{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:K6GT27FSQFXRNCJX7BGK5ZUXOP","short_pith_number":"pith:K6GT27FS","canonical_record":{"source":{"id":"1811.11833","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-11-28T21:06:27Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"7c71cccd8b33e206dc7b6f859ab117a271d1e4f1ff5d238f598bccd983fe5042","abstract_canon_sha256":"e04937e4777ed8bbc5a1dc07c18e7b387cc65dfb7ea7c4a4f269235e44fcfc3b"},"schema_version":"1.0"},"canonical_sha256":"578d3d7cb2816f168937f84caee69773fc4db23c8887a909f563c24734382f11","source":{"kind":"arxiv","id":"1811.11833","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.11833","created_at":"2026-05-17T23:59:37Z"},{"alias_kind":"arxiv_version","alias_value":"1811.11833v1","created_at":"2026-05-17T23:59:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.11833","created_at":"2026-05-17T23:59:37Z"},{"alias_kind":"pith_short_12","alias_value":"K6GT27FSQFXR","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"K6GT27FSQFXRNCJX","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"K6GT27FS","created_at":"2026-05-18T12:32:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:K6GT27FSQFXRNCJX7BGK5ZUXOP","target":"record","payload":{"canonical_record":{"source":{"id":"1811.11833","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-11-28T21:06:27Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"7c71cccd8b33e206dc7b6f859ab117a271d1e4f1ff5d238f598bccd983fe5042","abstract_canon_sha256":"e04937e4777ed8bbc5a1dc07c18e7b387cc65dfb7ea7c4a4f269235e44fcfc3b"},"schema_version":"1.0"},"canonical_sha256":"578d3d7cb2816f168937f84caee69773fc4db23c8887a909f563c24734382f11","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:37.502517Z","signature_b64":"sGvm4PwQUKKlvaHt0IjV5RTuob8IiphlNBTeJmUR34gOZ5arFCL1iz9pB1nj6vMKQrVoS40WvsnCH+BLXeCeBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"578d3d7cb2816f168937f84caee69773fc4db23c8887a909f563c24734382f11","last_reissued_at":"2026-05-17T23:59:37.501682Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:37.501682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.11833","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":"2026-05-17T23:59:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aWakOFAa6L6IT2XSRFheMCgrhwNB1UcmO7ircwZ21+wqZY2UclHWVPQKP/ns3WFwlRFSbin+2SXFFaM+pMIOCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T10:52:28.092672Z"},"content_sha256":"33b834abfbd3c5708bfcaa1910ddd0bb777ce44e277c4dc3fc072585fd8063ac","schema_version":"1.0","event_id":"sha256:33b834abfbd3c5708bfcaa1910ddd0bb777ce44e277c4dc3fc072585fd8063ac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:K6GT27FSQFXRNCJX7BGK5ZUXOP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Task Understanding in Visual Settings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.IR","authors_text":"Emine Yilmaz, Rishabh Mehrotra, Sebastin Santy, Wazeer Zulfikar","submitted_at":"2018-11-28T21:06:27Z","abstract_excerpt":"We consider the problem of understanding real world tasks depicted in visual images. While most existing image captioning methods excel in producing natural language descriptions of visual scenes involving human tasks, there is often the need for an understanding of the exact task being undertaken rather than a literal description of the scene. We leverage insights from real world task understanding systems, and propose a framework composed of convolutional neural networks, and an external hierarchical task ontology to produce task descriptions from input images. Detailed experiments highlight"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.11833","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":"2026-05-17T23:59:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h1rs6HE4JwfeTa8Yhpd5o8azE3EVAImM2rWPcENI8TXjter/KMpJ6rpiAoQ3LiJ9GLUSB9AAnxabWxqCXXN4Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T10:52:28.093297Z"},"content_sha256":"6717048d00fa189727bac5b843957613517328105c686726bedfde3c92fa0b9d","schema_version":"1.0","event_id":"sha256:6717048d00fa189727bac5b843957613517328105c686726bedfde3c92fa0b9d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K6GT27FSQFXRNCJX7BGK5ZUXOP/bundle.json","state_url":"https://