{"as_of":"2026-08-08T13:46:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:46fca93155ca9adec64037a8bbfcd6521ef7968a45e1a52b565c01b15ea8f7c0","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":20,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":20,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":20,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":20,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T14:51:51.721100Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-04T12:59:53.065299Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2403.02181","last_updated":"2024-07-09T11:59:01Z","snapshot_observed_at":"2026-07-06T17:39:16.540553Z","submitted_at":"2024-03-04T16:23:58Z","title":"Not All Layers of LLMs Are Necessary During Inference","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.02181","snapshot_observed_at":"2026-08-07T14:51:51.721100Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.17420","last_updated":"2025-05-23T03:10:11Z","snapshot_observed_at":"2026-08-08T01:16:58.792089Z","submitted_at":"2025-05-23T03:10:11Z","title":"DASH: Input-Aware Dynamic Layer Skipping for Efficient LLM Inference with Markov Decision Policies","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-07T14:51:51.721100Z"},"links":{"cited_paper":"/paper/2403.02181","citing_paper":"/paper/2505.17420"},"observation_digest":"sha256:58591b38cde20d1e6d3d387a624c8c93b55c748ff68ce94e9660551e4bc94195","observation_id":"65a5f1c8-cb1f-41ac-8afe-021d6ac540f2","resolution":{"observed_at":"2026-08-07T14:51:51.721100Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.02181","last_updated":"2024-07-09T11:59:01Z","snapshot_observed_at":"2026-07-06T17:39:16.540553Z","submitted_at":"2024-03-04T16:23:58Z","title":"Not All Layers of LLMs Are Necessary During Inference","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.02181","snapshot_observed_at":"2026-08-07T14:42:10.919440Z","title":"Not all layers of llms are necessary during inference","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.17998","last_updated":"2025-05-23T15:03:51Z","snapshot_observed_at":"2026-08-07T14:34:42.149071Z","submitted_at":"2025-05-23T15:03:51Z","title":"TRACE for Tracking the Emergence of Semantic Representations in Transformers","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T14:42:10.919440Z"},"links":{"cited_paper":"/paper/2403.02181","citing_paper":"/paper/2505.17998"},"observation_digest":"sha256:80e00eca0783121c891dedb5b13882f30635f912f1fab5d1c1cde754e4f53281","observation_id":"06a79309-8851-411c-b92e-49e741f4e1eb","resolution":{"observed_at":"2026-08-07T14:42:10.919440Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.02181","last_updated":"2024-07-09T11:59:01Z","snapshot_observed_at":"2026-07-06T17:39:16.540553Z","submitted_at":"2024-03-04T16:23:58Z","title":"Not All Layers of LLMs Are Necessary During Inference","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.02181","snapshot_observed_at":"2026-08-07T14:40:48.884963Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.18132","last_updated":"2025-06-17T09:32:43Z","snapshot_observed_at":"2026-08-07T14:32:46.481734Z","submitted_at":"2025-05-23T17:41:54Z","title":"BiggerGait: Unlocking Gait Recognition with Layer-wise Representations from Large Vision Models","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T14:40:48.884963Z"},"links":{"cited_paper":"/paper/2403.02181","citing_paper":"/paper/2505.18132"},"observation_digest":"sha256:1c663b39b004195a5d7a9a59bf2f5d1e86e620be9fa6b9cbe4ed5999c018b60b","observation_id":"1af3c9ca-d5ba-4759-89d8-a1783b92252d","resolution":{"observed_at":"2026-08-07T14:40:48.884963Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.02181","last_updated":"2024-07-09T11:59:01Z","snapshot_observed_at":"2026-07-06T17:39:16.540553Z","submitted_at":"2024-03-04T16:23:58Z","title":"Not All Layers of LLMs Are Necessary During