{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:GQ5OSV5X25TKQXARN5F5MGAIIL","short_pith_number":"pith:GQ5OSV5X","canonical_record":{"source":{"id":"1505.05232","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-05-20T02:52:07Z","cross_cats_sorted":[],"title_canon_sha256":"8a26b8970113897944e50d84fbdf11a51bde11fc26fd6547825c28c2379c4e8e","abstract_canon_sha256":"3ca95299d4fe887dff51f7fd5dd8ed7e3b36182a176aa60d7832afc42bdf06dd"},"schema_version":"1.0"},"canonical_sha256":"343ae957b7d766a85c116f4bd6180842e7e43752357c6d503f9e3d8abf073cc4","source":{"kind":"arxiv","id":"1505.05232","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1505.05232","created_at":"2026-05-18T02:03:58Z"},{"alias_kind":"arxiv_version","alias_value":"1505.05232v1","created_at":"2026-05-18T02:03:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1505.05232","created_at":"2026-05-18T02:03:58Z"},{"alias_kind":"pith_short_12","alias_value":"GQ5OSV5X25TK","created_at":"2026-05-18T12:29:22Z"},{"alias_kind":"pith_short_16","alias_value":"GQ5OSV5X25TKQXAR","created_at":"2026-05-18T12:29:22Z"},{"alias_kind":"pith_short_8","alias_value":"GQ5OSV5X","created_at":"2026-05-18T12:29:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:GQ5OSV5X25TKQXARN5F5MGAIIL","target":"record","payload":{"canonical_record":{"source":{"id":"1505.05232","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-05-20T02:52:07Z","cross_cats_sorted":[],"title_canon_sha256":"8a26b8970113897944e50d84fbdf11a51bde11fc26fd6547825c28c2379c4e8e","abstract_canon_sha256":"3ca95299d4fe887dff51f7fd5dd8ed7e3b36182a176aa60d7832afc42bdf06dd"},"schema_version":"1.0"},"canonical_sha256":"343ae957b7d766a85c116f4bd6180842e7e43752357c6d503f9e3d8abf073cc4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:03:58.988595Z","signature_b64":"V33HY+KGBmTbSXMvGNkcUch/eAOag0QxP5ElRWJ7SNIfn0Mjg+va5My2DE8yBS1MkCYy8rsXkYcRuPMK2aBIBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"343ae957b7d766a85c116f4bd6180842e7e43752357c6d503f9e3d8abf073cc4","last_reissued_at":"2026-05-18T02:03:58.987750Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:03:58.987750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1505.05232","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":"2026-05-18T02:03:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r2qw5jSL+apkdus0G8IXNTdXAs6oWwVr2R3XGnu7WbFDKNFYbOo5V9iCMdnPwtM5MKJVoeh4hnodCEHVDntQAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:53:54.909106Z"},"content_sha256":"9e76f0464bbe0b36282172ed6024dc89bc167ec3057175b778665d9fe61b217f","schema_version":"1.0","event_id":"sha256:9e76f0464bbe0b36282172ed6024dc89bc167ec3057175b778665d9fe61b217f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:GQ5OSV5X25TKQXARN5F5MGAIIL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-scale recognition with DAG-CNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deva Ramanan, Songfan Yang","submitted_at":"2015-05-20T02:52:07Z","abstract_excerpt":"We explore multi-scale convolutional neural nets (CNNs) for image classification. Contemporary approaches extract features from a single output layer. By extracting features from multiple layers, one can simultaneously reason about high, mid, and low-level features during classification. The resulting multi-scale architecture can itself be seen as a feed-forward model that is structured as a directed acyclic graph (DAG-CNNs). We use DAG-CNNs to learn a set of multiscale features that can be effectively shared between coarse and fine-grained classification tasks. While fine-tuning such models h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1505.05232","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":"2026-05-18T02:03:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lU4AprlwJUsw9ozDJ480+z6+XIz126JJkKZH3NHhFZ/u5/0ebokoB0bnMY2ocKW3/SKsc+TRSGgiuiNxiOTeDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:53:54.909592Z"},"content_sha256":"ba2a83dfd0da9e8294d416b95ced575149b389188147049ce3f7949845e04cd7","schema_version":"1.0","event_id":"sha256:ba2a83dfd0da9e8294d416b95ced575149b389188147049ce3f7949845e04cd7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GQ5OSV5X25TKQXARN5F5MGAIIL/bundle.json","state_url":"https://pith.science/