proposed model has a degree of translation invariance built-in, but the amount of computation it performs can be controlled independently of the input image s","authors_text":"Alex Graves, Koray Kavukcuoglu, Nicolas Heess, Volodymyr Mnih","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-06-24T14:16:56Z","title":"Recurrent Models of Visual Attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1406.6247","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":"sha256:8781e12d4861553b1e231544dd12ea9040ab91f3ef8819a959f66277db3967af","target":"record","created_at":"2026-05-18T02:49:03Z","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":"d7ed6575fcec28deb0f1504d2b4743bae5d1ef895b264ca424bda50ac0b36e24","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-06-24T14:16:56Z","title_canon_sha256":"b5f82e925cfd0bb4e0c5329f474e925ced6ad4ea003a1c9b76ce2934518d6c6e"},"schema_version":"1.0","source":{"id":"1406.6247","kind":"arxiv","version":1}},"canonical_sha256":"bc47afe51b18fae8a724df4166a6d8939ad542f34dd30b63d5d8fde3c3e9ff93","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bc47afe51b18fae8a724df4166a6d8939ad542f34dd30b63d5d8fde3c3e9ff93","first_computed_at":"2026-05-18T02:49:03.791346Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:49:03.791346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D084CnLqTpTWxrOW+Wl88ORksUSUxo62O9VrXkzmCdv8f1rJsN/ayuhqPOMIJZQyZTNCz5K7GOjARe7OKzxLAA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:49:03.791792Z","signed_message":"canonical_sha256_bytes"},"source_id":"1406.6247","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8781e12d4861553b1e231544dd12ea9040ab91f3ef8819a959f66277db3967af","sha256:217ab19c8f36600b50ddeef9dc577a8ed89c9ac3670a9b1db03bc88486c0c208"],"state_sha256":"e2d4dfe7c7cb6f41e1b12ae81e3f8aa551685090eaef27b560192bae92391b6d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c9hUXJnLCfvoJuqZ7o1VUSbiI4ZH+hxj8gqcxYM54+wqinLFIyqQS1kFMTyQrhEGxASXax+13NntsTog31yoDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T04:42:39.930648Z","bundle_sha256":"c6f79a9e7f9b6e2937063a8627201c0d1a12d8e89c5ef7d904e79d6ed4816d1a"}}