{"as_of":"2026-08-08T09:16:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:84e02b41d071bbf244e24c107d1e9fe48dfa9266acfb2328e0ac058af5661d34","coverage":[{"denominator":102,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T00:58:15.421753Z","state":"measured"},{"denominator":109,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":109,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":9,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":9,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T22:21:09.426211Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":2,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.12479","snapshot_observed_at":"2026-08-06T22:21:09.426211Z","title":"https://arxiv.org/abs/2506.12479 14","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.21853","last_updated":"2025-09-07T09:44:32Z","snapshot_observed_at":"2026-08-07T06:07:44.665917Z","submitted_at":"2025-06-27T02:08:40Z","title":"Skill-Nav: Enhanced Navigation with Versatile Quadrupedal Locomotion via Waypoint Interface","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T22:21:09.426211Z"},"links":{"cited_paper":"/paper/2506.12479","citing_paper":"/paper/2506.21853"},"observation_digest":"sha256:cc5addd7ded76f0f4485e0b39d69bec76b8225b67f49c86d5fa6b67dee12ec14","observation_id":"d92fb929-c2f8-4854-8bfe-5a777bcbb5ec","resolution":{"observed_at":"2026-08-06T22:21:09.426211Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.12479","snapshot_observed_at":"2026-08-06T14:43:22.098290Z","title":"Ai flow: Perspectives, scenarios, and approaches, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.18013","last_updated":"2025-07-29T10:30:18Z","snapshot_observed_at":"2026-08-07T23:55:13.139896Z","submitted_at":"2025-07-24T01:00:48Z","title":"Technical Report of TeleChat2, TeleChat2.5 and T1","version":3},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-06T14:43:22.098290Z"},"links":{"cited_paper":"/paper/2506.12479","citing_paper":"/paper/2507.18013"},"observation_digest":"sha256:f398d2c99e1ddd21fb003b3a18c4836aca758a461eab341f305a32c76e707859","observation_id":"5f8deec3-be83-4e38-9069-182357c66482","resolution":{"observed_at":"2026-08-06T14:43:22.098290Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"cited_work":{"arxiv_id":"2506.12479","doi":"10.48550/arxiv.2506.12479","metadata_source":"arxiv_reference","pith_arxiv_id":"2506.12479","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2506.12479 (2025)","venue":"ArXiv.org","work_id":"42dc61ce-8b4c-425e-80ee-39b5c927c89b","year":2025},"citing_paper":{"arxiv_id":"2605.08729","last_updated":"2026-06-29T11:45:55Z","snapshot_observed_at":"2026-08-01T08:29:29.120570Z","submitted_at":"2026-05-09T06:32:54Z","title":"Unison: Harmonizing Motion, Speech, and Sound for Human-Centric Audio-Video Generation","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-12T02:28:14.734682Z"},"links":{"cited_paper":"/paper/2506.12479","citing_paper":"/paper/2605.08729"},"observation_digest":"sha256:6b3b996fde0aafd8d56a58903be60f26e86028b6aaa8b7e3d1b4bf19eebeb760","observation_id":"74726bfd-03bc-4a3d-b355-81f16a3e9409","resolution":{"observed_at":"2026-05-12T07:36:44.030300Z","resolver_source":"arxiv_id","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":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"cited_work":{"arxiv_id":"2506.12479","doi":"10.48550/arxiv.2506.12479","metadata_source":"arxiv_reference","pith_arxiv_id":"2506.12479","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2506.12479 (2025)","venue":"ArXiv.org","work_id":"42dc61ce-8b4c-425e-80ee-39b5c927c89b","year":2025},"citing_paper":{"arxiv_id":"2605.08729","last_updated":"2026-06-29T11:45:55Z","snapshot_observed_at":"2026-08-01T08:29:29.120570Z","submitted_at":"2026-05-09T06:32:54Z","title":"Unison: Harmonizing Motion, Speech, and Sound for Human-Centric Audio-Video Generation","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-30T23:26:46.077894Z"},"links":{"cited_paper":"/paper/2506.12479","citing_paper":"/paper/2605.08729"},"observation_digest":"sha256:6db5efb7b459c81226b82e39094336144dd74b9f1031a446f89712f1f9e1a1a3","observation_id":"f124ec71-ba9f-4aa1-a7bb-b72510a474fd","resolution":{"observed_at":"2026-06-30T23:35:07.798707Z","resolver_source":"arxiv_id","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":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"cited_work":{"arxiv_id":"2506.12479","doi":"10.48550/arxiv.2506.12479","metadata_source":"arxiv_reference","pith_arxiv_id":"2506.12479","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2506.12479 (2025)","venue":"ArXiv.org","work_id":"42dc61ce-8b4c-425e-80ee-39b5c927c89b","year":2025},"citing_paper":{"arxiv_id":"2606.05911","last_updated":"2026-06-04T09:16:26Z","snapshot_observed_at":"2026-08-06T13:48:13.385785Z","submitted_at":"2026-06-04T09:16:26Z","title":"DBHN-Net: Dual-Branch Hybrid Neural Network For Low-Complexity Monaural Speech Enhancement","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-06-27T23:49:05.871422Z"},"links":{"cited_paper":"/paper/2506.12479","citing_paper":"/paper/2606.05911"},"observation_digest":"sha256:311080b08260d08a03b63db16f1eea7433268ec6de85ae75c7ae3108c714f4e3","observation_id":"3f639b45-7dac-40df-81c5-0932f9096acf","resolution":{"observed_at":"2026-07-02T15:37:06.108421Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"cited_work":{"arxiv_id":"2506.12479","doi":"10.48550/arxiv.2506.12479","metadata_source":"arxiv_reference","pith_arxiv_id":"2506.12479","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2506.12479 (2025)","venue":"ArXiv.org","work_id":"42dc61ce-8b4c-425e-80ee-39b5c927c89b","year":2025},"citing_paper":{"arxiv_id":"2606.08992","last_updated":"2026-06-08T03:42:08Z","snapshot_observed_at":"2026-08-01T21:35:10.152517Z","submitted_at":"2026-06-08T03:42:08Z","title":"SpaceVLN: A Zero-Shot Vision-and-Language Navigation Agent with Online Spatial Cognitive Memory and Reasoning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-06-27T16:49:46.634302Z"},"links":{"cited_paper":"/paper/2506.12479","citing_paper":"/paper/2606.08992"},"observation_digest":"sha256:2ac2a5a5557b06f288c09fb463c8bdcb71a498be7dd1f9452ee39a61d2119784","observation_id":"4d46bc25-db86-419b-90ad-e91fb3e0103f","resolution":{"observed_at":"2026-06-27T16:51:05.508049Z","resolver_source":"arxiv_id","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":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"cited_work":{"arxiv_id":"2506.12479","doi":"10.48550/arxiv.2506.12479","metadata_source":"arxiv_reference","pith_arxiv_id":"2506.12479","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2506.12479 (2025)","venue":"ArXiv.org","work_id":"42dc61ce-8b4c-425e-80ee-39b5c927c89b","year":2025},"citing_paper":{"arxiv_id":"2606.22905","last_updated":"2026-06-30T08:27:33Z","snapshot_observed_at":"2026-08-05T18:57:39.905774Z","submitted_at":"2026-06-22T06:41:17Z","title":"InteractiveAvatar: Real-Time Streaming Video Generation for Consistent and Intent-Aware Avatars","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-26T09:09:06.925645Z"},"links":{"cited_paper":"/paper/2506.12479","citing_paper":"/paper/2606.22905"},"observation_digest":"sha256:ac3f14d38d64cf0235144df9f667ce2f4406995b62ebd97ccc1be10467a39952","observation_id":"457fa5dd-b7a5-450e-837c-31a6d8f6753c","resolution":{"observed_at":"2026-07-04T10:09:44.576001Z","resolver_source":"arxiv_id","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":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"cited_work":{"arxiv_id":"2506.12479","doi":"10.48550/arxiv.2506.12479","metadata_source":"arxiv_reference","pith_arxiv_id":"2506.12479","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2506.12479 (2025)","venue":"ArXiv.org","work_id":"42dc61ce-8b4c-425e-80ee-39b5c927c89b","year":2025},"citing_paper":{"arxiv_id":"2606.22905","last_updated":"2026-06-30T08:27:33Z","snapshot_observed_at":"2026-08-05T18:57:39.905774Z","submitted_at":"2026-06-22T06:41:17Z","title":"InteractiveAvatar: Real-Time Streaming Video Generation for Consistent and Intent-Aware Avatars","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-01T07:00:53.496569Z"},"links":{"cited_paper":"/paper/2506.12479","citing_paper":"/paper/2606.22905"},"observation_digest":"sha256:d83590f39aae7f4e6e36a773b93bb69d3fc0213241c37c1fe29e4a7277287fe7","observation_id":"fd772f35-a873-4a95-9fec-eb6e11bd4f04","resolution":{"observed_at":"2026-07-01T07:05:29.093466Z","resolver_source":"arxiv_id","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":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.12479","snapshot_observed_at":"2026-08-01T03:52:55.335046Z","title":"arXiv