{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:7FSRUMGWHDWIQEYKBNDWDEIXNR","short_pith_number":"pith:7FSRUMGW","canonical_record":{"source":{"id":"1605.05395","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-05-17T23:08:46Z","cross_cats_sorted":[],"title_canon_sha256":"ac82d154b16480583ec8d260b5da929079686bc4d9c2377dfeb2b1dbac898a04","abstract_canon_sha256":"f124164890a1bf79dcb8b4e1c5e987dfd5695580740b826ce9fb0c824be2e040"},"schema_version":"1.0"},"canonical_sha256":"f9651a30d638ec88130a0b476191176c6b496ec68d5e9d5bf577ceb5e6822d05","source":{"kind":"arxiv","id":"1605.05395","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.05395","created_at":"2026-05-18T01:14:35Z"},{"alias_kind":"arxiv_version","alias_value":"1605.05395v1","created_at":"2026-05-18T01:14:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.05395","created_at":"2026-05-18T01:14:35Z"},{"alias_kind":"pith_short_12","alias_value":"7FSRUMGWHDWI","created_at":"2026-05-18T12:30:04Z"},{"alias_kind":"pith_short_16","alias_value":"7FSRUMGWHDWIQEYK","created_at":"2026-05-18T12:30:04Z"},{"alias_kind":"pith_short_8","alias_value":"7FSRUMGW","created_at":"2026-05-18T12:30:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:7FSRUMGWHDWIQEYKBNDWDEIXNR","target":"record","payload":{"canonical_record":{"source":{"id":"1605.05395","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-05-17T23:08:46Z","cross_cats_sorted":[],"title_canon_sha256":"ac82d154b16480583ec8d260b5da929079686bc4d9c2377dfeb2b1dbac898a04","abstract_canon_sha256":"f124164890a1bf79dcb8b4e1c5e987dfd5695580740b826ce9fb0c824be2e040"},"schema_version":"1.0"},"canonical_sha256":"f9651a30d638ec88130a0b476191176c6b496ec68d5e9d5bf577ceb5e6822d05","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:14:35.127058Z","signature_b64":"UEvn0odfbDHuJuoXcLJ/rRoU2/uNM2dbiZdAOctA1HhNYrBknXxRii9LH2p8rDi4SSYTKmftrQA7iHp5u12RCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9651a30d638ec88130a0b476191176c6b496ec68d5e9d5bf577ceb5e6822d05","last_reissued_at":"2026-05-18T01:14:35.126276Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:14:35.126276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1605.05395","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":"2026-05-18T01:14:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/HlEFKkx9bcbHsMLOo9ote+mbdZpzKs/U4f3h+vL8GUMD8ne9hOFeQCUN7hkgnbZKaDvPfD/hoDSTmeiQxiZCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T18:49:03.318748Z"},"content_sha256":"a3b25fda05d2ae34d29453788aebcd69a543408d310c47661984a9266bd6769b","schema_version":"1.0","event_id":"sha256:a3b25fda05d2ae34d29453788aebcd69a543408d310c47661984a9266bd6769b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:7FSRUMGWHDWIQEYKBNDWDEIXNR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Deep Representations of Fine-grained Visual Descriptions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bernt Schiele, Honglak Lee, Scott Reed, Zeynep Akata","submitted_at":"2016-05-17T23:08:46Z","abstract_excerpt":"State-of-the-art methods for zero-shot visual recognition formulate learning as a joint embedding problem of images and side information. In these formulations the current best complement to visual features are attributes: manually encoded vectors describing shared characteristics among categories. Despite good performance, attributes have limitations: (1) finer-grained recognition requires commensurately more attributes, and (2) attributes do not provide a natural language interface. We propose to overcome these limitations by training neural language models from scratch; i.e. without pre-tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.05395","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":"2026-05-18T01:14:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gQa8vJ1ngpAeMNe332PisN582eLeEPGv6Pn4ofiFeEFvI6BAYkyu2QGt8uJzOaWkn/WAwt0i1TcokHQNfljoBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T18:49:03.319475Z"},"content_sha256":"21fbd9a899e12909bca7a9364f643b6bad6f66fb4df1a958b86514d1936537ab","schema_version":"1.0","event_id":"sha256:21fbd9a899e12909bca7a9364f643b6bad6f66fb4df1a958b86514d1936537ab"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7FSRUMGWHDWIQEYKBNDWDEIXNR/bundle.json","state_url":"https://pith.science/pith/7FSRUMGWHDWIQEYKBNDWDEIXNR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7FSRUMGWHDWIQEYKBNDWDEIXNR/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":"2026-06-05T18:49:03Z","links":{"resolver":"https://pith.science/pith/7FSRUMGWHDWIQEYKBNDWDEIXNR","bundle":"https://pith.science/pith/7FSRUMGWHDWIQEYKBNDWDEIXNR/bundle.json","state":"https://pith.science/pith/7FSRUMGWHDWIQEYKBNDWDEIXNR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7FSRUMGWHDWIQEYKBNDWDEIXNR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:7FSRUMGWHDWIQEYKBNDWDEIXNR","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":"f124164890a1bf79dcb8b4e1c5e987dfd5695580740b826ce9fb0c824be2e040","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-05-17T23:08:46Z","title_canon_sha256":"ac82d154b16480583ec8d260b5da929079686bc4d9c2377dfeb2b1dbac898a04"},"schema_version":"1.0","source":{"id":"1605.05395","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.05395","created_at":"2026-05-18T01:14:35Z"},{"alias_kind":"arxiv_version","alias_value":"1605.05395v1","created_at":"2026-05-18T01:14:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.05395","created_at":"2026-05-18T01:14:35Z"},{"alias_kind":"pith_short_12","alias_value":"7FSRUMGWHDWI","created_at":"2026-05-18T12:30:04Z"},{"alias_kind":"pith_short_16","alias_value":"7FSRUMGWHDWIQEYK","created_at":"2026-05-18T12:30:04Z"},{"alias_kind":"pith_short_8","alias_value":"7FSRUMGW","created_at":"2026-05-18T12:30:04Z"}],"graph_snapshots":[{"event_id":"sha256:21fbd9a899e12909bca7a9364f643b6bad6f66fb4df1a958b86514d1936537ab","target":"graph","created_at":"2026-05-18T01:14:35Z","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":"State-of-the-art methods for zero-shot visual recognition formulate learning as a joint embedding problem of images and side information. In these formulations the current best complement to visual features are attributes: manually encoded vectors describing shared characteristics among categories. Despite good performance, attributes have limitations: (1) finer-grained recognition requires commensurately more attributes, and (2) attributes do not provide a natural language interface. We propose to overcome these limitations by training neural language models from scratch; i.e. without pre-tra","authors_text":"Bernt Schiele, Honglak Lee, Scott Reed, Zeynep Akata","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-05-17T23:08:46Z","title":"Learning Deep Representations of Fine-grained Visual Descriptions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.05395","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:a3b25fda05d2ae34d29453788aebcd69a543408d310c47661984a9266bd6769b","target":"record","created_at":"2026-05-18T01:14:35Z","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":"f124164890a1bf79dcb8b4e1c5e987dfd5695580740b826ce9fb0c824be2e040","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-05-17T23:08:46Z","title_canon_sha256":"ac82d154b16480583ec8d260b5da929079686bc4d9c2377dfeb2b1dbac898a04"},"schema_version":"1.0","source":{"id":"1605.05395","kind":"arxiv","version":1}},"canonical_sha256":"f9651a30d638ec88130a0b476191176c6b496ec68d5e9d5bf577ceb5e6822d05","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f9651a30d638ec88130a0b476191176c6b496ec68d5e9d5bf577ceb5e6822d05","first_computed_at":"2026-05-18T01:14:35.126276Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:14:35.126276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UEvn0odfbDHuJuoXcLJ/rRoU2/uNM2dbiZdAOctA1HhNYrBknXxRii9LH2p8rDi4SSYTKmftrQA7iHp5u12RCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:14:35.127058Z","signed_message":"canonical_sha256_bytes"},"source_id":"1605.05395","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a3b25fda05d2ae34d29453788aebcd69a543408d310c47661984a9266bd6769b","sha256:21fbd9a899e12909bca7a9364f643b6bad6f66fb4df1a958b86514d1936537ab"],"state_sha256":"d7c33d7cb30ffd85a83a3f5875d374cc39bd1165fa32253539391c8ffd8110e5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RhsLbJgeYQvosONj+Ueaet2bqPKjNz+QqWOSmnhPXFMb4fApO+573S2SmPpOpf4gVL9EdaV6WCtaDfeCATmXBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T18:49:03.324272Z","bundle_sha256":"0b263d3f39ad3e53787b2bc079658a6ce0f224fb324582e46ab61a5b40a64c67"}}