{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:RHTIT342Z634RJD4GCLKRZFN2V","short_pith_number":"pith:RHTIT342","canonical_record":{"source":{"id":"1812.01600","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-04T18:57:08Z","cross_cats_sorted":[],"title_canon_sha256":"bef2e8bc51cc6f48e4c73d8389ccd384ac80a339bcee0962a021f02dc809a5fc","abstract_canon_sha256":"3e0868ce5e57821a08d05e28ab14c0a7e37438bc54f482402541cfcc5b592cb0"},"schema_version":"1.0"},"canonical_sha256":"89e689ef9acfb7c8a47c3096a8e4add565940a5f3e0fe1a4ced61fb45ec150be","source":{"kind":"arxiv","id":"1812.01600","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.01600","created_at":"2026-07-04T23:50:53Z"},{"alias_kind":"arxiv_version","alias_value":"1812.01600v2","created_at":"2026-07-04T23:50:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.01600","created_at":"2026-07-04T23:50:53Z"},{"alias_kind":"pith_short_12","alias_value":"RHTIT342Z634","created_at":"2026-07-04T23:50:53Z"},{"alias_kind":"pith_short_16","alias_value":"RHTIT342Z634RJD4","created_at":"2026-07-04T23:50:53Z"},{"alias_kind":"pith_short_8","alias_value":"RHTIT342","created_at":"2026-07-04T23:50:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:RHTIT342Z634RJD4GCLKRZFN2V","target":"record","payload":{"canonical_record":{"source":{"id":"1812.01600","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-04T18:57:08Z","cross_cats_sorted":[],"title_canon_sha256":"bef2e8bc51cc6f48e4c73d8389ccd384ac80a339bcee0962a021f02dc809a5fc","abstract_canon_sha256":"3e0868ce5e57821a08d05e28ab14c0a7e37438bc54f482402541cfcc5b592cb0"},"schema_version":"1.0"},"canonical_sha256":"89e689ef9acfb7c8a47c3096a8e4add565940a5f3e0fe1a4ced61fb45ec150be","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:50:53.740977Z","signature_b64":"LCa5Ro2jbGqVBt7iyhaoICInHCz8HrpkoAakxEAK2isGfaizJo/dSEhEavToKmP7uLj8vN118cmkLmdR0Lj9BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89e689ef9acfb7c8a47c3096a8e4add565940a5f3e0fe1a4ced61fb45ec150be","last_reissued_at":"2026-07-04T23:50:53.740571Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:50:53.740571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.01600","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-04T23:50:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rNIVLTy+SaBOQsbclCOWVdq3NsKyjrZe9ybUvQs8OnfuQz/mTZWQ1oiZ4v32vnQLzl/FdYM9JvbnqDUjgUceBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T21:47:51.947867Z"},"content_sha256":"fd9322e3bb798196788f2d5fdb36c8cdce7ed42670bcadd06b7c026b3774e45e","schema_version":"1.0","event_id":"sha256:fd9322e3bb798196788f2d5fdb36c8cdce7ed42670bcadd06b7c026b3774e45e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:RHTIT342Z634RJD4GCLKRZFN2V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AutoFocus: Efficient Multi-Scale Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bharat Singh, Larry S. Davis, Mahyar Najibi","submitted_at":"2018-12-04T18:57:08Z","abstract_excerpt":"This paper describes AutoFocus, an efficient multi-scale inference algorithm for deep-learning based object detectors. Instead of processing an entire image pyramid, AutoFocus adopts a coarse to fine approach and only processes regions which are likely to contain small objects at finer scales. This is achieved by predicting category agnostic segmentation maps for small objects at coarser scales, called FocusPixels. FocusPixels can be predicted with high recall, and in many cases, they only cover a small fraction of the entire image. To make efficient use of FocusPixels, an algorithm is propose"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.01600","kind":"arxiv","version":2},"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/1812.01600/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":"2026-07-04T23:50:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JB0/4hl6V8h4b8KDSug/FtOCHEWtITXSkwIhJgR+F+ftjDKq7ZT1PB3bmCSO8rXyyMPBIrX5rFOgEHFT8cniDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T21:47:51.948412Z"},"content_sha256":"33420cd2934dbb4b782e0e72358ed739267f959d0dcff39f23926c18abe0a58f","schema_version":"1.0","event_id":"sha256:33420cd2934dbb4b782e0e72358ed739267f959d0dcff39f23926c18abe0a58f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RHTIT342Z634RJD4GCLKRZFN2V/bundle.json","state_url":"https://pith