preprint arXiv:2506.12479 , year=","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.23023","last_updated":"2026-07-28T02:01:27Z","snapshot_observed_at":"2026-08-06T04:02:53.538330Z","submitted_at":"2026-07-25T03:42:52Z","title":"OmniMate: Open-Ended Real-Time Streaming Audio-Visual Generation for Interactive Avatars","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-01T03:52:55.335046Z"},"links":{"cited_paper":"/paper/2506.12479","citing_paper":"/paper/2607.23023"},"observation_digest":"sha256:790d05419f60141d237789f90d5d343107763b54484339196cc7a92222d05ae1","observation_id":"89f6f0cb-1f9d-4efd-baf7-381e734b4b29","resolution":{"observed_at":"2026-08-01T03:52:55.335046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2506.12479/citation-record","integrity":"/paper/2506.12479/integrity","json":"/paper/2506.12479/citation-record.json","paper":"/paper/2506.12479"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:08.782774Z","title":null,"venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:08.782774Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:2c4da4a95be877636636e6e55e66a031f07242f9e378412485090c791da86fbd","observation_id":"c28d9103-1161-441d-bb09-f16d08a9f3ec","resolution":{"observed_at":"2026-08-07T00:58:08.782774Z","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":"2026-08-07T00:58:08.847076Z","title":"A mathematical theory of communication,","venue":null,"work_id":null,"year":1948},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:08.847076Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:9bf4d71daa14fb7755fe9f27e77c958a78a7361147ee8715287f955ca26b1f4a","observation_id":"770b25a7-99cf-4978-9e2c-9237a05d8c46","resolution":{"observed_at":"2026-08-07T00:58:08.847076Z","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":"2026-08-07T00:58:08.931651Z","title":"A survey on information and communication technologies for industry 4.0: State- of-the-art, taxonomies, perspectives, and challenges,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:08.931651Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:cbb6f6f8cff3543cf85408a523e456d325b65e1f48be9510807921999e5a5473","observation_id":"6b7c4b53-0607-4f56-908e-cec8aa948da5","resolution":{"observed_at":"2026-08-07T00:58:08.931651Z","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":"2026-08-07T00:58:09.016029Z","title":"Language models are few-shot learners,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:09.016029Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:ee01715bb2dc04e46d685adfea92c8d81fd29740c9d6aa7d1bff115606239f2a","observation_id":"08facc0b-36da-4087-b6d8-2f5ad0a492bc","resolution":{"observed_at":"2026-08-07T00:58:09.016029Z","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":"2026-08-07T00:58:09.102570Z","title":"Latva-aho and K","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:09.102570Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:f248733f746e7ca4e5da916a5f7c2871feb43a01a7472629dbb365476d22f3d5","observation_id":"445ee830-fc4a-4b23-844a-fbfcae2922ad","resolution":{"observed_at":"2026-08-07T00:58:09.102570Z","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":"2026-08-07T00:58:09.167426Z","title":"AI flow at the network edge,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:09.167426Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:8f4cd4317962b1617c0ca853996d7f5b782ee0062e79df514f3fbbfd7be79858","observation_id":"f6e97a8c-37a8-431f-8490-60fee4bb1549","resolution":{"observed_at":"2026-08-07T00:58:09.167426Z","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":"2026-08-07T00:58:09.194123Z","title":"A survey on mobile edge computing: The communication perspective,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:09.194123Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:c4a6efdffd106a581f8866671facaf2ecb685acbcc0dae68c4e8a1facd4d4aa2","observation_id":"c3bbb34b-23b7-4987-af4e-850afd881021","resolution":{"observed_at":"2026-08-07T00:58:09.194123Z","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":"2026-08-07T00:58:09.256380Z","title":"Communication-computation trade-off in resource-constrained edge inference,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:09.256380Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:ba724c24f7bfd05bb3abe20809cc258a83765a79e66861d9915dc9b9c8247003","observation_id":"6922a760-87de-4b9e-b550-1e2dd114cf3c","resolution":{"observed_at":"2026-08-07T00:58:09.256380Z","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":"2026-08-07T00:58:09.337541Z","title":"The roadmap to 6G: AI empowered wireless networks,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:09.337541Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:90452096516750c803af6e347ef15524b53403d3b77589a20df5ab709f5b6056","observation_id":"a856debe-fe94-479d-b985-2e386ffbfebf","resolution":{"observed_at":"2026-08-07T00:58:09.337541Z","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":"2026-08-07T00:58:09.486665Z","title":"Edge artificial intelligence for 6G: Vision, enabling technologies, and applications,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:09.486665Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:ab71526a855df5283217bcb3f105bd2b95b1d4a1d339e604fe40686c3c22f7d7","observation_id":"fd463997-e7cb-4588-9195-d7e6e344e0ae","resolution":{"observed_at":"2026-08-07T00:58:09.486665Z","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":"2026-08-07T00:58:09.569997Z","title":"Reconstructive sequence-graph network for video summarization,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:09.569997Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:0bec50e61ebd471889311604e085b1c2d88f1c3dda86f517c7531ff946ef4651","observation_id":"66cc8e14-b0b8-4c98-b739-8aa4cbf00c52","resolution":{"observed_at":"2026-08-07T00:58:09.569997Z","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":"2026-08-07T00:58:09.678910Z","title":"Two-stage learning to predict human eye fixations via sdaes,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:09.678910Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:1de220f0b02902d096c81753a9f10adc7119d72ba62b96980e29c59112c683a8","observation_id":"f8ea2ba5-b1c9-4a96-b476-4944ed2a4240","resolution":{"observed_at":"2026-08-07T00:58:09.678910Z","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":"2026-08-07T00:58:09.760145Z","title":"A review of co-saliency detection algorithms: Fundamentals, applications, and challenges,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:09.760145Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:4c6e96da916039654a66c92a34625fe4777e3aacc05523900f2d28ebce97617b","observation_id":"3bf8684f-967a-4523-ab68-69c1a48642f3","resolution":{"observed_at":"2026-08-07T00:58:09.760145Z","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":"2026-08-07T00:58:09.830665Z","title":"Deep neural networks with elastic rectified linear units for object recognition,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:09.830665Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:5ae283a5b8b4ec1a82ef4a638c31cfadb3a73eaf8e1fbd86f2fa92bfd198c3dd","observation_id":"1d82856e-0fb2-4c99-a563-9c2450b1c69c","resolution":{"observed_at":"2026-08-07T00:58:09.830665Z","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":"2026-08-07T00:58:09.977985Z","title":"Bayesian tensor approach for 3-d face modeling,","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:09.977985Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:27a67a30d725b1dfb1482c023ef5c558bca34806316c2874f1326824fe615b2a","observation_id":"9182d403-4aa9-4a22-bac9-62a9be195907","resolution":{"observed_at":"2026-08-07T00:58:09.977985Z","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":"2026-08-07T00:58:10.072421Z","title":"Attention is all you need,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:10.072421Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:c121aa88dc22fe72d703e978a5bb240bf1276f23ce9e87b12cc3561b7117d9fd","observation_id":"839ff41f-28b6-4dd5-acfa-8691240e3262","resolution":{"observed_at":"2026-08-07T00:58:10.072421Z","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":"2026-08-07T00:58:10.165530Z","title":"GPT-4 