pith.science/pith/K6GT27FSQFXRNCJX7BGK5ZUXOP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K6GT27FSQFXRNCJX7BGK5ZUXOP/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":"2026-06-09T10:52:28Z","links":{"resolver":"https://pith.science/pith/K6GT27FSQFXRNCJX7BGK5ZUXOP","bundle":"https://pith.science/pith/K6GT27FSQFXRNCJX7BGK5ZUXOP/bundle.json","state":"https://pith.science/pith/K6GT27FSQFXRNCJX7BGK5ZUXOP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K6GT27FSQFXRNCJX7BGK5ZUXOP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:K6GT27FSQFXRNCJX7BGK5ZUXOP","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":"e04937e4777ed8bbc5a1dc07c18e7b387cc65dfb7ea7c4a4f269235e44fcfc3b","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-11-28T21:06:27Z","title_canon_sha256":"7c71cccd8b33e206dc7b6f859ab117a271d1e4f1ff5d238f598bccd983fe5042"},"schema_version":"1.0","source":{"id":"1811.11833","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.11833","created_at":"2026-05-17T23:59:37Z"},{"alias_kind":"arxiv_version","alias_value":"1811.11833v1","created_at":"2026-05-17T23:59:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.11833","created_at":"2026-05-17T23:59:37Z"},{"alias_kind":"pith_short_12","alias_value":"K6GT27FSQFXR","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"K6GT27FSQFXRNCJX","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"K6GT27FS","created_at":"2026-05-18T12:32:33Z"}],"graph_snapshots":[{"event_id":"sha256:6717048d00fa189727bac5b843957613517328105c686726bedfde3c92fa0b9d","target":"graph","created_at":"2026-05-17T23:59:37Z","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 consider the problem of understanding real world tasks depicted in visual images. While most existing image captioning methods excel in producing natural language descriptions of visual scenes involving human tasks, there is often the need for an understanding of the exact task being undertaken rather than a literal description of the scene. We leverage insights from real world task understanding systems, and propose a framework composed of convolutional neural networks, and an external hierarchical task ontology to produce task descriptions from input images. Detailed experiments highlight","authors_text":"Emine Yilmaz, Rishabh Mehrotra, Sebastin Santy, Wazeer Zulfikar","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-11-28T21:06:27Z","title":"Towards Task Understanding in Visual Settings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.11833","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":"sha256:33b834abfbd3c5708bfcaa1910ddd0bb777ce44e277c4dc3fc072585fd8063ac","target":"record","created_at":"2026-05-17T23:59:37Z","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":"e04937e4777ed8bbc5a1dc07c18e7b387cc65dfb7ea7c4a4f269235e44fcfc3b","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-11-28T21:06:27Z","title_canon_sha256":"7c71cccd8b33e206dc7b6f859ab117a271d1e4f1ff5d238f598bccd983fe5042"},"schema_version":"1.0","source":{"id":"1811.11833","kind":"arxiv","version":1}},"canonical_sha256":"578d3d7cb2816f168937f84caee69773fc4db23c8887a909f563c24734382f11","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"578d3d7cb2816f168937f84caee69773fc4db23c8887a909f563c24734382f11","first_computed_at":"2026-05-17T23:59:37.501682Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:59:37.501682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sGvm4PwQUKKlvaHt0IjV5RTuob8IiphlNBTeJmUR34gOZ5arFCL1iz9pB1nj6vMKQrVoS40WvsnCH+BLXeCeBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:59:37.502517Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.11833","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:33b834abfbd3c5708bfcaa1910ddd0bb777ce44e277c4dc3fc072585fd8063ac","sha256:6717048d00fa189727bac5b843957613517328105c686726bedfde3c92fa0b9d"],"state_sha256":"9922005fc454e528cc97e02e1db4972c60e72e66d1d992600c10a11475755a5a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ytLocdg1WxfDoy2E6wZ7nbq7ti/TiSi7ILxP3PJ3tPWbWyl6VAmHYIZaxCAM5s59r3lfldrd3YYA9MMYgPfHCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T10:52:28.096454Z","bundle_sha256":"2b4a4b5b4f8d7e7c631aa7c3eb0140f32b03638a9c738ebad6f7ebaf40a76ce8"}}