{"as_of":"2026-08-08T11:03:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:91813853debb67468bcc943a927d0bd92fef433de5a61684b3d9228058b2e0eb","coverage":[{"denominator":300,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-31T23:06:37.385242Z","state":"measured"},{"denominator":100,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":100,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2607.24082/citation-record","integrity":"/paper/2607.24082/integrity","json":"/paper/2607.24082/citation-record.json","paper":"/paper/2607.24082"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:28.573184Z","title":"Gradient-based learning applied to document recognition,","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:28.573184Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:e5d34f90565cb0f382082904efad6d51fdc1cc86087ae0e7c798a15f93d59e0c","observation_id":"c9dbf4e7-24ee-4d7a-aa83-4a5f291a8700","resolution":{"observed_at":"2026-07-31T23:06:28.573184Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:28.691830Z","title":"Maximum mutual information estimation of hidden markov model parameters for speech recognition,","venue":null,"work_id":null,"year":1986},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:28.691830Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:6427e562c186ae85e591c10cf01a7624206ed85b1df0afd920cd0ffc0d9866a1","observation_id":"277b4b36-ff9a-4673-bf91-e13216573f6a","resolution":{"observed_at":"2026-07-31T23:06:28.691830Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:28.832158Z","title":"A neural proba- bilistic language model,","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:28.832158Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:630342227e0c8209d01f12748e96ad69a31fb5c3ffde46502a090f54ac3278e4","observation_id":"4f767e4f-d11b-4301-897d-15e23c3239c8","resolution":{"observed_at":"2026-07-31T23:06:28.832158Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:28.966759Z","title":"A mathematical theory of communication,","venue":null,"work_id":null,"year":1948},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:28.966759Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:83fb782cea2b9edf26e25398c9c103c8a061cf0b1fe7ad6e011071e0409d3e16","observation_id":"f7a9f3f9-9800-40dc-973f-eebc42012e6b","resolution":{"observed_at":"2026-07-31T23:06:28.966759Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:29.098012Z","title":"Recent contributions to the mathematical theory of com- munication,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:29.098012Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:f3a3eb7ce7bdaeac6758069872af633a6d377da71063a1a097f5b5a71579ce04","observation_id":"b6daf291-9625-46af-9005-e940d9462a7b","resolution":{"observed_at":"2026-07-31T23:06:29.098012Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:29.186347Z","title":"Tomasello, m., constructing a language: a usage-based theory of language acquisition. cambridge, ma: Harvard university press, 2003. pp. 388. hardback, £29.95. isbn 0-674-01030-2","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:29.186347Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:a9fda5d8f43e98a46a5469e9655c3ba5e8bd6aa9be1a6cf381791de3944d42f1","observation_id":"0d95b4fa-0c97-42b1-b299-bc974555fb1f","resolution":{"observed_at":"2026-07-31T23:06:29.186347Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:29.316994Z","title":"Bloom,How children learn the meanings of words","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:29.316994Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:344d8738ccd7f2532a0750dae245d295a41be150d0daa93c6d8c960fde89ecae","observation_id":"effa41a4-e5d6-468f-9b4b-46f6a0638b29","resolution":{"observed_at":"2026-07-31T23:06:29.316994Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:29.427300Z","title":"Winner,The point of words: Children’s understanding of metaphor and irony","venue":null,"work_id":null,"year":1988},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:29.427300Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:0148874510bb084ea94a362289a84c401dc875445d4937e226895d6929b299b6","observation_id":"8fc23331-8827-4904-8f8a-812c777e832e","resolution":{"observed_at":"2026-07-31T23:06:29.427300Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:29.558116Z","title":"Playing with expectations: A contextual view of humor development,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:29.558116Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:6a98d87ad7bd1f977a186355b70ee1f7461d815fba01b15bf2fded58353e9dd8","observation_id":"0fe8661a-9d9e-4755-86ec-62e220344f13","resolution":{"observed_at":"2026-07-31T23:06:29.558116Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:29.703709Z","title":"Empathy and moral development,","venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:29.703709Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:637c7e8bbe3264d30fbd66a1ee2b5c1ffe16917010492e00dbc4d5c7f5d6828b","observation_id":"c4b2530b-16b1-4d61-a5c5-b60a8369c50b","resolution":{"observed_at":"2026-07-31T23:06:29.703709Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:29.810371Z","title":null,"venue":null,"work_id":null,"year":1990},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:29.810371Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:179bd0e9ff7bf555e5f4050d29ce5893cbd56d67d854a0e623c26805b3c73d6f","observation_id":"11579ff6-2d39-49e6-8109-560d894adea6","resolution":{"observed_at":"2026-07-31T23:06:29.810371Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:29.954983Z","title":"A theory of argumentative understand- ing: Relationships among position preference, judgments of goodness, memory and reasoning,","venue":null,"work_id":null,"year":1993},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:29.954983Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:3ff11c31ad34f0643c40048a3822fcd5146060759830ef0071751d7b7cf97423","observation_id":"e7dff02f-3df9-4946-a929-e2dc07cb18cb","resolution":{"observed_at":"2026-07-31T23:06:29.954983Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:30.042209Z","title":"Attention is all you