technical report,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:10.165530Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:9def74db8d264f7b0e45177b4a2ef1cb78b840d8c4f220e605fd2c55e42f819a","observation_id":"e3973ad9-1405-4d9c-8bad-d8d5620c10da","resolution":{"observed_at":"2026-08-07T00:58:10.165530Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.19437","last_updated":"2025-02-18T17:26:38Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-27T04:03:16Z","title":"DeepSeek-V3 Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.19437","snapshot_observed_at":"2026-08-07T00:58:10.265776Z","title":"DeepSeek-V3 technical report,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:10.265776Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:c1dbb568b023c90b97872f8e38a8bea0c53b8d88b8489ae0138f6e7a6dd90723","observation_id":"d07af860-f7d8-4830-b317-ab066f737acd","resolution":{"observed_at":"2026-08-07T00:58:10.265776Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.15115","last_updated":"2025-01-03T02:18:21Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-19T17:56:09Z","title":"Qwen2.5 Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.15115","snapshot_observed_at":"2026-08-07T00:58:10.393350Z","title":"Qwen2.5 technical report,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:10.393350Z"},"links":{"cited_paper":"/paper/2412.15115","citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:0563285f9af3e68de45632b1bb5556fe4afb678c0c08a6283bc42687ba0d80ce","observation_id":"dcc20b4a-0138-4061-a7f6-99cdcc7858f7","resolution":{"observed_at":"2026-08-07T00:58:10.393350Z","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":"2026-08-07T00:58:10.481608Z","title":"Visual instruction tuning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:10.481608Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:dc5564393ec0062931e78f684fddc3c5d89d0288a0d98332453b2cb8d75949bf","observation_id":"2fecd691-64e4-4d7b-bb58-c86715bc2ef9","resolution":{"observed_at":"2026-08-07T00:58:10.481608Z","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":"2026-08-07T00:58:10.529572Z","title":"Positive-incentive noise,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:10.529572Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:ee9a92c0371903cb9258934547f7355c6f6be38f4bfaabda1aa2fd4acc398c06","observation_id":"c23ea920-ad64-4333-b1cd-4dfd0b6f3a3e","resolution":{"observed_at":"2026-08-07T00:58:10.529572Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.11903","last_updated":"2023-01-10T23:07:57Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-01-28T02:33:07Z","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.11903","snapshot_observed_at":"2026-08-07T00:58:10.582016Z","title":"Chain-of-thought prompting elicits reasoning in large language models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:10.582016Z"},"links":{"cited_paper":"/paper/2201.11903","citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:1197cebbd94f90421bfc6fbc100c6eb4af6393fe8a52da7c99303d11642ccc7a","observation_id":"40a2e46a-817d-4300-a49c-000acbc2ef81","resolution":{"observed_at":"2026-08-07T00:58:10.582016Z","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":"2026-08-07T00:58:10.671303Z","title":"A survey on large language model based autonomous agents,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:10.671303Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:4ea94526443dc14912134d898768f5cc1a60a53079f3c0619a61080c9bb6dccd","observation_id":"c2d2b2e4-5439-4378-87ba-69651390fa18","resolution":{"observed_at":"2026-08-07T00:58:10.671303Z","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":"2026-08-07T00:58:10.801744Z","title":"WirelessLLM: Empowering large language models towards wireless intelligence,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:10.801744Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:f43bcec47ffb2e4dbe02a7b4ca8396dba461f59c9d30e309f168804de5dd3cae","observation_id":"a14bc073-83f6-434c-bc9e-9eeac06f6d1c","resolution":{"observed_at":"2026-08-07T00:58:10.801744Z","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":"2026-08-07T00:58:10.882205Z","title":"Task-oriented communication for edge video analytics,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:10.882205Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:5f1b0998b4fc0d9fb2089482b276287afc57a169eb3fe32cfa7612b1950820a7","observation_id":"17c7b8be-c702-4583-b2fe-aee99ec69719","resolution":{"observed_at":"2026-08-07T00:58:10.882205Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1512.03385","last_updated":"2015-12-10T19:51:55Z","snapshot_observed_at":"2026-07-06T04:39:28.429064Z","submitted_at":"2015-12-10T19:51:55Z","title":"Deep Residual Learning for Image Recognition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1512.03385","snapshot_observed_at":"2026-08-07T00:58:10.967773Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:10.967773Z"},"links":{"cited_paper":"/paper/1512.03385","citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:6d2ad5a17184bac6b270b6c49637bdd1a5f8468ca7284485c00affa1d0177195","observation_id":"746ff8a8-d58f-460a-9b52-a2518eb11773","resolution":{"observed_at":"2026-08-07T00:58:10.967773Z","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":"2026-08-07T00:58:11.081431Z","title":"Large language models empowered autonomous edge AI for connected intelligence,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:11.081431Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:55e43ab3b43dbeb06ab2d5d0ca69e18be9c97e1d159d8ea5dcf365a47060b49a","observation_id":"3f0d605d-a7b6-487d-b48d-98f6eccdd935","resolution":{"observed_at":"2026-08-07T00:58:11.081431Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.00020","last_updated":"2021-02-26T19:04:58Z","snapshot_observed_at":"2026-07-06T10:45:03.059688Z","submitted_at":"2021-02-26T19:04:58Z","title":"Learning Transferable Visual Models From Natural Language Supervision","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.00020","snapshot_observed_at":"2026-08-07T00:58:11.149104Z","title":"Learning transferable visual models from natural language supervision,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:11.149104Z"},"links":{"cited_paper":"/paper/2103.00020","citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:34428bceb6824e8931216a0461690a3131e803c71ddef1626cbb05d6ef93a616","observation_id":"43dc7d00-3200-46a3-b649-c30ab74213be","resolution":{"observed_at":"2026-08-07T00:58:11.149104Z","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":"2503.12926","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.230195Z","title":"Task-oriented feature compression for multimodal understanding via device-edge co-inference,","venue":null,"work_id":"ced1883d-a4a5-4311-9ca3-ce5f4b912e7b","year":2025},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:11.244590Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:5f50883af2c51ce41a7b576b3d9a32a4fe01b8075b212bcb84ede34d289dd8ce","observation_id":"c6a31f2e-2d85-4593-a82c-b3967ddb4845","resolution":{"observed_at":"2026-08-07T00:58:16.238891Z","resolver_source":"raw_fallback","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:17.068443Z","title":"Task-oriented communication for multidevice cooperative edge inference,","venue":null,"work_id":"2fadbcec-989c-46c0-a455-b7922b25e702","year":2022},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:11.364130Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:c5c6bd1c491f1ce26818eeb608043ddb27504e254037c413e24c5b417e8b249f","observation_id":"469f2137-85bf-4d01-bb9a-a69ff4f08e7e","resolution":{"observed_at":"2026-08-07T00:58:17.073251Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:17.053235Z","title":"Study on density peaks clustering based on k-nearest neighbors and principal component analysis,","venue":null,"work_id":"2153c21b-7a54-4dd0-acab-4d197557bb10","year":2016},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:11.458092Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:00753ba38c5ccfb3c530eecb7bd0eae773ebfed2d709ab33b432e22c0b4875bc","observation_id":"fb0cef92-b722-4f65-8c44-0ebcc87185f6","resolution":{"observed_at":"2026-08-07T00:58:17.057960Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:17.038101Z","title":"Variational