Inference","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.02181","snapshot_observed_at":"2026-08-07T13:40:16.842408Z","title":"Not all layers of llms are necessary during inference","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.21594","last_updated":"2025-05-27T14:55:16Z","snapshot_observed_at":"2026-08-07T13:28:18.126229Z","submitted_at":"2025-05-27T14:55:16Z","title":"Fast and Cost-effective Speculative Edge-Cloud Decoding with Early Exits","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T13:40:16.842408Z"},"links":{"cited_paper":"/paper/2403.02181","citing_paper":"/paper/2505.21594"},"observation_digest":"sha256:97234cad1fbed23b421f18ee38ba3afd74665d9054bb1880f6e97ad9e58bf5f8","observation_id":"9883a815-5f21-4f95-a1eb-855dcf203db1","resolution":{"observed_at":"2026-08-07T13:40:16.842408Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.02181","last_updated":"2024-07-09T11:59:01Z","snapshot_observed_at":"2026-07-06T17:39:16.540553Z","submitted_at":"2024-03-04T16:23:58Z","title":"Not All Layers of LLMs Are Necessary During Inference","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.02181","snapshot_observed_at":"2026-08-07T13:51:17.229319Z","title":"URL https: //doi.org/10.48550/arXiv.2403.02181","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.23807","last_updated":"2025-06-03T03:06:29Z","snapshot_observed_at":"2026-08-07T13:44:15.426026Z","submitted_at":"2025-05-27T07:35:00Z","title":"DLP: Dynamic Layerwise Pruning in Large Language Models","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T13:51:17.229319Z"},"links":{"cited_paper":"/paper/2403.02181","citing_paper":"/paper/2505.23807"},"observation_digest":"sha256:d8baf6743b307cf489d34e7f09a1e8a575f9601c68ef3a5c24fa2c6db5001df5","observation_id":"f806f274-382b-4650-88c7-eb6b5c29eb11","resolution":{"observed_at":"2026-08-07T13:51:17.229319Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.02181","last_updated":"2024-07-09T11:59:01Z","snapshot_observed_at":"2026-07-06T17:39:16.540553Z","submitted_at":"2024-03-04T16:23:58Z","title":"Not All Layers of LLMs Are Necessary During Inference","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.02181","snapshot_observed_at":"2026-08-07T10:51:51.474200Z","title":"Not all layers of llms are necessary during inference, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.04179","last_updated":"2025-06-04T17:26:31Z","snapshot_observed_at":"2026-08-07T23:11:03.041831Z","submitted_at":"2025-06-04T17:26:31Z","title":"SkipGPT: Dynamic Layer Pruning Reinvented with Token Awareness and Module Decoupling","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-07T10:51:51.474200Z"},"links":{"cited_paper":"/paper/2403.02181","citing_paper":"/paper/2506.04179"},"observation_digest":"sha256:d43fd677457134245a6fe01df85ee9728cc64e74a4d356cf132a4721e957d1d1","observation_id":"758b547f-5e71-42ed-8775-8fc551ed1a5e","resolution":{"observed_at":"2026-08-07T10:51:51.474200Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.02181","last_updated":"2024-07-09T11:59:01Z","snapshot_observed_at":"2026-07-06T17:39:16.540553Z","submitted_at":"2024-03-04T16:23:58Z","title":"Not All Layers of LLMs Are Necessary During Inference","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.02181","snapshot_observed_at":"2026-08-06T22:40:53.825000Z","title":"Not All Layers of LLMs Are Necessary During Inference , July 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.21103","last_updated":"2025-06-26T09:01:19Z","snapshot_observed_at":"2026-08-06T22:31:44.262653Z","submitted_at":"2025-06-26T09:01:19Z","title":"Learning to Skip the Middle Layers of Transformers","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-06T22:40:53.825000Z"},"links":{"cited_paper":"/paper/2403.02181","citing_paper":"/paper/2506.21103"},"observation_digest":"sha256:58915ba74c9076b8771cd03ca5a702ad07c3193bc7ea28300a885f7c29a9c619","observation_id":"ea168e31-aac8-45c6-9ada-e8dd34e8e2af","resolution":{"observed_at":"2026-08-06T22:40:53.825000Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.02181","last_updated":"2024-07-09T11:59:01Z","snapshot_observed_at":"2026-07-06T17:39:16.540553Z","submitted_at":"2024-03-04T16:23:58Z","title":"Not