.science/pith/RHTIT342Z634RJD4GCLKRZFN2V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RHTIT342Z634RJD4GCLKRZFN2V/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":"2026-08-15T21:47:51Z","links":{"resolver":"https://pith.science/pith/RHTIT342Z634RJD4GCLKRZFN2V","bundle":"https://pith.science/pith/RHTIT342Z634RJD4GCLKRZFN2V/bundle.json","state":"https://pith.science/pith/RHTIT342Z634RJD4GCLKRZFN2V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RHTIT342Z634RJD4GCLKRZFN2V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:RHTIT342Z634RJD4GCLKRZFN2V","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":"3e0868ce5e57821a08d05e28ab14c0a7e37438bc54f482402541cfcc5b592cb0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-04T18:57:08Z","title_canon_sha256":"bef2e8bc51cc6f48e4c73d8389ccd384ac80a339bcee0962a021f02dc809a5fc"},"schema_version":"1.0","source":{"id":"1812.01600","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.01600","created_at":"2026-07-04T23:50:53Z"},{"alias_kind":"arxiv_version","alias_value":"1812.01600v2","created_at":"2026-07-04T23:50:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.01600","created_at":"2026-07-04T23:50:53Z"},{"alias_kind":"pith_short_12","alias_value":"RHTIT342Z634","created_at":"2026-07-04T23:50:53Z"},{"alias_kind":"pith_short_16","alias_value":"RHTIT342Z634RJD4","created_at":"2026-07-04T23:50:53Z"},{"alias_kind":"pith_short_8","alias_value":"RHTIT342","created_at":"2026-07-04T23:50:53Z"}],"graph_snapshots":[{"event_id":"sha256:33420cd2934dbb4b782e0e72358ed739267f959d0dcff39f23926c18abe0a58f","target":"graph","created_at":"2026-07-04T23:50:53Z","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/1812.01600/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper describes AutoFocus, an efficient multi-scale inference algorithm for deep-learning based object detectors. Instead of processing an entire image pyramid, AutoFocus adopts a coarse to fine approach and only processes regions which are likely to contain small objects at finer scales. This is achieved by predicting category agnostic segmentation maps for small objects at coarser scales, called FocusPixels. FocusPixels can be predicted with high recall, and in many cases, they only cover a small fraction of the entire image. To make efficient use of FocusPixels, an algorithm is propose","authors_text":"Bharat Singh, Larry S. Davis, Mahyar Najibi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-04T18:57:08Z","title":"AutoFocus: Efficient Multi-Scale Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.01600","kind":"arxiv","version":2},"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:fd9322e3bb798196788f2d5fdb36c8cdce7ed42670bcadd06b7c026b3774e45e","target":"record","created_at":"2026-07-04T23:50:53Z","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":"3e0868ce5e57821a08d05e28ab14c0a7e37438bc54f482402541cfcc5b592cb0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-04T18:57:08Z","title_canon_sha256":"bef2e8bc51cc6f48e4c73d8389ccd384ac80a339bcee0962a021f02dc809a5fc"},"schema_version":"1.0","source":{"id":"1812.01600","kind":"arxiv","version":2}},"canonical_sha256":"89e689ef9acfb7c8a47c3096a8e4add565940a5f3e0fe1a4ced61fb45ec150be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89e689ef9acfb7c8a47c3096a8e4add565940a5f3e0fe1a4ced61fb45ec150be","first_computed_at":"2026-07-04T23:50:53.740571Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:50:53.740571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LCa5Ro2jbGqVBt7iyhaoICInHCz8HrpkoAakxEAK2isGfaizJo/dSEhEavToKmP7uLj8vN118cmkLmdR0Lj9BA==","signature_status":"signed_v1","signed_at":"2026-07-04T23:50:53.740977Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.01600","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fd9322e3bb798196788f2d5fdb36c8cdce7ed42670bcadd06b7c026b3774e45e","sha256:33420cd2934dbb4b782e0e72358ed739267f959d0dcff39f23926c18abe0a58f"],"state_sha256":"30cf3dfd9f5998f9a63feaa23481461c372784cdf3c345e3a0fcdff4e49f378f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UUV6LMe2ksBKKafwlXVaDxgqb2hb5NuWBhh2Xlltkb0FKa/Z4ilBfbJVsCx3zSw0B8jfbtFkWSn4mfNeaMYECg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T21:47:51.952427Z","bundle_sha256":"3abed24beb85cf22527c722204eb1ada542ce5685f80c5da031a18048b26d73d"}}