need,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:30.042209Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:93706f881294967ff4e2f81d8f00a0c308e8fc31a3533b6dd29a94871d62e708","observation_id":"46138173-0843-4b41-b206-053c9a26c3aa","resolution":{"observed_at":"2026-07-31T23:06:30.042209Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-07T07:30:12.213965Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-07-31T23:06:30.128270Z","title":"Gpt-4 technical report,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:30.128270Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:fe37aa9f3c1ab5997d29353ea54670723bdcdd655655e2b07ad9b6f5b09ebc46","observation_id":"a904af26-84f6-4ccb-b50a-bedd73badcd5","resolution":{"observed_at":"2026-07-31T23:06:30.128270Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:30.276790Z","title":null,"venue":null,"work_id":null,"year":1984},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:30.276790Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:447c274533362f1dd17768c2f4c24a84d27eed5a0721b1869d08893936a8b923","observation_id":"c4c9fdf6-7d02-48cc-95de-9444ddf7d195","resolution":{"observed_at":"2026-07-31T23:06:30.276790Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:30.357579Z","title":"Imagenet classification with deep convolutional neural networks,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:30.357579Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:889820152a430ec2739c86d24296c21f665bf184cee748731ce211dc2be01351","observation_id":"00cad60f-9a13-48f7-b71e-a3f5db9cd6d9","resolution":{"observed_at":"2026-07-31T23:06:30.357579Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.5567","last_updated":"2014-12-19T21:36:13Z","snapshot_observed_at":"2026-07-06T04:03:56.251710Z","submitted_at":"2014-12-17T20:39:45Z","title":"Deep Speech: Scaling up end-to-end speech recognition","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.5567","snapshot_observed_at":"2026-07-31T23:06:30.462774Z","title":"Deep speech: Scaling up end-to-end speech recognition,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:30.462774Z"},"links":{"cited_paper":"/paper/1412.5567","citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:a39f71b77bbf6334be685cb75d3c3d33dd031aa5a40d2d5996115e7f72a1fec1","observation_id":"3104b090-de81-49f1-8ca1-699f4617a492","resolution":{"observed_at":"2026-07-31T23:06:30.462774Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:30.477804Z","title":"Rich feature hierarchies for accurate object detection and semantic segmentation,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:30.477804Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:3525220d70c33630effdcd9ed305300ad1307394b45448fecc96aa6a67781efa","observation_id":"928c392d-fe3f-40ac-81ec-997add166cd1","resolution":{"observed_at":"2026-07-31T23:06:30.477804Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:30.530520Z","title":"Bert: Pre- training of deep bidirectional transformers for language understanding,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:30.530520Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:198fe2d59c4d5496fe46cf13256be4bcac7040428aa34dafba9b1087f8b835f1","observation_id":"0cbb4655-294c-4f76-ab39-894da77598c2","resolution":{"observed_at":"2026-07-31T23:06:30.530520Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:30.706861Z","title":"Improving language understanding by generative pre-training,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:30.706861Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:4945b70da753438d6ab4fd2d50bf87a05add8dd532618af75f80aae7157ed65f","observation_id":"b4ba6c4b-d773-499f-9dd1-ab5c9518ae36","resolution":{"observed_at":"2026-07-31T23:06:30.706861Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:30.770963Z","title":"Learning transferable visual models from natural language supervision,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:30.770963Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:a03a00156cfa58d307621aca6ea1392ba09d255768cea595704882a9d61cff8b","observation_id":"7bd113ba-c834-4249-ba97-5d22db8a511a","resolution":{"observed_at":"2026-07-31T23:06:30.770963Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:30.863676Z","title":"Videobert: A joint model for video and language representation learning,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:30.863676Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:4443e8de4a9303e0ed690c2c6289052dfe42dc53c1f25fb5424db6a7752736ed","observation_id":"b2732a47-decb-4477-9ef6-f9560f2bcbc2","resolution":{"observed_at":"2026-07-31T23:06:30.863676Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:30.953321Z","title":"Vatt: Transformers for multimodal self-supervised learning from raw video, audio and text,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:30.953321Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:934a23aef4955d342780974fc98b858bbd9ec57b5d162ac78c5d8ab80c72f999","observation_id":"a3563a00-2af3-41db-83c8-78a612a85554","resolution":{"observed_at":"2026-07-31T23:06:30.953321Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:31.041414Z","title":"Flamingo: a visual language model for few-shot learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:31.041414Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:2ceb5322d36f316df7c69297f31fe8af4858637adf4f24a2a89ac0a9b162970d","observation_id":"a1ccc038-e140-4a5d-ba83-bdb289b0e9d7","resolution":{"observed_at":"2026-07-31T23:06:31.041414Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:31.156462Z","title":"Visual instruction tuning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:31.156462Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:51f3ce28e3bf3076b8553ea2934791722effc7381b0914e3670a9edaf46d735d","observation_id":"227abffd-85bc-442c-af1a-56e11183fe7b","resolution":{"observed_at":"2026-07-31T23:06:31.156462Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:31.245329Z","title":"Paper review:’sparks of artificial general intelligence: Early experiments with