All Layers of LLMs Are Necessary During Inference","version":3},"cited_work":{"arxiv_id":"2403.02181","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.02181","snapshot_observed_at":"2026-07-04T12:59:53.065299Z","title":"arXiv preprint arXiv:2403.02181 , year=","venue":null,"work_id":"4da1f717-0221-4710-9b2f-84d7cd8bfb60","year":2024},"citing_paper":{"arxiv_id":"2507.05387","last_updated":"2026-04-03T19:07:42Z","snapshot_observed_at":"2026-08-03T04:01:26.875993Z","submitted_at":"2025-07-07T18:18:51Z","title":"The Generalization Ridge: Information Flow in Natural Language Generation","version":5},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-19T05:30:38.612759Z"},"links":{"cited_paper":"/paper/2403.02181","citing_paper":"/paper/2507.05387"},"observation_digest":"sha256:2303db6fdc2897b26d401415baa3f99d9dc5f1fe4b58e6d4238260f199df984a","observation_id":"7c52b842-cf4b-45e7-8193-9c8129f8ed96","resolution":{"observed_at":"2026-05-19T05:32:05.666881Z","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":"2403.02181","last_updated":"2024-07-09T11:59:01Z","snapshot_observed_at":"2026-07-06T17:39:16.540553Z","submitted_at":"2024-03-04T16:23:58Z","title":"Not All Layers of LLMs Are Necessary During Inference","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.02181","snapshot_observed_at":"2026-08-06T18:38:59.698293Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.08064","last_updated":"2026-06-06T18:51:46Z","snapshot_observed_at":"2026-08-06T18:26:57.432317Z","submitted_at":"2025-07-10T16:47:25Z","title":"PUMA: Layer-Pruned Language Model for Efficient Unified Multimodal Retrieval with Modality-Adaptive Learning","version":4},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T18:38:59.698293Z"},"links":{"cited_paper":"/paper/2403.02181","citing_paper":"/paper/2507.08064"},"observation_digest":"sha256:316248cfb6fc1021a21e73bcf437c0b548b2dd4db76bd5f7b9993fc73fc9093c","observation_id":"efce8ef1-28f1-416c-b1fe-982961308b2c","resolution":{"observed_at":"2026-08-06T18:38:59.698293Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.02181","last_updated":"2024-07-09T11:59:01Z","snapshot_observed_at":"2026-07-06T17:39:16.540553Z","submitted_at":"2024-03-04T16:23:58Z","title":"Not All Layers of LLMs Are Necessary During Inference","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.02181","snapshot_observed_at":"2026-07-13T19:34:58.789459Z","title":"Not all layers of llms are necessary during inference.arXiv preprint arXiv:2403.02181, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.23483","last_updated":"2026-07-06T05:32:03Z","snapshot_observed_at":"2026-08-07T04:45:34.480037Z","submitted_at":"2026-03-24T17:45:47Z","title":"SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-13T19:34:58.789459Z"},"links":{"cited_paper":"/paper/2403.02181","citing_paper":"/paper/2603.23483"},"observation_digest":"sha256:7b4c16d8d14a50373c3609182183b800f9ab937adb43118746dbbfb8a527de0b","observation_id":"cc2b33b2-b2ca-4e61-ad20-7f2e725eeba2","resolution":{"observed_at":"2026-07-13T19:34:58.789459Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.02181","last_updated":"2024-07-09T11:59:01Z","snapshot_observed_at":"2026-07-06T17:39:16.540553Z","submitted_at":"2024-03-04T16:23:58Z","title":"Not All Layers of LLMs Are Necessary During Inference","version":3},"cited_work":{"arxiv_id":"2403.02181","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.02181","snapshot_observed_at":"2026-07-04T12:59:53.065299Z","title":"arXiv preprint arXiv:2403.02181 , year=","venue":null,"work_id":"4da1f717-0221-4710-9b2f-84d7cd8bfb60","year":2024},"citing_paper":{"arxiv_id":"2604.06393","last_updated":"2026-04-07T19:23:47Z","snapshot_observed_at":"2026-08-04T11:45:10.032776Z","submitted_at":"2026-04-07T19:23:47Z","title":"ART: Attention Replacement Technique to Improve Factuality in LLMs","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-10T19:48:22.430128Z"},"links":{"cited_paper":"/paper/2403.02181","citing_paper":"/paper/2604.06393"},"observation_digest":"sha256:9d6cc0ad5de695d1ab37ba2fc3e3ed1c85aa12ef055e00dff419aea87dc6be58","observation_id":"a3022ec2-1dec-4774-86cc-f6a000948b01","resolution":{"observed_at":"2026-05-10T22:30:50.936267Z","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":"2403.02181","last_updated":"2024-07-09T11:59:01Z","snapshot_observed_at":"2026-07-06T17:39:16.540553Z","submitted_at":"2024-03-04T16:23:58Z","title":"Not All Layers of LLMs Are Necessary During Inference","version":3},"cited_work":{"arxiv_id":"2403.02181","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.02181","snapshot_observed_at":"2026-07-04T12:59:53.065299Z","title":"arXiv preprint arXiv:2403.02181 , year=","venue":null,"work_id":"4da1f717-0221-4710-9b2f-84d7cd8bfb60","year":2024},"citing_paper":{"arxiv_id":"2604.18592","last_updated":"2026-03-27T15:27:58Z","snapshot_observed_at":"2026-08-05T01:52:00.445011Z","submitted_at":"2026-03-27T15:27:58Z","title":"Two-dimensional early exit optimisation of LLM inference","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-14T22:59:07.065193Z"},"links":{"cited_paper":"/paper/2403.02181","citing_paper":"/paper/2604.18592"},"observation_digest":"sha256:462955666fcf54c2ecdf6671d5466c4ad5d84423011c15172ba694b3d94c9d87","observation_id":"98f661ad-d752-4acd-b51e-5aba33f1dca8","resolution":{"observed_at":"2026-05-14T22:59:34.249383Z","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":"2403.02181","last_updated":"2024-07-09T11:59:01Z","snapshot_observed_at":"2026-07-06T17:39:16.540553Z","submitted_at":"2024-03-04T16:23:58Z","title":"Not All Layers of LLMs Are Necessary During Inference","version":3},"cited_work":{"arxiv_id":"2403.02181","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.02181","snapshot_observed_at":"2026-07-04T12:59:53.065299Z","title":"arXiv preprint arXiv:2403.02181 , year=","venue":null,"work_id":"4da1f717-0221-4710-9b2f-84d7cd8bfb60","year":2024},"citing_paper":{"arxiv_id":"2604.20503","last_updated":"2026-04-22T12:44:39Z","snapshot_observed_at":"2026-07-06T23:06:55.880484Z","submitted_at":"2026-04-22T12:44:39Z","title":"FASER: Fine-Grained Phase Management for Speculative Decoding in Dynamic LLM Serving","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-09T22:56:19.734262Z"},"links":{"cited_paper":"/paper/2403.02181","citing_paper":"/paper/2604.20503"},"observation_digest":"sha256:496d8c1899fae29973829b0ff308aca5e507a4c13fd7e4fcc158f2f82c51494d","observation_id":"c809a79f-d64b-4827-96d9-10c3cbd014b6","resolution":{"observed_at":"2026-05-09T22:59:17.732430Z","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":"2403.02181","last_updated":"2024-07-09T11:59:01Z","snapshot_observed_at":"2026-07-06T17:39:16.540553Z","submitted_at":"2024-03-04T16:23:58Z","title":"Not All Layers of LLMs Are Necessary During Inference","version":3},"cited_work":{"arxiv_id":"2403.02181","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.02181","snapshot_observed_at":"2026-07-04T12:59:53.065299Z","title":"arXiv preprint arXiv:2403.02181 , year=","venue":null,"work_id":"4da1f717-0221-4710-9b2f-84d7cd8bfb60","year":2024},"citing_paper":{"arxiv_id":"2605.23033","last_updated":"2026-05-21T20:58:42Z","snapshot_observed_at":"2026-07-06T23:33:19.375527Z","submitted_at":"2026-05-21T20:58:42Z","title":"Uncovering the Latent Potential of Deep Intermediate