image compression with a scale hyperprior,","venue":null,"work_id":"a46c89db-a994-4206-b96c-55610bbb05b5","year":2018},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:11.520168Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:790ba0a8750b28e6a8590710a3cbbbbdd87a88ef55a07b74bf76a44241ebd3b3","observation_id":"0d1fc641-c9e6-4b1a-848a-e2d741c4d57b","resolution":{"observed_at":"2026-08-07T00:58:17.043114Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:17.022633Z","title":"Channel-wise autoregressive entropy models for learned image compression,","venue":null,"work_id":"170272db-1a68-4dff-9edd-6cecb20f94ae","year":2020},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:11.619396Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:ee20e17fc13871512d73707fd429288b890af598ff23fc9208ceadb93d0e2f23","observation_id":"a9b01d6e-9253-4e14-b701-cd356476537b","resolution":{"observed_at":"2026-08-07T00:58:17.027806Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":{"arxiv_id":"2408.03326","last_updated":"2024-10-26T16:35:13Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-08-06T17:59:44Z","title":"LLaVA-OneVision: Easy Visual Task Transfer","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.03326","snapshot_observed_at":"2026-08-07T00:58:11.688742Z","title":"LLaV A-OneVision: Easy visual task transfer,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:11.688742Z"},"links":{"cited_paper":"/paper/2408.03326","citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:7ba1f6f2d14f11cd11ad2a0d74e8ef36f108d9f2f2ce259fe57757cadff741d0","observation_id":"f590f93a-580a-4b65-92e0-6dd5aee179fa","resolution":{"observed_at":"2026-08-07T00:58:11.688742Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:17.007295Z","title":"LoRA: Low-rank adaptation of large language models,","venue":null,"work_id":"bb00ad9e-4583-442d-994c-cc01c9b0d94d","year":2022},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:11.803263Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:2ae17d9faf947128d9c4c5482356d6230757e1e43bb9ff504b34e51de6acefb8","observation_id":"24726006-afd2-4d7b-acea-4c9ab8fed95d","resolution":{"observed_at":"2026-08-07T00:58:17.012305Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.992191Z","title":"Improved baselines with visual instruction tuning,","venue":null,"work_id":"83640d86-5d82-4256-ac04-18f0ce60f3ec","year":2024},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:11.865376Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:e73e24f274c8d89b9c74692310bc7b26e3ec68f1db49bad1de29264f578bc01d","observation_id":"2d897c27-6158-4f69-b787-8650c9fa4eee","resolution":{"observed_at":"2026-08-07T00:58:16.996924Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":{"arxiv_id":"2306.13394","last_updated":"2025-10-24T02:45:36Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-06-23T09:22:36Z","title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.13394","snapshot_observed_at":"2026-08-07T00:58:11.948904Z","title":"MME: A comprehensive evaluation benchmark for multimodal large language models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:11.948904Z"},"links":{"cited_paper":"/paper/2306.13394","citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:7d56c9fce7de62f066fe09c211e1fe5d2e510ec4fe9047fa7f7fb61c14dae911","observation_id":"8ea96dad-4f2f-4555-b6b8-37e1083f6a64","resolution":{"observed_at":"2026-08-07T00:58:11.948904Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.976285Z","title":"The JPEG 2000 still image compression standard,","venue":null,"work_id":"f56a0376-99ed-4c1d-a3ea-948cd6496eac","year":2000},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:12.024445Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:78d62f95442356f496f1e28b7c43140c1b77a42c01a7e1321b2b3d901f40c80b","observation_id":"a1fcdf1c-b075-4d53-8726-51b1155350d6","resolution":{"observed_at":"2026-08-07T00:58:16.981067Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.960050Z","title":"Research on the WebP image format,","venue":null,"work_id":"5eddd1a0-4308-4813-a31c-e51f6f2a780a","year":2016},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:12.173874Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:9c34741ee733669cdabd670475751dcd2cbff392d00a5e3f745fc8e8be730815","observation_id":"4c230fa4-61cc-4ccb-a540-0706855c7216","resolution":{"observed_at":"2026-08-07T00:58:16.965462Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":{"arxiv_id":"2305.20050","last_updated":"2023-05-31T17:24:00Z","snapshot_observed_at":"2026-08-05T13:11:04.104454Z","submitted_at":"2023-05-31T17:24:00Z","title":"Let's Verify Step by Step","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.20050","snapshot_observed_at":"2026-08-07T00:58:12.244680Z","title":"Let’s verify step by step,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:12.244680Z"},"links":{"cited_paper":"/paper/2305.20050","citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:afc57ced4a2486c4c7c1c7721c8df8e9a2b7e3447312214d4b61a9edd04e4cdb","observation_id":"ed825d76-b21e-4613-9f36-c2c1ea341b8d","resolution":{"observed_at":"2026-08-07T00:58:12.244680Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.07974","last_updated":"2024-06-06T17:41:21Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-03-12T17:58:04Z","title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.07974","snapshot_observed_at":"2026-08-07T00:58:12.358095Z","title":"Livecodebench: Holistic and contamination free evaluation of large language models for code,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:12.358095Z"},"links":{"cited_paper":"/paper/2403.07974","citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:0c7be55569694b3bb1079a7c319f055b4a5b16c6258d5d983e286f431249e8ab","observation_id":"77356eaa-d091-4086-b05b-088674186ec9","resolution":{"observed_at":"2026-08-07T00:58:12.358095Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.944060Z","title":"Low-rank matrix factorization for deep neural network training with high-dimensional output targets,","venue":null,"work_id":"033eb3ea-6bbc-400c-9377-574e8b29ea27","year":2013},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:12.460084Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:d73fe3ba07212a523173b9d1753f4ca2fecda719b831b311f4849217ed870556","observation_id":"b1868d00-df62-4e58-a884-608df8b4778a","resolution":{"observed_at":"2026-08-07T00:58:16.949234Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.928514Z","title":"Learning low-rank deep neural networks via singular vector orthogonality regularization and singular value sparsification,","venue":null,"work_id":"02071698-ef24-4be7-b478-be58aeca6e9a","year":2020},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:12.577444Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:839effa54f0c35d5065e3c9f1e2234ff628616fb7bd986278eccf4a2126bc062","observation_id":"4681b954-1b96-4ab8-8cdd-b3f987471e36","resolution":{"observed_at":"2026-08-07T00:58:16.933393Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":{"arxiv_id":"2402.12354","last_updated":"2024-07-04T18:33:00Z","snapshot_observed_at":"2026-08-03T17:12:16.534784Z","submitted_at":"2024-02-19T18:33:49Z","title":"LoRA+: Efficient Low Rank Adaptation of Large Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.12354","snapshot_observed_at":"2026-08-07T00:58:12.645489Z","title":"LoRA+: Efficient low rank adaptation of large models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:12.645489Z"},"links":{"cited_paper":"/paper/2402.12354","citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:4f9ba709a55f35a55d1795c92c5e5e41f29b8337e7ab9d6e7bd6bf65ea43bb75","observation_id":"c440cf49-dcfb-48a1-bc01-ea18736ea259","resolution":{"observed_at":"2026-08-07T00:58:12.645489Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.912494Z","title":"Early-exit deep neural network-a comprehensive survey,","venue":null,"work_id":"b7d09561-3444-45a5-8a72-8fe801f79ac3","year":2024},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:12.718065Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:798efe42367235c9cbc23f94fb41cbc7ac75c9e993966079aa983420f3aac878","observation_id":"f3c1d2fa-64c4-4d4a-b38c-eef21de59fce","resolution":{"observed_at":"2026-08-07T00:58:16.917186Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.895996Z","title":"EE-LLM: large-scale training and