pith/GQ5OSV5X25TKQXARN5F5MGAIIL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GQ5OSV5X25TKQXARN5F5MGAIIL/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":"2026-08-04T17:53:54Z","links":{"resolver":"https://pith.science/pith/GQ5OSV5X25TKQXARN5F5MGAIIL","bundle":"https://pith.science/pith/GQ5OSV5X25TKQXARN5F5MGAIIL/bundle.json","state":"https://pith.science/pith/GQ5OSV5X25TKQXARN5F5MGAIIL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GQ5OSV5X25TKQXARN5F5MGAIIL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:GQ5OSV5X25TKQXARN5F5MGAIIL","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":"3ca95299d4fe887dff51f7fd5dd8ed7e3b36182a176aa60d7832afc42bdf06dd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-05-20T02:52:07Z","title_canon_sha256":"8a26b8970113897944e50d84fbdf11a51bde11fc26fd6547825c28c2379c4e8e"},"schema_version":"1.0","source":{"id":"1505.05232","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1505.05232","created_at":"2026-05-18T02:03:58Z"},{"alias_kind":"arxiv_version","alias_value":"1505.05232v1","created_at":"2026-05-18T02:03:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1505.05232","created_at":"2026-05-18T02:03:58Z"},{"alias_kind":"pith_short_12","alias_value":"GQ5OSV5X25TK","created_at":"2026-05-18T12:29:22Z"},{"alias_kind":"pith_short_16","alias_value":"GQ5OSV5X25TKQXAR","created_at":"2026-05-18T12:29:22Z"},{"alias_kind":"pith_short_8","alias_value":"GQ5OSV5X","created_at":"2026-05-18T12:29:22Z"}],"graph_snapshots":[{"event_id":"sha256:ba2a83dfd0da9e8294d416b95ced575149b389188147049ce3f7949845e04cd7","target":"graph","created_at":"2026-05-18T02:03:58Z","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":"We explore multi-scale convolutional neural nets (CNNs) for image classification. Contemporary approaches extract features from a single output layer. By extracting features from multiple layers, one can simultaneously reason about high, mid, and low-level features during classification. The resulting multi-scale architecture can itself be seen as a feed-forward model that is structured as a directed acyclic graph (DAG-CNNs). We use DAG-CNNs to learn a set of multiscale features that can be effectively shared between coarse and fine-grained classification tasks. While fine-tuning such models h","authors_text":"Deva Ramanan, Songfan Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-05-20T02:52:07Z","title":"Multi-scale recognition with DAG-CNNs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1505.05232","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":"sha256:9e76f0464bbe0b36282172ed6024dc89bc167ec3057175b778665d9fe61b217f","target":"record","created_at":"2026-05-18T02:03:58Z","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":"3ca95299d4fe887dff51f7fd5dd8ed7e3b36182a176aa60d7832afc42bdf06dd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-05-20T02:52:07Z","title_canon_sha256":"8a26b8970113897944e50d84fbdf11a51bde11fc26fd6547825c28c2379c4e8e"},"schema_version":"1.0","source":{"id":"1505.05232","kind":"arxiv","version":1}},"canonical_sha256":"343ae957b7d766a85c116f4bd6180842e7e43752357c6d503f9e3d8abf073cc4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"343ae957b7d766a85c116f4bd6180842e7e43752357c6d503f9e3d8abf073cc4","first_computed_at":"2026-05-18T02:03:58.987750Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:03:58.987750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V33HY+KGBmTbSXMvGNkcUch/eAOag0QxP5ElRWJ7SNIfn0Mjg+va5My2DE8yBS1MkCYy8rsXkYcRuPMK2aBIBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:03:58.988595Z","signed_message":"canonical_sha256_bytes"},"source_id":"1505.05232","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9e76f0464bbe0b36282172ed6024dc89bc167ec3057175b778665d9fe61b217f","sha256:ba2a83dfd0da9e8294d416b95ced575149b389188147049ce3f7949845e04cd7"],"state_sha256":"5b4d699abba30eca4a0679dfb3343bc340edf9d09e98410a3b9dee4c79d009a1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z0HgzbQUqfM31F+nw0U3KJanCYppmpdEs3PbQsEXxBeFaScTh5qaq47bLU5d68p/3PcPb82aYjcgSR6D8ZSVAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T17:53:54.914299Z","bundle_sha256":"71fae7bb4ea9da991a1b04367df2f1fd7b3c407d73ebd6c5af53eea97d658588"}}