{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:2RNR6HYJ3Y5HADKG437MPFFM3X","short_pith_number":"pith:2RNR6HYJ","canonical_record":{"source":{"id":"2111.07534","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-15T04:47:47Z","cross_cats_sorted":[],"title_canon_sha256":"7fc44c2918c06941fbcafba80e036dc5e179db6c3a0fc8122571331b914f828d","abstract_canon_sha256":"2573aa049f75516c10a307d409c61089d1abdfebdd2c0e1c66638a4074fbddb0"},"schema_version":"1.0"},"canonical_sha256":"d45b1f1f09de3a700d46e6fec794acddda29c698fc23500d8aca9648c20c46b6","source":{"kind":"arxiv","id":"2111.07534","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.07534","created_at":"2026-07-05T03:31:40Z"},{"alias_kind":"arxiv_version","alias_value":"2111.07534v1","created_at":"2026-07-05T03:31:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.07534","created_at":"2026-07-05T03:31:40Z"},{"alias_kind":"pith_short_12","alias_value":"2RNR6HYJ3Y5H","created_at":"2026-07-05T03:31:40Z"},{"alias_kind":"pith_short_16","alias_value":"2RNR6HYJ3Y5HADKG","created_at":"2026-07-05T03:31:40Z"},{"alias_kind":"pith_short_8","alias_value":"2RNR6HYJ","created_at":"2026-07-05T03:31:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:2RNR6HYJ3Y5HADKG437MPFFM3X","target":"record","payload":{"canonical_record":{"source":{"id":"2111.07534","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-15T04:47:47Z","cross_cats_sorted":[],"title_canon_sha256":"7fc44c2918c06941fbcafba80e036dc5e179db6c3a0fc8122571331b914f828d","abstract_canon_sha256":"2573aa049f75516c10a307d409c61089d1abdfebdd2c0e1c66638a4074fbddb0"},"schema_version":"1.0"},"canonical_sha256":"d45b1f1f09de3a700d46e6fec794acddda29c698fc23500d8aca9648c20c46b6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:31:40.788966Z","signature_b64":"r9cF8itdJvtr1/0zvFVVYXWpX5CdBVQbF9QgBBELDSpGLWiLj0CdejEy+VcZKCYynAcAYGYL7RLu0f46JsXjBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d45b1f1f09de3a700d46e6fec794acddda29c698fc23500d8aca9648c20c46b6","last_reissued_at":"2026-07-05T03:31:40.788632Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:31:40.788632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.07534","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":"2026-07-05T03:31:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7uOGxIpqFUAVMUnl4UW6M8PhzV+vMXUp2mfmIhFLhgy2LfAVZowBoEVmaVxsaM68naCGhNUT8zg+0ylmaNxgBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T12:22:15.354336Z"},"content_sha256":"c2022b95fb34d01a3e61661355f033e31eee7caae7fe7b32d05fd3ca571663f0","schema_version":"1.0","event_id":"sha256:c2022b95fb34d01a3e61661355f033e31eee7caae7fe7b32d05fd3ca571663f0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:2RNR6HYJ3Y5HADKG437MPFFM3X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Probabilistic Hard Attention Model For Sequentially Observed Scenes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"James J. Clark, Samrudhdhi B. Rangrej","submitted_at":"2021-11-15T04:47:47Z","abstract_excerpt":"A visual hard attention model actively selects and observes a sequence of subregions in an image to make a prediction. The majority of hard attention models determine the attention-worthy regions by first analyzing a complete image. However, it may be the case that the entire image is not available initially but instead sensed gradually through a series of partial observations. In this paper, we design an efficient hard attention model for classifying such sequentially observed scenes. The presented model never observes an image completely. To select informative regions under partial observabi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.07534","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/2111.07534/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":"2026-07-05T03:31:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XF+va6Zop0BR/H5yose3+HPG0ok6iMIwmNxYxY7MxmQqVrwCUZhA0ciDQ4FwcVIZaeZ0HaIFGfbeeE1WLrshCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T12:22:15.354841Z"},"content_sha256":"971c9e66542370c10d5b34eb860510d207d1105c3eb887f21d6a2a2e57251caa","schema_version":"1.0","event_id":"sha256:971c9e66542370c10d5b34eb860510d207d1105c3eb887f21d6a2a2e57251caa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2RNR6HYJ3Y5HADKG437MPFFM3X/bundle.json","state_url":"https://