inference of early-exit large language models with 3d parallelism,","venue":null,"work_id":"85b05df8-6397-4d54-a4a0-bf0f99bf6cb8","year":2024},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:12.852444Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:8955da7f9e087c51cf59abb25bfd065ad469c217197f7b38e27d9f058a27cf30","observation_id":"6317f728-1230-4bf9-893d-8fc319ce752f","resolution":{"observed_at":"2026-08-07T00:58:16.902369Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"2504.10724","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.061424Z","title":"HELIOS: Adaptive model and early-exit selection for efficient llm inference serving,","venue":null,"work_id":"5a29903d-e90e-450a-a147-42641934da37","year":2025},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:12.943628Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:ab38c1328cf89b1845c617065383b6f6283cee2df1d55a0106915603eaad92b9","observation_id":"f6fecf8a-7fa1-4848-8195-919d748f2536","resolution":{"observed_at":"2026-08-07T00:58:16.073817Z","resolver_source":"raw_fallback","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.880654Z","title":"Branchynet: Fast inference via early exiting from deep neural networks,","venue":null,"work_id":"17c8c340-6704-4c0e-a701-8e9f4ca329f3","year":2016},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:13.112517Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:592cd59dcac720be75520c179502e3680ef02a2349a473f4ccdb61a0977c7c2a","observation_id":"48ced121-9e48-400a-abd4-69fa8af5ca3d","resolution":{"observed_at":"2026-08-07T00:58:16.885408Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.865736Z","title":"Branchy-gnn: A device-edge co-inference framework for efficient point cloud processing,","venue":null,"work_id":"93dd2607-6bb4-4226-9541-e80260f43d2a","year":2021},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:13.297017Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:e47d950791dd2ef1b6dc51e4096fd7462bfc13fb6a656690ee4f30a45b3fe02d","observation_id":"a8a4ea96-d0e1-4310-b284-7a89059a5366","resolution":{"observed_at":"2026-08-07T00:58:16.870473Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":{"arxiv_id":"2104.00749","last_updated":"2022-04-25T10:38:17Z","snapshot_observed_at":"2026-07-06T10:55:50.888606Z","submitted_at":"2021-04-01T20:01:57Z","title":"Anytime Dense Prediction with Confidence Adaptivity","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.00749","snapshot_observed_at":"2026-08-07T00:58:13.434912Z","title":"Anytime dense prediction with confidence adaptivity,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:13.434912Z"},"links":{"cited_paper":"/paper/2104.00749","citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:93d0a98b85cebc981fd06a12869703862e046f598072243622c92788544b9d8e","observation_id":"01747405-c07b-44df-bc3c-ad66635e46a7","resolution":{"observed_at":"2026-08-07T00:58:13.434912Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.850080Z","title":"DeeBERT: Dynamic early exiting for accelerating BERT inference,","venue":null,"work_id":"b1d7448c-bab7-4316-a65e-36658cdf1b34","year":2020},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:13.525808Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:8bf88178835b936e1c40b4ea0966b36f02a8f47641e453cb8477975df0e2b2f3","observation_id":"ab9dd46f-43ff-45d7-baff-8d03419f4fa4","resolution":{"observed_at":"2026-08-07T00:58:16.854989Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.834565Z","title":"SkipBERT: Efficient inference with shallow layer skipping,","venue":null,"work_id":"a75f28fc-9dc6-4e49-b046-edcdf9f5cc34","year":2022},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:13.609702Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:8aeecbf1b5712c2a398322ed96864745e06404f893bf2e3309459d44ad4716cd","observation_id":"b8c0680e-8c3c-4c83-b7de-1da4e922f446","resolution":{"observed_at":"2026-08-07T00:58:16.839814Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.818803Z","title":"Confident adaptive language modeling,","venue":null,"work_id":"dd8ea204-c4c4-4b52-8f70-7c8a00ba58c6","year":2022},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:13.732905Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:eb7c51cb09109cd84c98415f81609dc902c864f2ca3cdf6ee37b72c285f38c23","observation_id":"d8c965b9-9718-40f5-8331-052b4fe2aa7b","resolution":{"observed_at":"2026-08-07T00:58:16.824204Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":{"arxiv_id":"2402.00518","last_updated":"2024-02-01T11:39:04Z","snapshot_observed_at":"2026-07-06T17:23:39.158867Z","submitted_at":"2024-02-01T11:39:04Z","title":"EE-Tuning: An Economical yet Scalable Solution for Tuning Early-Exit Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.00518","snapshot_observed_at":"2026-08-07T00:58:13.818664Z","title":"EE-Tuning: An economical yet scalable solution for tuning early-exit large language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:13.818664Z"},"links":{"cited_paper":"/paper/2402.00518","citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:fdd386cac92954e93a6a700aa1aca63479421147dcf496c3182c60c7ac6f7043","observation_id":"03448e97-d814-4afb-ac6f-b2401a2c65eb","resolution":{"observed_at":"2026-08-07T00:58:13.818664Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.802950Z","title":"SVD-LLM: Truncation-aware singular value decomposition for large language model compression,","venue":null,"work_id":"f3562ae3-2b77-4799-a33f-3b8a6e067415","year":2025},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:13.905327Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:25960ed4fad4ec1145239eda1092336b0d6f873f72ddc3f6e70e67242e73cf6b","observation_id":"2d7b0b71-03e0-4109-8460-0e9a4bfece2e","resolution":{"observed_at":"2026-08-07T00:58:16.808037Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.787887Z","title":"LayerSkip: Enabling early exit inference and self-speculative decoding,","venue":null,"work_id":"20647915-49d7-4999-95db-1fe35408187f","year":2024},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:14.018014Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:02b60fecdbdb77ff680ae7bfc4c8d8103563cdfc52f018359d3ada03e195de0a","observation_id":"47f8ab9d-0986-410f-a00a-71047a03cf60","resolution":{"observed_at":"2026-08-07T00:58:16.792770Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":{"arxiv_id":"2401.03804","last_updated":"2024-04-02T01:45:11Z","snapshot_observed_at":"2026-08-06T10:09:37.454888Z","submitted_at":"2024-01-08T10:43:19Z","title":"TeleChat Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.03804","snapshot_observed_at":"2026-08-07T00:58:14.132023Z","title":"Telechat technical report,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:14.132023Z"},"links":{"cited_paper":"/paper/2401.03804","citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:b09b5681dc2533cb70e3d09e64d0cdd123eca9075478bb87ddbfad5f07e88f8e","observation_id":"5d53f9ea-7d4c-4188-a259-d041855b85d8","resolution":{"observed_at":"2026-08-07T00:58:14.132023Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2009.03300","last_updated":"2021-01-12T18:57:11Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-09-07T17:59:25Z","title":"Measuring Massive Multitask Language Understanding","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2009.03300","snapshot_observed_at":"2026-08-07T00:58:14.238314Z","title":"Measuring massive multitask language understanding,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:14.238314Z"},"links":{"cited_paper":"/paper/2009.03300","citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:67cb1fe491ea4e8ebeb1dd3ded6c607ad6372f3a01fbc732f10e819e2282f4ea","observation_id":"c3a73f2b-01d0-4b87-ba48-a1d92266d1b8","resolution":{"observed_at":"2026-08-07T00:58:14.238314Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.09212","last_updated":"2024-01-17T19:09:57Z","snapshot_observed_at":"2026-08-04T18:52:19.083847Z","submitted_at":"2023-06-15T15:49:51Z","title":"CMMLU: Measuring massive multitask language understanding in Chinese","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.09212","snapshot_observed_at":"2026-08-07T00:58:14.352916Z","title":"CMMLU: Measuring massive multitask language understanding in