{"as_of":"2026-08-05T11:32:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c1ca72838b085655bdc221293e14372071026250f03edadda6933eeb04edaecb","coverage":[{"denominator":13,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":13,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-10T17:21:59.224547Z","state":"measured"},{"denominator":23,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":23,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-05T06:32:48.257954+00:00","state":"measured"},{"denominator":10,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":10,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T13:36:48.927975Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-07-04T15:19:55.999542Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2604.07798","last_updated":"2026-04-22T11:39:55Z","snapshot_observed_at":"2026-08-03T00:22:12.229929Z","submitted_at":"2026-04-09T04:51:07Z","title":"Lightweight LLM Agent Memory with Small Language Models","version":3},"cited_work":{"arxiv_id":"2604.07798","doi":null,"metadata_source":"pith","pith_arxiv_id":"2604.07798","snapshot_observed_at":"2026-07-04T15:19:55.999542Z","title":"Lightweight LLM Agent Memory with Small Language Models","venue":"cs.AI","work_id":"d479f2d7-04ef-4ea0-abe8-dc76e2cd22ee","year":2026},"citing_paper":{"arxiv_id":"2604.12610","last_updated":"2026-04-14T11:36:29Z","snapshot_observed_at":"2026-08-02T05:17:11.221332Z","submitted_at":"2026-04-14T11:36:29Z","title":"Transforming External Knowledge into Triplets for Enhanced Retrieval in RAG of LLMs","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-10T15:42:59.063869Z"},"links":{"cited_paper":"/paper/2604.07798","citing_paper":"/paper/2604.12610"},"observation_digest":"sha256:5cb758f0974c045193517773a8202c846a930975ee9465d125b86ed4ca95d78c","observation_id":"8ccdd440-6999-4d84-8569-280062f40933","resolution":{"observed_at":"2026-05-11T09:56:05.334639Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2604.07798","last_updated":"2026-04-22T11:39:55Z","snapshot_observed_at":"2026-08-03T00:22:12.229929Z","submitted_at":"2026-04-09T04:51:07Z","title":"Lightweight LLM Agent Memory with Small Language Models","version":3},"cited_work":{"arxiv_id":"2604.07798","doi":null,"metadata_source":"pith","pith_arxiv_id":"2604.07798","snapshot_observed_at":"2026-07-04T15:19:55.999542Z","title":"Lightweight LLM Agent Memory with Small Language Models","venue":"cs.AI","work_id":"d479f2d7-04ef-4ea0-abe8-dc76e2cd22ee","year":2026},"citing_paper":{"arxiv_id":"2604.19351","last_updated":"2026-05-05T06:39:27Z","snapshot_observed_at":"2026-07-06T23:06:02.635464Z","submitted_at":"2026-04-21T11:33:24Z","title":"DASH-KV: Accelerating Long-Context LLM Inference via Asymmetric KV Cache Hashing","version":4},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-05-10T02:23:37.859259Z"},"links":{"cited_paper":"/paper/2604.07798","citing_paper":"/paper/2604.19351"},"observation_digest":"sha256:d6b4b83e563608e84562258a8d00bddd9cd955d841d901edd3d0bc2b69210893","observation_id":"27a43a41-eaf9-4779-9bee-fff1dfb05ac5","resolution":{"observed_at":"2026-05-11T13:06:03.391106Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2604.07798","last_updated":"2026-04-22T11:39:55Z","snapshot_observed_at":"2026-08-03T00:22:12.229929Z","submitted_at":"2026-04-09T04:51:07Z","title":"Lightweight LLM Agent Memory with Small Language Models","version":3},"cited_work":{"arxiv_id":"2604.07798","doi":null,"metadata_source":"pith","pith_arxiv_id":"2604.07798","snapshot_observed_at":"2026-07-04T15:19:55.999542Z","title":"Lightweight LLM Agent Memory with Small Language Models","venue":"cs.AI","work_id":"d479f2d7-04ef-4ea0-abe8-dc76e2cd22ee","year":2026},"citing_paper":{"arxiv_id":"2604.21251","last_updated":"2026-05-15T10:37:48Z","snapshot_observed_at":"2026-08-03T02:32:14.992671Z","submitted_at":"2026-04-23T03:42:41Z","title":"CAP: Controllable Alignment Prompting for Unlearning in LLMs","version":3},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-05-09T21:55:12.005455Z"},"links":{"cited_paper":"/paper/2604.07798","citing_paper":"/paper/2604.21251"},"observation_digest":"sha256:a262c8b1dd9603eac27d4438898ef194d13106f1a12cac4ba0aeb4e2367068fc","observation_id":"ebda1b2c-7c16-4e28-99b2-ba241792ab01","resolution":{"observed_at":"2026-05-11T14:26:02.555086Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2604.07798","last_updated":"2026-04-22T11:39:55Z","snapshot_observed_at":"2026-08-03T00:22:12.229929Z","submitted_at":"2026-04-09T04:51:07Z","title":"Lightweight LLM Agent Memory with Small Language Models","version":3},"cited_work":{"arxiv_id":"2604.07798","doi":null,"metadata_source":"pith","pith_arxiv_id":"2604.07798","snapshot_observed_at":"2026-07-04T15:19:55.999542Z","title":"Lightweight