Representations","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-05-25T05:36:24.743558Z"},"links":{"cited_paper":"/paper/2403.02181","citing_paper":"/paper/2605.23033"},"observation_digest":"sha256:e3ba30183bb2d732668772d1995a43e36a26f5c531ad7bf7350abe1d0f8dda58","observation_id":"4d52b39b-3349-45cc-b7bc-24048a299838","resolution":{"observed_at":"2026-05-25T05:36:39.238068Z","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":"2403.02181","last_updated":"2024-07-09T11:59:01Z","snapshot_observed_at":"2026-07-06T17:39:16.540553Z","submitted_at":"2024-03-04T16:23:58Z","title":"Not All Layers of LLMs Are Necessary During Inference","version":3},"cited_work":{"arxiv_id":"2403.02181","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.02181","snapshot_observed_at":"2026-07-04T12:59:53.065299Z","title":"arXiv preprint arXiv:2403.02181 , year=","venue":null,"work_id":"4da1f717-0221-4710-9b2f-84d7cd8bfb60","year":2024},"citing_paper":{"arxiv_id":"2605.27033","last_updated":"2026-05-26T13:55:08Z","snapshot_observed_at":"2026-08-06T04:40:28.567525Z","submitted_at":"2026-05-26T13:55:08Z","title":"Tracing Computation Density in LLMs","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-29T18:20:33.014687Z"},"links":{"cited_paper":"/paper/2403.02181","citing_paper":"/paper/2605.27033"},"observation_digest":"sha256:ea1c872f25383d3e11fb0aae8cfbf88e093cfc46601f86a6a8701740a6598201","observation_id":"580f8cd7-5742-4426-907a-3b50a66e464c","resolution":{"observed_at":"2026-06-29T18:23:50.641403Z","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":"2403.02181","last_updated":"2024-07-09T11:59:01Z","snapshot_observed_at":"2026-07-06T17:39:16.540553Z","submitted_at":"2024-03-04T16:23:58Z","title":"Not All Layers of LLMs Are Necessary During Inference","version":3},"cited_work":{"arxiv_id":"2403.02181","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.02181","snapshot_observed_at":"2026-07-04T12:59:53.065299Z","title":"arXiv preprint arXiv:2403.02181 , year=","venue":null,"work_id":"4da1f717-0221-4710-9b2f-84d7cd8bfb60","year":2024},"citing_paper":{"arxiv_id":"2606.05586","last_updated":"2026-06-04T02:04:15Z","snapshot_observed_at":"2026-08-07T01:36:04.675661Z","submitted_at":"2026-06-04T02:04:15Z","title":"BMCR: Adaptive Backbone Module Composition via Reinforcement Learning for Remote Sensing Object Detection","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-06-28T02:53:19.538957Z"},"links":{"cited_paper":"/paper/2403.02181","citing_paper":"/paper/2606.05586"},"observation_digest":"sha256:a3f4b7a982662d613506f465e0e9199eba01594b268fa9b32f82c95f8c94db83","observation_id":"0172b41d-5f07-47d1-98bc-ea5c03dfda5f","resolution":{"observed_at":"2026-07-02T11:46:56.207806Z","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":"2403.02181","last_updated":"2024-07-09T11:59:01Z","snapshot_observed_at":"2026-07-06T17:39:16.540553Z","submitted_at":"2024-03-04T16:23:58Z","title":"Not All Layers of LLMs Are Necessary During Inference","version":3},"cited_work":{"arxiv_id":"2403.02181","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.02181","snapshot_observed_at":"2026-07-04T12:59:53.065299Z","title":"arXiv preprint arXiv:2403.02181 , year=","venue":null,"work_id":"4da1f717-0221-4710-9b2f-84d7cd8bfb60","year":2024},"citing_paper":{"arxiv_id":"2606.06906","last_updated":"2026-06-05T04:49:37Z","snapshot_observed_at":"2026-08-02T10:42:01.638389Z","submitted_at":"2026-06-05T04:49:37Z","title":"EASE-TTT: Evidence-Aligned Selective Test-Time Training for Long-Context Question Answering","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-06-27T22:05:00.537690Z"},"links":{"cited_paper":"/paper/2403.02181","citing_paper":"/paper/2606.06906"},"observation_digest":"sha256:7a3b839bd9bbe7a81de358bf5df99773c64226153c2e62015344b59bc470cce2","observation_id":"45e80d92-669e-4507-b095-7fb32045213b","resolution":{"observed_at":"2026-07-02T17:17:15.073583Z","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":"2403.02181","last_updated":"2024-07-09T11:59:01Z","snapshot_observed_at":"2026-07-06T17:39:16.540553Z","submitted_at":"2024-03-04T16:23:58Z","title":"Not