gpt-4’,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:31.245329Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:29be375e2a6d4475d6174c33e13e1c53b9c49f7e5edd0f6fa030acf8c5d2088a","observation_id":"bdf2401d-0bae-4434-8723-ee804d79e213","resolution":{"observed_at":"2026-07-31T23:06:31.245329Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.20404","last_updated":"2024-12-29T08:52:49Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-29T08:52:49Z","title":"Open-Sora: Democratizing Efficient Video Production for All","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.20404","snapshot_observed_at":"2026-07-31T23:06:31.331270Z","title":"Open-sora: Democratizing efficient video production for all,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:31.331270Z"},"links":{"cited_paper":"/paper/2412.20404","citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:fced48ab7604f013a419fde9c2dfca8d4d111440d23c90f007fb4f8dc4904d08","observation_id":"9f58d57a-6b6f-48a1-a874-a0317d22e96b","resolution":{"observed_at":"2026-07-31T23:06:31.331270Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2604.14148","last_updated":"2026-04-15T17:59:40Z","snapshot_observed_at":"2026-07-06T23:02:00.082783Z","submitted_at":"2026-04-15T17:59:40Z","title":"Seedance 2.0: Advancing Video Generation for World Complexity","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2604.14148","snapshot_observed_at":"2026-07-31T23:06:31.421381Z","title":"Seedance 2.0: Advancing video generation for world complexity,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:31.421381Z"},"links":{"cited_paper":"/paper/2604.14148","citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:8685adb8cd59ecd57e49302ae8b6232185eae4f662980c36df5673d3ef589845","observation_id":"d955b80b-f486-48e3-acf0-ca160cbe39d3","resolution":{"observed_at":"2026-07-31T23:06:31.421381Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.07959","last_updated":"2025-08-11T13:10:44Z","snapshot_observed_at":"2026-08-05T21:46:17.718649Z","submitted_at":"2025-08-11T13:10:44Z","title":"Large Language Models for Subjective Language Understanding: A Survey","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.07959","snapshot_observed_at":"2026-07-31T23:06:31.514825Z","title":"Large lan- guage models for subjective language understanding: A survey,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:31.514825Z"},"links":{"cited_paper":"/paper/2508.07959","citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:b9b1bd594ed540e1c202b012b9dd47ba27bd61e1ac9a623016b403f6dbe0bdcd","observation_id":"5fae12f0-f3d3-4963-b8b0-dd825f988f28","resolution":{"observed_at":"2026-07-31T23:06:31.514825Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1007/s11263-026-02784-5","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Looking beyond the obvious: A survey on abstract concept recognition for video understanding: Looking beyond the obvious: A survey on abstract concept","venue":"International Journal of Computer Vision","work_id":"2ed0c0de-cc0c-4424-a239-93729a537a1e","year":2026},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:31.587129Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:daf800bfd0accb9feac6672b98d1bb80debc113bfa512f1e4eeac8d91a8eb45f","observation_id":"c4d687b6-65c2-4a26-936a-71fc7a780dcc","resolution":{"observed_at":"2026-07-31T23:11:04.457232Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:31.696978Z","title":"Class-basedn-gram models of natural language,","venue":null,"work_id":null,"year":1992},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:31.696978Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:e0c69d17b869b0c25ad383eaa9e7ea76c71fe32d634ff20c93b1e60917938431","observation_id":"1307bb32-fcb1-4321-bedf-b4e72a97d1d0","resolution":{"observed_at":"2026-07-31T23:06:31.696978Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1301.3781","last_updated":"2013-09-07T00:30:40Z","snapshot_observed_at":"2026-07-06T03:04:11.148340Z","submitted_at":"2013-01-16T18:24:43Z","title":"Efficient Estimation of Word Representations in Vector Space","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1301.3781","snapshot_observed_at":"2026-07-31T23:06:31.794371Z","title":"Efficient estimation of word representations in vector space,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:31.794371Z"},"links":{"cited_paper":"/paper/1301.3781","citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:9e6c0285471bbd9511931031512b594bc2af041a639645aa7fee9c0a9c6a7c08","observation_id":"79590d0a-8b98-4a74-a929-1ec99a1f9b16","resolution":{"observed_at":"2026-07-31T23:06:31.794371Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:31.879655Z","title":"Introduction to the CoNLL-2003 shared task: Language-independent named entity recognition,","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:31.879655Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:56dbd9cc960109a291718987cb9090de59caeed6e6c14d8831835aa81a519bd5","observation_id":"a0d7cb64-58a4-45f8-b40a-dc16ebac3bc8","resolution":{"observed_at":"2026-07-31T23:06:31.879655Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:31.976760Z","title":"Message Understanding Conference- 6: A brief history,","venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:31.976760Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:191db8e9262fe859ae2b839d2976f9fcb783b48a15da8786085ef76662342c44","observation_id":"4a5235a3-f421-40bd-8ee3-fa095d196007","resolution":{"observed_at":"2026-07-31T23:06:31.976760Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:32.073526Z","title":"Statistical phrase-based transla- tion,","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:32.073526Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:3440a2ce7098cc8ac9a9ec3be4acaf447df190c00c5df80fae5455196703db85","observation_id":"413c8121-df07-427d-9a08-3c82ff00fd51","resolution":{"observed_at":"2026-07-31T23:06:32.073526Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1409.0473","last_updated":"2016-05-19T21:53:22Z","snapshot_observed_at":"2026-07-06T03:53:10.336430Z","submitted_at":"2014-09-01T16:33:02Z","title":"Neural Machine Translation by Jointly Learning to Align and Translate","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.0473","snapshot_observed_at":"2026-07-31T23:06:32.172809Z","title":"Neural machine translation by jointly