chinese,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:14.352916Z"},"links":{"cited_paper":"/paper/2306.09212","citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:55d6fe5a0c213538e922d8e6d151c5f6344f8ceadd7f103c1321f0593c343907","observation_id":"3c58b6da-bc5d-46ee-94c3-aa2a10efd123","resolution":{"observed_at":"2026-08-07T00:58:14.352916Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.08322","last_updated":"2023-11-06T13:24:16Z","snapshot_observed_at":"2026-08-07T23:54:46.322439Z","submitted_at":"2023-05-15T03:20:19Z","title":"C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.08322","snapshot_observed_at":"2026-08-07T00:58:14.456272Z","title":"C-Eval: A Multi-Level Multi-Discipline chinese evaluation suite for foundation models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:14.456272Z"},"links":{"cited_paper":"/paper/2305.08322","citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:088949830690ae716b57a3f98d40c2f16ac2630f6b10e8da8fee1ad704d6564a","observation_id":"bb066663-b1b1-43f0-acb7-bab36b5b58ce","resolution":{"observed_at":"2026-08-07T00:58:14.456272Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.14168","last_updated":"2021-11-18T00:23:45Z","snapshot_observed_at":"2026-08-07T01:45:38.840969Z","submitted_at":"2021-10-27T04:49:45Z","title":"Training Verifiers to Solve Math Word Problems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.14168","snapshot_observed_at":"2026-08-07T00:58:14.566547Z","title":"Training verifiers to solve math word problems,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:14.566547Z"},"links":{"cited_paper":"/paper/2110.14168","citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:4a3e20bb51e41b3f55c3ded7c6e41e51161e91862e8374e8b07def2ff840121c","observation_id":"1a50353e-5d4e-47b2-8d3e-c38a19e3ba02","resolution":{"observed_at":"2026-08-07T00:58:14.566547Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.03874","last_updated":"2021-11-08T21:30:18Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2021-03-05T18:59:39Z","title":"Measuring Mathematical Problem Solving With the MATH Dataset","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.03874","snapshot_observed_at":"2026-08-07T00:58:14.673669Z","title":"Measuring mathematical problem solving with the math dataset,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:14.673669Z"},"links":{"cited_paper":"/paper/2103.03874","citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:15a2a41234d6d24513eacb96474de08f17be790e5272805b13988be8daf0a8e7","observation_id":"8c7bf44f-89ac-4609-96b7-447c7cd7d933","resolution":{"observed_at":"2026-08-07T00:58:14.673669Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.09261","last_updated":"2022-10-17T17:08:26Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-10-17T17:08:26Z","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.09261","snapshot_observed_at":"2026-08-07T00:58:14.782234Z","title":"Challenging BIG-Bench tasks and whether chain-of-thought can solve them,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:14.782234Z"},"links":{"cited_paper":"/paper/2210.09261","citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:b466df19ab764a75d64691644504dc0c410f807f4116976b591e2485772ade71","observation_id":"26dc7054-565c-47ac-be98-4c64076e228c","resolution":{"observed_at":"2026-08-07T00:58:14.782234Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.772262Z","title":"A diagram is worth a dozen images,","venue":null,"work_id":"cfdc8441-0382-41cf-9b0e-c4b4e21cbdab","year":2016},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:14.853345Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:41c3b46a91b60a83a98618d776196d26fa8449ab05ba21a4e7eb2960467922f4","observation_id":"4a30e3d6-03ca-4ed2-a9c8-3036123aaa9d","resolution":{"observed_at":"2026-08-07T00:58:16.777460Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.757184Z","title":"MMBench: Is your multi-modal model an all-around player?","venue":null,"work_id":"efa81a48-0550-408d-8117-9aa2f6a12fb3","year":2024},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:14.989180Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:d303de48f29859ca7a276c3c2bf65442107e05532b0e6c68df65c42a3ca1d037","observation_id":"fc99ef18-eaf0-479e-bd98-f3ea71ae6b0b","resolution":{"observed_at":"2026-08-07T00:58:16.761850Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.741821Z","title":"Are we on the right way for evaluating large vision-language models?","venue":null,"work_id":"94b17625-3db7-4487-87f1-d17901b38097","year":2024},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:15.015126Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:411185fb82f5c5d56294139444898a878395d355bd5dbe7349156fd5d24ac048","observation_id":"cdb35325-f5ae-46e7-8556-33a58d0b9415","resolution":{"observed_at":"2026-08-07T00:58:16.746949Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.726336Z","title":"Learn to explain: Multimodal reasoning via thought chains for science question answering,","venue":null,"work_id":"15ec112e-88e9-4827-98d0-2382a953a35e","year":2022},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:15.084586Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:359a4dd9ec8a507d0181b0b67d4ad4ff25548bda7a7605d493c3134bb48ac7e1","observation_id":"7422f77a-f1f2-47bb-b839-7f61367f0221","resolution":{"observed_at":"2026-08-07T00:58:16.731173Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.710397Z","title":"SEED-Bench: Benchmarking multimodal large language models,","venue":null,"work_id":"583b4be2-37d0-4782-8803-5f23743b738b","year":2024},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:15.205577Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:f43fad07ddaa4c1e1ac2ad7525342df63810bb9fb404915380ce2f19247eeb62","observation_id":"8ceadc7f-8d66-4e0e-9115-d0b6ffded55a","resolution":{"observed_at":"2026-08-07T00:58:16.715569Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.693403Z","title":"ChartQA: A benchmark for question answering about charts with visual and logical reasoning,","venue":null,"work_id":"3338d7d9-a6a1-4db9-bf02-5dcf764044b1","year":2022},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:15.264573Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:11c2126786896804bd2c45ee9000f2d2f8e16836d44fdd75656015cb421f15ae","observation_id":"a5c87e50-4013-41ce-8947-66d91cd55942","resolution":{"observed_at":"2026-08-07T00:58:16.698272Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.677136Z","title":"DocVQA: A dataset for VQA on document images,","venue":null,"work_id":"76209922-b4a9-4fae-918c-9d2d1f5f7793","year":2021},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:15.269252Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:d0cfa9e24603f27b1f4e8a4c27bd616d40a98eee54593f6aa95baafad2d0d396","observation_id":"45209dd0-1759-4c85-b014-c07c00486d19","resolution":{"observed_at":"2026-08-07T00:58:16.682650Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.661015Z","title":"InfographicVQA,","venue":null,"work_id":"75c34b0f-327a-41af-a398-b20d0d756a19","year":2022},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:15.273401Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:82b9c77a6a8f4c1f6fffcf739ac0125884766d2c6d13ceeaf3e00a8193e4e157","observation_id":"11b1155d-fc6c-4dbb-be44-26afd6e282a4","resolution":{"observed_at":"2026-08-07T00:58:16.665962Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":{"arxiv_id":"2306.05685","last_updated":"2023-12-24T02:01:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-06-09T05:55:52Z","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.05685","snapshot_observed_at":"2026-08-07T00:58:15.277655Z","title":"Judging LLM-as-a-judge with MT-Bench and chatbot arena,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:15.277655Z"},"links":{"cited_paper":"/paper/2306.05685","citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:0c0a186d5ff2fbfcd2f709b72dfa472f6f0116ce55ee9298e320b654f08f190b","observation_id":"965c4136-1d34-41aa-81ca-126c3a8931bb","resolution":{"observed_at":"2026-08-07T00:58:15.277655Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.04475","last_updated":"2025-03-10T09:27:03Z","snapshot_observed_at":"2026-07-06T17:56:23.317089Z","submitted_at":"2024-04-06T02:29:02Z","title":"Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.04475","snapshot_observed_at":"2026-08-07T00:58:15.282543Z","title":"Length-controlled alpacaeval: A simple way to debias automatic