pith.science/pith/2RNR6HYJ3Y5HADKG437MPFFM3X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2RNR6HYJ3Y5HADKG437MPFFM3X/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":"2026-08-13T12:22:15Z","links":{"resolver":"https://pith.science/pith/2RNR6HYJ3Y5HADKG437MPFFM3X","bundle":"https://pith.science/pith/2RNR6HYJ3Y5HADKG437MPFFM3X/bundle.json","state":"https://pith.science/pith/2RNR6HYJ3Y5HADKG437MPFFM3X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2RNR6HYJ3Y5HADKG437MPFFM3X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:2RNR6HYJ3Y5HADKG437MPFFM3X","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":"2573aa049f75516c10a307d409c61089d1abdfebdd2c0e1c66638a4074fbddb0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-15T04:47:47Z","title_canon_sha256":"7fc44c2918c06941fbcafba80e036dc5e179db6c3a0fc8122571331b914f828d"},"schema_version":"1.0","source":{"id":"2111.07534","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.07534","created_at":"2026-07-05T03:31:40Z"},{"alias_kind":"arxiv_version","alias_value":"2111.07534v1","created_at":"2026-07-05T03:31:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.07534","created_at":"2026-07-05T03:31:40Z"},{"alias_kind":"pith_short_12","alias_value":"2RNR6HYJ3Y5H","created_at":"2026-07-05T03:31:40Z"},{"alias_kind":"pith_short_16","alias_value":"2RNR6HYJ3Y5HADKG","created_at":"2026-07-05T03:31:40Z"},{"alias_kind":"pith_short_8","alias_value":"2RNR6HYJ","created_at":"2026-07-05T03:31:40Z"}],"graph_snapshots":[{"event_id":"sha256:971c9e66542370c10d5b34eb860510d207d1105c3eb887f21d6a2a2e57251caa","target":"graph","created_at":"2026-07-05T03:31:40Z","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/2111.07534/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A visual hard attention model actively selects and observes a sequence of subregions in an image to make a prediction. The majority of hard attention models determine the attention-worthy regions by first analyzing a complete image. However, it may be the case that the entire image is not available initially but instead sensed gradually through a series of partial observations. In this paper, we design an efficient hard attention model for classifying such sequentially observed scenes. The presented model never observes an image completely. To select informative regions under partial observabi","authors_text":"James J. Clark, Samrudhdhi B. Rangrej","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-15T04:47:47Z","title":"A Probabilistic Hard Attention Model For Sequentially Observed Scenes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.07534","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:c2022b95fb34d01a3e61661355f033e31eee7caae7fe7b32d05fd3ca571663f0","target":"record","created_at":"2026-07-05T03:31:40Z","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":"2573aa049f75516c10a307d409c61089d1abdfebdd2c0e1c66638a4074fbddb0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-15T04:47:47Z","title_canon_sha256":"7fc44c2918c06941fbcafba80e036dc5e179db6c3a0fc8122571331b914f828d"},"schema_version":"1.0","source":{"id":"2111.07534","kind":"arxiv","version":1}},"canonical_sha256":"d45b1f1f09de3a700d46e6fec794acddda29c698fc23500d8aca9648c20c46b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d45b1f1f09de3a700d46e6fec794acddda29c698fc23500d8aca9648c20c46b6","first_computed_at":"2026-07-05T03:31:40.788632Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:31:40.788632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r9cF8itdJvtr1/0zvFVVYXWpX5CdBVQbF9QgBBELDSpGLWiLj0CdejEy+VcZKCYynAcAYGYL7RLu0f46JsXjBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:31:40.788966Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.07534","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c2022b95fb34d01a3e61661355f033e31eee7caae7fe7b32d05fd3ca571663f0","sha256:971c9e66542370c10d5b34eb860510d207d1105c3eb887f21d6a2a2e57251caa"],"state_sha256":"2edee93046b0cbc9978110d9df4e2d29caa6bfd1c10276e4844d12d5b37eadaf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mg+7i/ggdvzqmCKdTnJosP15tptlWuVOdy+HrU9gFYpXzug8CtaFTKw5c+eLACSDQFx5kZ3KIdS1GCK1L80SAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T12:22:15.359844Z","bundle_sha256":"209e532520743d22bddbfc454b5c192f73247e1c79138b270677a2dc0531499e"}}