learning to align and translate,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:32.172809Z"},"links":{"cited_paper":"/paper/1409.0473","citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:13469e6f1b2cc0cde0e8bed00fd326416097c06427086a45385113f6d549d977","observation_id":"ee6d6a85-ba6b-40fb-ad70-1f43d5f64ccb","resolution":{"observed_at":"2026-07-31T23:06:32.172809Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:32.296847Z","title":"SQuAD: 100,000+ questions for machine comprehension of text,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:32.296847Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:4c45ed0195fe4763435b24c432ba113db1be53f2f1bda5950f30dbbce7deb2fb","observation_id":"6e419b96-0bbe-43cb-a51c-995757b8575d","resolution":{"observed_at":"2026-07-31T23:06:32.296847Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:32.364148Z","title":"A neural attention model for abstractive sentence summarization,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:32.364148Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:8adea5a79cf2ed5fb1f4fa187d516c906a057f20b45ab2231ad8c88a60abfb84","observation_id":"7e805a8f-c91f-44a4-be07-7280d3cb8fc0","resolution":{"observed_at":"2026-07-31T23:06:32.364148Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:32.475164Z","title":"Automatically constructing a corpus of sentential paraphrases,","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:32.475164Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:9503a88d8b9778c7c231e6bf7be546797c654b3aa73b567e6d16f2494c4c1578","observation_id":"3a319a71-fbed-4d7d-ac3a-42897f593d68","resolution":{"observed_at":"2026-07-31T23:06:32.475164Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:32.548817Z","title":"Imagenet: A large-scale hierarchical image database,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:32.548817Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:14dece356ecb9367f6b10fdf95367e284475e18eba32dd510843963d6cf1eb0a","observation_id":"1f8aabab-8942-4c5d-a1d3-5512271d77dd","resolution":{"observed_at":"2026-07-31T23:06:32.548817Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:32.621605Z","title":"Faster r-cnn: Towards real-time object detection with region proposal networks,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:32.621605Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:9c75df2297e65d6e0e69adeca5e6125dbc54ca59f5c05857a9af1f4a2cc69564","observation_id":"bd1f18a0-d79b-46fc-9085-e07b62ce1e96","resolution":{"observed_at":"2026-07-31T23:06:32.621605Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:32.719957Z","title":"Fully convolutional networks for semantic segmentation,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:32.719957Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:5b9ff462f7e8a622c6acc81cbafea120deee3e83706549598ee64a8eb3ced389","observation_id":"e6403cc5-991f-4b13-b5a3-60a210352a57","resolution":{"observed_at":"2026-07-31T23:06:32.719957Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:32.806551Z","title":"Mask r-cnn,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:32.806551Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:cb7150fe8a521c053d89d4430a4b86a7cb7d30bc6a7e54df09b0b3a92a7d2786","observation_id":"2199ee92-9810-417d-94dc-4355ee9e969f","resolution":{"observed_at":"2026-07-31T23:06:32.806551Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:32.867666Z","title":"Realtime multi-person 2d pose estimation using part affinity fields,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:32.867666Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:c892059b3809d3f58c76932924486fefb87aadd167c935028a54efbff197bd41","observation_id":"62af743d-8d33-4ef1-9a5c-3678afa64d23","resolution":{"observed_at":"2026-07-31T23:06:32.867666Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:32.919777Z","title":"State of the art in example-based texture synthesis,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:32.919777Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:ab0679ac0efbf1c9754ced05d1bc456ae3ccccad239f68a782c3a26c4c24632d","observation_id":"7b31c8c3-c5fe-4478-9499-e1625117d295","resolution":{"observed_at":"2026-07-31T23:06:32.919777Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:32.971653Z","title":"Texture synthesis using convo- lutional neural networks,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:32.971653Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:130830fb20bc09c9f182d8d729385e1eccbdbbb90bee5d6152b3c90007e2ccb9","observation_id":"dc3d3bc2-61fe-4e54-a453-587d0f4597f6","resolution":{"observed_at":"2026-07-31T23:06:32.971653Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:33.030371Z","title":"Globally and locally consistent image completion,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:33.030371Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:c459746c623e01103b33b9d3ba544a43ec02fbdf707723f1a8cb3a07539e9b18","observation_id":"e4ab2440-6e4a-48d2-b81f-99cf3cbdc149","resolution":{"observed_at":"2026-07-31T23:06:33.030371Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:33.110339Z","title":"Image completion with structure propagation,","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:33.110339Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:0f04ba48fddc15e30e6b134c1e188f46594a67b93ee0b4855ceb1e8f0220d62e","observation_id":"64046091-f4c5-4bc0-93e5-6eb8697f53cb","resolution":{"observed_at":"2026-07-31T23:06:33.110339Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1312.6114","last_updated":"2022-12-10T21:04:00Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2013-12-20T20:58:10Z","title":"Auto-Encoding Variational Bayes","version":11},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1312.6114","snapshot_observed_at":"2026-07-31T23:06:33.194516Z","title":"Auto-encoding variational bayes,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:33.194516Z"},"links":{"cited_paper":"/paper/1312.6114","citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:a6ae6441db84ac1cfa0a082eb2fff854f6a2450b577dabbf8b9795c43b44d78e","observation_id":"1bc2ebca-08c3-4d1b-8c98-6814baa382d1","resolution":{"observed_at":"2026-07-31T23:06:33.194516Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:33.256343Z","title":"Generative