evaluators,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:15.282543Z"},"links":{"cited_paper":"/paper/2404.04475","citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:ffef3258a78ba8407b023336aacd2605432f62a9f60165f52041d3eb19d6c582","observation_id":"865c8c86-1197-4188-a3b3-cc76c4a526b2","resolution":{"observed_at":"2026-08-07T00:58:15.282543Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.11939","last_updated":"2024-10-14T18:11:58Z","snapshot_observed_at":"2026-08-02T11:33:41.297984Z","submitted_at":"2024-06-17T17:26:10Z","title":"From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.11939","snapshot_observed_at":"2026-08-07T00:58:15.287360Z","title":"From crowdsourced data to high-quality benchmarks: Arena-hard and benchbuilder pipeline,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:15.287360Z"},"links":{"cited_paper":"/paper/2406.11939","citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:fd47e2305611dd7405ad7873a51db6fc1b6b125a9a486424b5e05be9559f5f22","observation_id":"0ebd55a3-2a46-419e-ade5-a04d60fee373","resolution":{"observed_at":"2026-08-07T00:58:15.287360Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.13923","last_updated":"2025-02-19T18:00:14Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-02-19T18:00:14Z","title":"Qwen2.5-VL Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.13923","snapshot_observed_at":"2026-08-07T00:58:15.292198Z","title":"Qwen2.5-VL technical report,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:15.292198Z"},"links":{"cited_paper":"/paper/2502.13923","citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:52d6c95f78f6d551a1b6133182f380803991de7734e49ce6cb96e7d6dd9ce818","observation_id":"33b331d8-e283-4712-8c6f-58c769bc7516","resolution":{"observed_at":"2026-08-07T00:58:15.292198Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.17811","last_updated":"2025-01-29T18:00:19Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-01-29T18:00:19Z","title":"Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.17811","snapshot_observed_at":"2026-08-07T00:58:15.296832Z","title":"Janus-Pro: Unified multimodal understanding and generation with data and model scaling,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:15.296832Z"},"links":{"cited_paper":"/paper/2501.17811","citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:8bda7c6bb41e33e241d43293648bdaf8450d369a9740f336cc145608ba1ab6c0","observation_id":"22a539dd-561d-4e16-a9c4-6ec45a3773ee","resolution":{"observed_at":"2026-08-07T00:58:15.296832Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.645094Z","title":"Temos: Generating diverse human motions from textual descriptions,","venue":null,"work_id":"769c8a25-f810-454a-aeb5-018fc97102fe","year":2022},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:15.301782Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:f6a735ef3a099883ee1868e48aeebe64e27906ab5efcb8222283f4f393968340","observation_id":"0afd4224-a0f2-4151-b259-0f06d1c3c87a","resolution":{"observed_at":"2026-08-07T00:58:16.650111Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.629584Z","title":"Generating diverse and natural 3D human motions from text,","venue":null,"work_id":"230cf7e8-4b41-4060-8392-3de18ad082ca","year":2022},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:15.307416Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:c203267f8400c26d99e8401cd9f7b6867cf867b8cf7ec3fa0c68817d86ddf10b","observation_id":"dd3bfcc8-d189-4b46-b3c5-7560add9dfe8","resolution":{"observed_at":"2026-08-07T00:58:16.634667Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.614099Z","title":"Human motion diffusion model,","venue":null,"work_id":"c91795f3-77af-4869-b6ab-33b9e3614e91","year":2023},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:15.312076Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:d8f26e64312aaf1a6302db5dc8eeb6273dd68a09b2f1ed13ae1c673566af6255","observation_id":"f3af5c27-8111-4af9-8181-89c838c35226","resolution":{"observed_at":"2026-08-07T00:58:16.619064Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":{"arxiv_id":"2303.01418","last_updated":"2023-08-30T04:41:10Z","snapshot_observed_at":"2026-08-04T22:38:03.106382Z","submitted_at":"2023-03-02T17:09:27Z","title":"Human Motion Diffusion as a Generative Prior","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.01418","snapshot_observed_at":"2026-08-07T00:58:15.316983Z","title":"Human motion diffusion as a generative prior,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:15.316983Z"},"links":{"cited_paper":"/paper/2303.01418","citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:20c0e943cd11487ef3647e326af2f8ef6f4d30128e061049fb4f386197149afd","observation_id":"13efc6a3-4d2b-4220-add6-fa365210360b","resolution":{"observed_at":"2026-08-07T00:58:15.316983Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.598403Z","title":"Intergen: Diffusion-based multi-human motion generation under complex interactions,","venue":null,"work_id":"6df8094b-0ab9-44f9-bfd1-c927e9360e32","year":2024},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:15.322737Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:8fa3db81720ebec716bdc1ab066b3035a0574a86ecdc2161df378d34d249a546","observation_id":"7b389243-a452-4a56-a781-c92e215793d7","resolution":{"observed_at":"2026-08-07T00:58:16.603270Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.582797Z","title":"Freemotion: A unified framework for number-free text-to-motion synthesis,","venue":null,"work_id":"352d128f-b046-4b3a-9282-139cd6c48a0a","year":2024},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:15.328295Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:4180e862836617f9eb72b66fc0d39efb15b9efd32163b7278271601a3af3b535","observation_id":"517f20ff-c3f2-475a-bd96-127391382cbb","resolution":{"observed_at":"2026-08-07T00:58:16.587704Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":{"arxiv_id":"2504.12103","last_updated":"2025-04-16T14:12:25Z","snapshot_observed_at":"2026-08-07T16:01:47.090806Z","submitted_at":"2025-04-16T14:12:25Z","title":"Metric-Solver: Sliding Anchored Metric Depth Estimation from a Single Image","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.12103","snapshot_observed_at":"2026-08-07T00:58:15.333651Z","title":"Metric-Solver: Sliding anchored metric depth estimation from a single image,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:15.333651Z"},"links":{"cited_paper":"/paper/2504.12103","citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:7f15cc605c012982becab7ed02561c5ab41080254a5a9a5955fa3f5777074b04","observation_id":"0dac3641-b705-45c0-9f75-1863e7c766e6","resolution":{"observed_at":"2026-08-07T00:58:15.333651Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.565689Z","title":"Adabins: Depth estimation using adaptive bins,","venue":null,"work_id":"09cdf72b-6d45-48d2-b82b-b015916ee19c","year":2021},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:15.338793Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:40952749ef384afc3f6f8f84057ddc7e56f32864cd454cf91f907f41ec6623c5","observation_id":"ad4fe4ee-192a-405c-8acf-ba1f8f0ba655","resolution":{"observed_at":"2026-08-07T00:58:16.570901Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":{"arxiv_id":"2203.01502","last_updated":"2022-06-06T08:55:02Z","snapshot_observed_at":"2026-08-06T03:14:28.220190Z","submitted_at":"2022-03-03T03:27:20Z","title":"NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.01502","snapshot_observed_at":"2026-08-07T00:58:15.344217Z","title":"New crfs: Neural window fully-connected crfs for monocular depth estimation,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:15.344217Z"},"links":{"cited_paper":"/paper/2203.01502","citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:58719c7cb9cf0e792ba0f694a09be6113152984c300853e46035f862adea1b7c","observation_id":"bebc1258-8268-4c44-ac6f-255edf806fc0","resolution":{"observed_at":"2026-08-07T00:58:15.344217Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.550528Z","title":"Vision transformers for dense prediction,","venue":null,"work_id":"d6d8a3cc-52eb-4b34-9578-0039997849b4","year":2021},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:15.349548Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:fe304791750bb4f0826ebfa7567f0cbe00502f425e600891a7109557397af942","observation_id":"85d4e241-ec59-4310-9862-b5438dd57234","resolution":{"observed_at":"2026-08-07T00:58:16.555260Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.534253Z","title":"P3depth: Monocular depth estimation with a piecewise planarity prior,","venue":null,"work_id":"7036bda5-0f23-4b23-844f-d518e4819fbb","year":2022},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:15.354950Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:b5352b224624e7e41d50275ab4fece241200ad261084786084c2dcd80e538ecf","observation_id":"d15b08b1-9c1b-4496-b243-65c72cb9ced7","resolution":{"observed_at":"2026-08-07T00:58:16.539421Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.517901Z","title":"Swin transformer v2: Scaling up capacity and resolution,","venue":null,"work_id":"2aff5f58-2307-4a08-a267-d4c79f0f495a","year":2022},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:15.361067Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:e16675d607b86b6c003c969db327035dd4f5e2de6ac843589b63c983f5212067","observation_id":"ba4e07b3-119c-40ab-9c8f-68d751f7fc65","resolution":{"observed_at":"2026-08-07T00:58:16.523742Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.500861Z","title":"All in tokens: Unifying output space of visual tasks via soft token,","venue":null,"work_id":"4ef0ecc5-1fb4-47a1-a838-5dc4cc313e66","year":2023},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:15.365858Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:9e744d8252f5353abd0426e5edcccd88a5c9f8b4ebb3894b46e07b02171e4ec3","observation_id":"4a694291-6cb9-4f96-b54a-5812b3e445ec","resolution":{"observed_at":"2026-08-07T00:58:16.505966Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.485012Z","title":"Unleashing text-to-image diffusion models for visual perception,","venue":null,"work_id":"a86e169b-0462-4477-8441-64129c4b9d8a","year":2023},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:15.371561Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:14451a75a5b851fdc7b61467f36891fa0e0c61ae951967930a3df9eb698d5236","observation_id":"3a93dd5b-64ed-49f2-a91d-8475ee69467f","resolution":{"observed_at":"2026-08-07T00:58:16.490085Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.466325Z","title":"Iebins: Iterative elastic bins for monocular depth estimation,","venue":null,"work_id":"a660337e-2441-4db9-ae50-c898f14e2970","year":2023},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:15.376522Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:591d54ea738d474d3bd6250d968553b2870dc02f70209ac14e424e334b6df3e7","observation_id":"590fc2eb-f25f-40c2-9cdb-8e79f5bb5c39","resolution":{"observed_at":"2026-08-07T00:58:16.471339Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":{"arxiv_id":"2302.12288","last_updated":"2023-02-23T19:13:10Z","snapshot_observed_at":"2026-07-06T14:55:15.719380Z","submitted_at":"2023-02-23T19:13:10Z","title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.12288","snapshot_observed_at":"2026-08-07T00:58:15.381352Z","title":"Zoedepth: Zero-shot transfer by combining relative and metric depth,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:15.381352Z"},"links":{"cited_paper":"/paper/2302.12288","citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:8f9e5b6ae0f588ce31d357e22a8125106758b1699ccd6acc41a83fcfb34a502b","observation_id":"14afafde-34a7-4452-a463-ddc9c7f14226","resolution":{"observed_at":"2026-08-07T00:58:15.381352Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.451473Z","title":"Depth anything: Unleashing the power of large-scale unlabeled data,","venue":null,"work_id":"3183e83e-4303-40ae-b125-50088e5e6f59","year":2024},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:15.386383Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:f0f818d953031ae2432e96d13bfd844c2dca949692a79d227c7c97b76f1d399d","observation_id":"432f9c79-33b3-437d-8ffc-2b1d37ff60f4","resolution":{"observed_at":"2026-08-07T00:58:16.456167Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"2026-08-07T00:58:15.391152Z","title":"OmniVDiff: Omni controllable video diffusion for generation and understanding,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:15.391152Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:679a73b3701dff6f32a7fbf741978e2cb09024284cec2b857e4ce1a9b7006a2f","observation_id":"f2f143a5-94a8-4b40-a690-52d702f4c191","resolution":{"observed_at":"2026-08-07T00:58:15.391152Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.06886","last_updated":"2025-08-25T02:20:09Z","snapshot_observed_at":"2026-08-06T16:04:56.349386Z","submitted_at":"2024-07-09T14:14:47Z","title":"Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI","version":8},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.06886","snapshot_observed_at":"2026-08-07T00:58:15.396770Z","title":"Aligning cyber space with physical world: A comprehensive survey on embodied AI,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:15.396770Z"},"links":{"cited_paper":"/paper/2407.06886","citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:2f25afccccda5a240bc1ccc1f05800b5cb457440412c7ee3952d81d4492c04ef","observation_id":"1ec6fba2-47c3-47aa-942d-fe44c6ebe1eb","resolution":{"observed_at":"2026-08-07T00:58:15.396770Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.434899Z","title":"Embodied-AI with large models: research and challenges,","venue":null,"work_id":"acc982e7-4345-4c07-bcea-99614a9d9af3","year":2024},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:15.401556Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:b775b6c05727605de02e7f89222c0ebc50e9df78b5072de033dfefedecb40807","observation_id":"e525bddf-281d-4a0f-b12b-aaa207fc65fe","resolution":{"observed_at":"2026-08-07T00:58:16.440566Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.417493Z","title":"Learning task-oriented communication for edge inference: An information bottleneck approach,","venue":null,"work_id":"c3c31cd8-1642-42df-b085-716dfd5ba3c4","year":2022},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:15.406103Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:ad1c1ac6ade00c43dbe222fe6a81d212558357f83cb4449012d59f3d03c8e87c","observation_id":"076dcd3c-efe0-4fa7-9e5a-be0c64ae3eee","resolution":{"observed_at":"2026-08-07T00:58:16.422667Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.401854Z","title":"Empowering smart glasses with large language models: Towards ubiquitous AGI,","venue":null,"work_id":"a34d1494-b733-4552-9a43-a41d9ee0db3d","year":2024},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:15.411095Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:081861498c920b32f7057d9dcfaea7aa80cdfc109a822285c18df1bbf3e10eb2","observation_id":"24646e0b-c3d0-4fdd-a68a-0c3052bb52d3","resolution":{"observed_at":"2026-08-07T00:58:16.406808Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.384664Z","title":"Dres-FL: Dropout-resilient secure federated learning for non-IID clients via secret data sharing,","venue":null,"work_id":"4fbb28fc-92cd-454f-891f-d5cc9d6cec8c","year":2022},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:15.416948Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:567c66583d6602df852b41ee2165f6cecacff3dc272e33e226e4c11f010e38f0","observation_id":"74d56998-f2fd-4fc9-9efa-ff663408fc1b","resolution":{"observed_at":"2026-08-07T00:58:16.391074Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:58:16.368225Z","title":"Federated machine learning: Concept and applications,","venue":null,"work_id":"f1f1a0c5-c83c-49d9-a098-bf7d65c17046","year":2019},"citing_paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches","version":3},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-07T00:58:15.421753Z"},"links":{"citing_paper":"/paper/2506.12479"},"observation_digest":"sha256:14412634570323995325dad7f6c7310fdf60d854ec29c477bdb0ab79a4512c02","observation_id":"9a9c75de-44f4-4013-a307-81f27a1bf141","resolution":{"observed_at":"2026-08-07T00:58:16.373443Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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"}}],"paper":{"arxiv_id":"2506.12479","last_updated":"2025-07-24T18:15:00Z","latest_version":3,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-07T23:55:04.908565Z","submitted_at":"2025-06-14T12:43:07Z","title":"AI Flow: Perspectives, Scenarios, and Approaches"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":53,"verified_exact":2,"verified_fuzzy":45},"total_outbound_references":102},"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 102 outbound references and 9 inbound Pith citation observations for arXiv:2506.12479."}