All Layers of LLMs Are Necessary During Inference","version":3},"cited_work":{"arxiv_id":"2403.02181","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.02181","snapshot_observed_at":"2026-07-04T12:59:53.065299Z","title":"arXiv preprint arXiv:2403.02181 , year=","venue":null,"work_id":"4da1f717-0221-4710-9b2f-84d7cd8bfb60","year":2024},"citing_paper":{"arxiv_id":"2606.26620","last_updated":"2026-06-25T05:33:03Z","snapshot_observed_at":"2026-08-07T13:16:24.780198Z","submitted_at":"2026-06-25T05:33:03Z","title":"Discovering Millions of Interpretable Features with Sparse Autoencoders","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-06-26T05:34:00.754172Z"},"links":{"cited_paper":"/paper/2403.02181","citing_paper":"/paper/2606.26620"},"observation_digest":"sha256:b1aeeb9d138547cab5f5495389545f0940afef2042155404e84e082e616353d9","observation_id":"1ecd1bd1-d70a-4a0d-ab9f-b80bb7f08137","resolution":{"observed_at":"2026-07-04T12:59:53.066618Z","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":"2403.02181","last_updated":"2024-07-09T11:59:01Z","snapshot_observed_at":"2026-07-06T17:39:16.540553Z","submitted_at":"2024-03-04T16:23:58Z","title":"Not All Layers of LLMs Are Necessary During Inference","version":3},"cited_work":{"arxiv_id":"2403.02181","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.02181","snapshot_observed_at":"2026-07-04T12:59:53.065299Z","title":"arXiv preprint arXiv:2403.02181 , year=","venue":null,"work_id":"4da1f717-0221-4710-9b2f-84d7cd8bfb60","year":2024},"citing_paper":{"arxiv_id":"2606.27743","last_updated":"2026-06-26T05:48:21Z","snapshot_observed_at":"2026-08-05T16:07:01.090621Z","submitted_at":"2026-06-26T05:48:21Z","title":"End-to-End Dynamic Sparsity for Resource-Adaptive LLM Inference","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-06-29T03:27:08.181406Z"},"links":{"cited_paper":"/paper/2403.02181","citing_paper":"/paper/2606.27743"},"observation_digest":"sha256:bb26e362050ec11c35a8a0d55eb72ea46eab13b8b112aae5440b64bcd8a43167","observation_id":"3abb809e-ae2c-4581-b83b-b07fd8c08c75","resolution":{"observed_at":"2026-07-01T17:35:52.028452Z","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":"2403.02181","last_updated":"2024-07-09T11:59:01Z","snapshot_observed_at":"2026-07-06T17:39:16.540553Z","submitted_at":"2024-03-04T16:23:58Z","title":"Not All Layers of LLMs Are Necessary During Inference","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.02181","snapshot_observed_at":"2026-08-02T13:18:20.471944Z","title":"arXiv preprint arXiv:2403.02181 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.21613","last_updated":"2026-05-25T03:54:43Z","snapshot_observed_at":"2026-08-05T19:56:10.288136Z","submitted_at":"2026-05-25T03:54:43Z","title":"The Hard Decision Layer: Evidence for Committed Inference in Transformers","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-02T13:18:20.471944Z"},"links":{"cited_paper":"/paper/2403.02181","citing_paper":"/paper/2607.21613"},"observation_digest":"sha256:a3c55036f9fd7a2e7a6554140013bd9a3935ad5265cadb52e7dcd6a211d86b8c","observation_id":"0a491cf3-9029-4d8c-8950-f06722cc2fed","resolution":{"observed_at":"2026-08-02T13:18:20.471944Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2403.02181/citation-record","integrity":"/paper/2403.02181/integrity","json":"/paper/2403.02181/citation-record.json","paper":"/paper/2403.02181"},"outbound":[],"paper":{"arxiv_id":"2403.02181","last_updated":"2024-07-09T11:59:01Z","latest_version":3,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T17:39:16.540553Z","submitted_at":"2024-03-04T16:23:58Z","title":"Not All Layers of LLMs Are Necessary During Inference"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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 0 of 0 outbound references and 20 inbound Pith citation observations for arXiv:2403.02181."}