adversarial nets,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:33.256343Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:8565dc823a836cdfc51a6c163053b8f1a92f03913565907c4ecf7cb0683347e9","observation_id":"ad12e4e9-2258-44b0-8b71-5eea30f1ffbf","resolution":{"observed_at":"2026-07-31T23:06:33.256343Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:33.327229Z","title":"A tutorial on hidden markov models and selected applica- tions in speech recognition,","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:33.327229Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:6a340894294df5d377072ca98a6b0a4f95857972afa9ee873ddca29dfaadb69f","observation_id":"9214cdf4-da90-460c-aa13-7af33848dd41","resolution":{"observed_at":"2026-07-31T23:06:33.327229Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:33.393998Z","title":"Suppression of acoustic noise in speech using spectral subtraction,","venue":null,"work_id":null,"year":1979},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:33.393998Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:f979a493e5a1c048e8ab52f861abde07ed8aedc9143e405f603c8ffd1a6772d0","observation_id":"0c3b3de3-8f17-4a2a-b09b-462a206cf96f","resolution":{"observed_at":"2026-07-31T23:06:33.393998Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:33.472024Z","title":"Listen, attend and spell: A neural network for large vocabulary conversational speech recognition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:33.472024Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:0aeca6a6c320d94fc759d7bc2f9a8dd713f265ab10a29fded49059abe11012e0","observation_id":"c1028e37-d303-4665-a28c-d471d74a58d6","resolution":{"observed_at":"2026-07-31T23:06:33.472024Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:33.536571Z","title":"X-vectors: Robust dnn embeddings for speaker recognition,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:33.536571Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:0fd2b2f2d572a62161969c9f770172afd90cae8be8bc78baa85ad6d568548d3b","observation_id":"f9409aec-605c-46f2-b336-d91929c4c27f","resolution":{"observed_at":"2026-07-31T23:06:33.536571Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:33.587382Z","title":"Emotional speech synthesis: a review","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:33.587382Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:a51cc79bc96f0ab96a6240b04c3bad07e0863781013b5958822d7fe1bed99cf0","observation_id":"2746ebbc-5dcb-4bfc-b447-f26f1fec4552","resolution":{"observed_at":"2026-07-31T23:06:33.587382Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:33.651302Z","title":"Speech parameter generation algorithms for hmm-based speech syn- thesis,","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:33.651302Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:36fecbf1455ea05d22edd5709eeabf2f35d3d05d6e1ceb09cd75ed62f4314644","observation_id":"c9cb962b-8cac-458b-9b25-f622f43f293d","resolution":{"observed_at":"2026-07-31T23:06:33.651302Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1609.03499","last_updated":"2016-09-19T18:04:35Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2016-09-12T17:29:40Z","title":"WaveNet: A Generative Model for Raw Audio","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.03499","snapshot_observed_at":"2026-07-31T23:06:33.716266Z","title":"Wavenet: A generative model for raw audio,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:33.716266Z"},"links":{"cited_paper":"/paper/1609.03499","citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:7f0992bdfd6811fb92c235af3995efebe2b8a7ccb54192cadd2081c5a923d27c","observation_id":"39f61dc7-5d07-475f-aa57-f2e649c54e3a","resolution":{"observed_at":"2026-07-31T23:06:33.716266Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1703.10135","last_updated":"2017-04-06T21:20:34Z","snapshot_observed_at":"2026-08-05T15:51:16.043022Z","submitted_at":"2017-03-29T16:55:13Z","title":"Tacotron: Towards End-to-End Speech Synthesis","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1703.10135","snapshot_observed_at":"2026-07-31T23:06:33.805902Z","title":"Tacotron: Towards end- to-end speech synthesis,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:33.805902Z"},"links":{"cited_paper":"/paper/1703.10135","citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:26abc368d07977e68f8b17c718b5f354b493e49ed1cb1d7788d3a2dd54951f37","observation_id":"afeab639-2508-4ab8-a2d6-031aa1a64ec2","resolution":{"observed_at":"2026-07-31T23:06:33.805902Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:33.880024Z","title":"Imagebind: One embedding space to bind them all,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:33.880024Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:ac8e79d23ad5c5988fcff29c1792e1e733ca9c67e3de148e95feb4431f8b03e4","observation_id":"baff9827-f56f-4b08-92e0-d6f2aab8b8de","resolution":{"observed_at":"2026-07-31T23:06:33.880024Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:33.966317Z","title":"Making computers laugh: Inves- tigations in automatic humor recognition,","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:33.966317Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:423b19dd64930b6404c99cd9b675eaf14eb8aa87a289d8bd1c617375b6890772","observation_id":"919a19ec-a234-4373-9f59-d69b6a68a314","resolution":{"observed_at":"2026-07-31T23:06:33.966317Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:34.053367Z","title":"SemEval-2017 task 6: #HashtagWars: Learning a sense of humor,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:34.053367Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:15deb611744b9049a68a4fa834dca956b3b3dc6f44d59705a25bd030a74aba2b","observation_id":"159c79ca-cace-44e9-89bd-253bd688004e","resolution":{"observed_at":"2026-07-31T23:06:34.053367Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:34.115433Z","title":"“president vows to cut <taxes>hair","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:34.115433Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:1758e9cfbf4cdbe691f38a59af3b4771c6baffa8f863f61305829f91b1cfff88","observation_id":"68b9667d-5af5-47ff-b3a7-e7d891538bfe","resolution":{"observed_at":"2026-07-31T23:06:34.115433Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:34.174724Z","title":"Cards against AI: Predicting humor in a fill-in-the-blank party game,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:34.174724Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:3108d790bb050823d6ef142d88e5c0b1395329540e79336d345e5a5069822473","observation_id":"305266ba-c71b-4ebb-87dd-c4ffa7e17788","resolution":{"observed_at":"2026-07-31T23:06:34.174724Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:34.249972Z","title":"Can language models make fun? a case study in Chinese comical crosstalk,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:34.249972Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:4fbf47f33fa7379a593796e1da0f19f01804da79c81d23d51317bf615a1ebc02","observation_id":"b71c99e6-d06e-453e-8087-9d3b124a3b12","resolution":{"observed_at":"2026-07-31T23:06:34.249972Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:34.309983Z","title":"Talk funny! a large-scale humor response dataset with chain-of-humor interpretation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:34.309983Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:044fbb8c3c309ac83afc9777cd1897bbb1a3f4f7ea9a46b955ceaf27c55c8522","observation_id":"35c7fe66-76c9-4fe4-bddd-c1e67757d913","resolution":{"observed_at":"2026-07-31T23:06:34.309983Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:34.371935Z","title":"Chumor 2.0: Towards better benchmarking Chinese humor understanding from (ruo zhi ba),","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:34.371935Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:b0ac211188e4d827292b269b7ae7e18b689c56209b8305570bda1a20f0750fa9","observation_id":"50b18314-261b-4e85-b334-d47d3322c0e2","resolution":{"observed_at":"2026-07-31T23:06:34.371935Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:34.431601Z","title":"“what do you call a dog that is incontrovertibly true? dogma","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:34.431601Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:6bb404632af4123e31f10b138793cb18c38efd1f4450e152d0b05cbd02c84297","observation_id":"e8d851df-84cd-419c-85b4-c756a9520918","resolution":{"observed_at":"2026-07-31T23:06:34.431601Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.20417","last_updated":"2025-03-26T10:44:51Z","snapshot_observed_at":"2026-08-07T16:35:55.358678Z","submitted_at":"2025-03-26T10:44:51Z","title":"CFunModel: A \"Funny\" Language Model Capable of Chinese Humor Generation and Processing","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.20417","snapshot_observed_at":"2026-07-31T23:06:34.482030Z","title":"Cfunmodel: A","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:34.482030Z"},"links":{"cited_paper":"/paper/2503.20417","citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:2b7398b43872a667ab3e79dc7f708cebaecf6877207cdae0fbe4e6c1138299fb","observation_id":"610de6d9-82ef-440d-9e8f-d58673d5321a","resolution":{"observed_at":"2026-07-31T23:06:34.482030Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:34.546937Z","title":"Comparing apples to oranges: A dataset & analysis of LLM humour understanding from traditional puns to topical jokes,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:34.546937Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:afe0d0eaa96f96b4955910189268e5ebe8fce09d2bc8e675cd741565055aae80","observation_id":"bd47d40d-06ba-4423-9d20-a7586587ab00","resolution":{"observed_at":"2026-07-31T23:06:34.546937Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:34.605441Z","title":"Drivel-ology: Challenging llms with interpreting nonsense with depth,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:34.605441Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:95c447e17d9a15b7740df046524fcbde628b51c7519d1850cfa95161abfc8170","observation_id":"78597be5-6c6c-4f82-b82f-9a115fe42f2d","resolution":{"observed_at":"2026-07-31T23:06:34.605441Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:34.681857Z","title":"Do androids laugh at electric sheep? humor “understanding","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:34.681857Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:2b53b5a8f4597b052bc012639716d5d2e5ea8109118b8de7fe4aabb7a83c7da5","observation_id":"52aa0cf0-0349-421f-9b61-637bea711db0","resolution":{"observed_at":"2026-07-31T23:06:34.681857Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:34.763346Z","title":"Humor in ai: Massive scale crowd-sourced preferences and benchmarks for cartoon caption- ing,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:34.763346Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:64b3125aaa9700e85a57cb2e0ce95f5b3e129aaa6f02d1839ba435fff89a42e7","observation_id":"808e1485-99cd-4601-9c71-21dcc37af998","resolution":{"observed_at":"2026-07-31T23:06:34.763346Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:34.821481Z","title":"Let’s think outside the box: Exploring leap-of-thought in large language models with creative humor generation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:34.821481Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:b5535fe51311be5627318c1a4400c918593134508c2ffbee8c795f4f8039e78e","observation_id":"acdd9115-4cbf-4e90-9112-a6db2828ffc3","resolution":{"observed_at":"2026-07-31T23:06:34.821481Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:34.880914Z","title":"Cracking the code of juxtaposition: can ai models understand the humorous contradictions,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:34.880914Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:6608fa416775cd35975e9f4992114607a5094a3c26eb92e29f8ac3410b50b686","observation_id":"8f675ebd-bacf-4076-a88b-b3e7fc2d41aa","resolution":{"observed_at":"2026-07-31T23:06:34.880914Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:34.937397Z","title":"Visionarena: 230k real world user-vlm conversations with preference labels,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:34.937397Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:30a5fc89f067227d83a93ee34152f4ba4620838a7506891b1b20ac47efe06639","observation_id":"caad345d-e85e-43e2-8898-70996b93f245","resolution":{"observed_at":"2026-07-31T23:06:34.937397Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:35.018626Z","title":"D-humor: Dark humor understanding via multimodal open-ended reasoning,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:35.018626Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:1c0c9280077c3e578910feea17957e3aa70f340a83bd2f57305a8e392d1d8bb4","observation_id":"bdaa9010-a4a9-4ab6-98c1-98bdc1f8a664","resolution":{"observed_at":"2026-07-31T23:06:35.018626Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:35.100649Z","title":"Humor in pixels: Benchmarking large multimodal models understanding of online comics,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:35.100649Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:cb604795ad9a0ce872893164822472142a39e4b52b5cfe9bba2083aec6ea53ae","observation_id":"2614ce19-b2fc-45e1-82d1-f9f2fea1f840","resolution":{"observed_at":"2026-07-31T23:06:35.100649Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:35.183291Z","title":"HumorDB: Can AI understand graphical humor?","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:35.183291Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:8919c925a71c7a84919cf029363e895ae242b1bb1aae197f3750ab389c691624","observation_id":"39fb7113-e84b-437c-8b09-102e6571cd02","resolution":{"observed_at":"2026-07-31T23:06:35.183291Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2509.25773","last_updated":"2026-06-01T11:57:22Z","snapshot_observed_at":"2026-08-04T13:42:19.588845Z","submitted_at":"2025-09-30T04:33:52Z","title":"v-HUB: A Benchmark for Video Humor Understanding from Vision and Sound","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2509.25773","snapshot_observed_at":"2026-07-31T23:06:35.266094Z","title":"V-hub: A visual-centric humor understanding benchmark for video llms,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:35.266094Z"},"links":{"cited_paper":"/paper/2509.25773","citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:0af02a2d1faeabe2c0cf0b089c6f0ad5fd8a60d3279e9c27c9c2bcef2292f6d4","observation_id":"90d46e73-f65f-4287-9a63-b1f806f9562b","resolution":{"observed_at":"2026-07-31T23:06:35.266094Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:35.348822Z","title":"GODBench: A benchmark for multimodal large language models in video comment art,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:35.348822Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:6850a78adbbc38ced833c778e06664dfdf9ee6f9d22aa42f207c6d6c7edce3f0","observation_id":"35b70e3b-3beb-41e7-a262-b9ccc3704dbe","resolution":{"observed_at":"2026-07-31T23:06:35.348822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:35.430693Z","title":"Can language models laugh at YouTube short-form videos?","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:35.430693Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:07b08d6c5fd11a9f2be467f1b74e5c3b723652c897dbfc175d16019a2a7d9dcb","observation_id":"661b1361-e493-4d14-a56e-de3aeae4dd1e","resolution":{"observed_at":"2026-07-31T23:06:35.430693Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:35.512237Z","title":"Towards multimodal prediction of spontaneous humor: A novel dataset and first results,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:35.512237Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:2577965b8d798170777a1e59ec3b87a0f1e431b3c59a6e8acce0f9528b42a413","observation_id":"8d6e5538-ea86-4691-95f7-cd87aa6fd35c","resolution":{"observed_at":"2026-07-31T23:06:35.512237Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:35.572711Z","title":"StandUp4AI: A new multilingual dataset for humor detection in stand- up comedy videos,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:35.572711Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:837866af80af8d0509e24d1400ffb32b8370363bde9bd2016761191f85101cd2","observation_id":"60bb9a9a-63cb-4c1b-8848-c609f3b83b68","resolution":{"observed_at":"2026-07-31T23:06:35.572711Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:35.663927Z","title":"Testing the ability of language models to interpret figurative language,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:35.663927Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:e338e89b9ba125dcb856e0673775f2d0f545651a92b05150db0c2e228e0246b4","observation_id":"488a3b9f-d733-4bb7-a581-58ab3c50c60c","resolution":{"observed_at":"2026-07-31T23:06:35.663927Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:35.755355Z","title":"FLUTE: Figurative language understanding through textual explanations,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:35.755355Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:7d9811d6be7614cbfb6401e1e1420cb7e03350fb4b2f7f99267c45bd575cc99a","observation_id":"10ca347e-1071-400c-a02d-55e412870542","resolution":{"observed_at":"2026-07-31T23:06:35.755355Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:35.816252Z","title":"Chinese metaphorical relation extraction,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:35.816252Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:bb7d67ef18984f1fc5fc40c432b2a1ce9b903042d63bfc018e010463feff7465","observation_id":"c5527058-faf0-453d-adef-df0a931313f6","resolution":{"observed_at":"2026-07-31T23:06:35.816252Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:35.874739Z","title":"Chinese idiom paraphrasing,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:35.874739Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:fd5ad85f39eca73c124e831faf44b90a81e3bb7aab8c4c594e879b022cbe1197","observation_id":"767c08dd-8744-4c23-92d4-e7bb3f96e13f","resolution":{"observed_at":"2026-07-31T23:06:35.874739Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:35.965548Z","title":"Multi-lingual and multi- cultural figurative language understanding,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:35.965548Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:80d16b417dd458f70cf049b455c6ece54c78af27dce4b610cf891ca3da8613f5","observation_id":"31c096cf-b288-4e21-984f-162548a1cd0a","resolution":{"observed_at":"2026-07-31T23:06:35.965548Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:36.066097Z","title":"NewsMet : A ‘do it all’ dataset of contemporary metaphors in news headlines,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:36.066097Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:dbd7c9004cc821806be8a5e15a596295c0427b94f43915a2df3af2b51f24ee4a","observation_id":"dd8dc4c2-bda0-472d-becf-2c92d0e02bca","resolution":{"observed_at":"2026-07-31T23:06:36.066097Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:36.141789Z","title":"MMTE: Corpus and metrics for evaluating machine translation quality of metaphorical language,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:36.141789Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:cf895a43e415f22877dbf09a1ac7c55b3aed073f2b173f212ae37505f2fd7647","observation_id":"d1ce41c0-b2d7-4b92-814b-d2c9767bf286","resolution":{"observed_at":"2026-07-31T23:06:36.141789Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:36.211900Z","title":"MetaPro 2.0: Computational metaphor processing on the effectiveness of anomalous language modeling,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:36.211900Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:bb3257a72cec5c4b82361863fdb2fb657dc0fefe5bc47a1ca9db9c4fe251d988","observation_id":"58903f20-7d71-4966-b280-ccc1524cbc57","resolution":{"observed_at":"2026-07-31T23:06:36.211900Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:36.259854Z","title":"Metaphor understanding challenge dataset for LLMs,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:36.259854Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:6831fec7548e8238d6399daecef20fda6ed1af489dd469b83d3ed57fe38f0170","observation_id":"e523dea2-1dad-4a6f-a847-97bc00785440","resolution":{"observed_at":"2026-07-31T23:06:36.259854Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:36.264933Z","title":"Enhancing information extraction with metorie: A metaphor and trap-based dataset for cross-domain fine-tuning,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:36.264933Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:2ff856dd1867d15eff484fd0bb382e5519ce24ec4976c5f1120857fc4e48e618","observation_id":"82947df9-a48b-4f7a-b6df-c359868ed67e","resolution":{"observed_at":"2026-07-31T23:06:36.264933Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:36.397469Z","title":"Investigating the impact of conceptual metaphors on llm-based nli through shapley interactions,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:36.397469Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:0405b25bd4b909179637358344bfd2950c865c5bb63d4ab7a27e12135bc12454","observation_id":"b00ddf23-56c0-4b48-8257-32ccf097a020","resolution":{"observed_at":"2026-07-31T23:06:36.397469Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:36.585547Z","title":"Automatic extraction of metaphoric analogies from literary texts: Task formulation, dataset construction, and evaluation,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:36.585547Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:63e71f737e896ba1c1184fbf462b203e78ff40ef5ddad1b3683adcce3e1e35bf","observation_id":"8e7146e6-0c20-4716-af17-aa04076eccc1","resolution":{"observed_at":"2026-07-31T23:06:36.585547Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:36.754864Z","title":"Comparative study of multilingual idioms and similes in large language models,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:36.754864Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:98ccd21a537c6b997da360065eca4ffc99a92aaedf1924ed1fe22fd1791da364","observation_id":"e46fe196-905c-406c-bd8e-1f851a995d19","resolution":{"observed_at":"2026-07-31T23:06:36.754864Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:36.923497Z","title":"I spy a metaphor: Large language models and diffusion models co-create visual metaphors,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:36.923497Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:d7292c3526a97b880be113b53eb5181d8ef159682b5679fea28978c05d342052","observation_id":"2d5cc939-e7d2-4469-8325-57a9e0780db6","resolution":{"observed_at":"2026-07-31T23:06:36.923497Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:37.127225Z","title":"MultiCMET: A novel Chinese benchmark for understanding multimodal metaphor,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:37.127225Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:66568b4afc63876a8c4784bde44ba5942a489217dffcd3befdf2eb29dd0a4356","observation_id":"d83e82dd-9bc4-457e-b527-0ace628af36b","resolution":{"observed_at":"2026-07-31T23:06:37.127225Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:37.291198Z","title":"MemeCap: A dataset for captioning and interpreting memes,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:37.291198Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:2fe0d12155644f545ae47395052b5e330e706ce674fb9679da6a0d83c577aeaa","observation_id":"a96ea23c-32a3-406d-ade1-c4192f11c38d","resolution":{"observed_at":"2026-07-31T23:06:37.291198Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T23:06:37.385242Z","title":"Cultural bias matters: A cross-cultural benchmark dataset and sentiment-enriched model for understanding multimodal metaphors,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence","version":1},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-07-31T23:06:37.385242Z"},"links":{"citing_paper":"/paper/2607.24082"},"observation_digest":"sha256:8423b0044cffed52197b74e16bb7bbfc282608c3ff5dfba4a087e959bf0abbca","observation_id":"1e8cbc95-83f4-4227-ba80-88dc0eba9cf8","resolution":{"observed_at":"2026-07-31T23:06:37.385242Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.24082","last_updated":"2026-07-27T07:23:22Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-06T03:54:26.893671Z","submitted_at":"2026-07-27T07:23:22Z","title":"Towards High-Level Semantic Intelligence"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":99,"verified_exact":1,"verified_fuzzy":0},"total_outbound_references":300},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 100 of 300 outbound references and 0 inbound Pith citation observations for arXiv:2607.24082."}