LLM Agent Memory with Small Language Models","venue":"cs.AI","work_id":"d479f2d7-04ef-4ea0-abe8-dc76e2cd22ee","year":2026},"citing_paper":{"arxiv_id":"2604.23270","last_updated":"2026-07-06T07:22:31Z","snapshot_observed_at":"2026-07-12T18:23:55.772199Z","submitted_at":"2026-04-25T12:24:04Z","title":"CAP-CoT: Cycle Adversarial Prompt for Improving Chain of Thoughts in LLM Reasoning","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-05-08T08:12:26.110376Z"},"links":{"cited_paper":"/paper/2604.07798","citing_paper":"/paper/2604.23270"},"observation_digest":"sha256:c03ac59f05f7a6d01d2ecef88a233b6f9397287212b2e46f3dadc7adfd5bf5ea","observation_id":"df697c23-10a8-452f-b3b7-d55d96733e60","resolution":{"observed_at":"2026-05-11T20:41:14.396012Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2604.07798","last_updated":"2026-04-22T11:39:55Z","snapshot_observed_at":"2026-08-03T00:22:12.229929Z","submitted_at":"2026-04-09T04:51:07Z","title":"Lightweight LLM Agent Memory with Small Language Models","version":3},"cited_work":{"arxiv_id":"2604.07798","doi":null,"metadata_source":"pith","pith_arxiv_id":"2604.07798","snapshot_observed_at":"2026-07-04T15:19:55.999542Z","title":"Lightweight LLM Agent Memory with Small Language Models","venue":"cs.AI","work_id":"d479f2d7-04ef-4ea0-abe8-dc76e2cd22ee","year":2026},"citing_paper":{"arxiv_id":"2604.23277","last_updated":"2026-04-25T12:40:54Z","snapshot_observed_at":"2026-07-06T23:09:34.300163Z","submitted_at":"2026-04-25T12:40:54Z","title":"From Similarity to Structure: Training-free LLM Context Compression with Hybrid Graph Priors","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-08T08:26:15.223253Z"},"links":{"cited_paper":"/paper/2604.07798","citing_paper":"/paper/2604.23277"},"observation_digest":"sha256:f64d6a4486b19d36831c632ee2e5d6c34d9d151867756e2aae369e00243bb9ba","observation_id":"d8a0fe8d-902f-4cad-81fa-93ac95070785","resolution":{"observed_at":"2026-05-11T20:36:11.721575Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2604.07798","last_updated":"2026-04-22T11:39:55Z","snapshot_observed_at":"2026-08-03T00:22:12.229929Z","submitted_at":"2026-04-09T04:51:07Z","title":"Lightweight LLM Agent Memory with Small Language Models","version":3},"cited_work":{"arxiv_id":"2604.07798","doi":null,"metadata_source":"pith","pith_arxiv_id":"2604.07798","snapshot_observed_at":"2026-07-04T15:19:55.999542Z","title":"Lightweight LLM Agent Memory with Small Language Models","venue":"cs.AI","work_id":"d479f2d7-04ef-4ea0-abe8-dc76e2cd22ee","year":2026},"citing_paper":{"arxiv_id":"2604.23293","last_updated":"2026-06-25T12:46:57Z","snapshot_observed_at":"2026-07-06T23:09:34.300163Z","submitted_at":"2026-04-25T13:15:29Z","title":"Partial exploiters sustain cooperation: the hump-shaped strategy stably coexists with unconditional cooperators","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-07-04T15:12:08.612215Z"},"links":{"cited_paper":"/paper/2604.07798","citing_paper":"/paper/2604.23293"},"observation_digest":"sha256:b4a996b7055602487a0bdae126532b7e601a814c423e206a26d23de1ca7c3c78","observation_id":"551059ad-eaaf-4094-825c-311faf5838df","resolution":{"observed_at":"2026-07-04T15:19:56.000824Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2604.07798","last_updated":"2026-04-22T11:39:55Z","snapshot_observed_at":"2026-08-03T00:22:12.229929Z","submitted_at":"2026-04-09T04:51:07Z","title":"Lightweight LLM Agent Memory with Small Language Models","version":3},"cited_work":{"arxiv_id":"2604.07798","doi":null,"metadata_source":"pith","pith_arxiv_id":"2604.07798","snapshot_observed_at":"2026-07-04T15:19:55.999542Z","title":"Lightweight LLM Agent Memory with Small Language Models","venue":"cs.AI","work_id":"d479f2d7-04ef-4ea0-abe8-dc76e2cd22ee","year":2026},"citing_paper":{"arxiv_id":"2605.25971","last_updated":"2026-05-26T04:49:24Z","snapshot_observed_at":"2026-07-06T23:35:50.787324Z","submitted_at":"2026-05-25T15:47:21Z","title":"Anticipate and Learn: Unleashing Idle-Time Compute in Proactive Agents","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-06-29T21:44:44.789852Z"},"links":{"cited_paper":"/paper/2604.07798","citing_paper":"/paper/2605.25971"},"observation_digest":"sha256:8c9a21128d2ffa239eeed95187c6f0d85449105b04fe2f708d4d79bf6415479a","observation_id":"1110bb69-e6da-4a44-bdf1-5079b81c5543","resolution":{"observed_at":"2026-06-29T21:54:00.013941Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2604.07798","last_updated":"2026-04-22T11:39:55Z","snapshot_observed_at":"2026-08-03T00:22:12.229929Z","submitted_at":"2026-04-09T04:51:07Z","title":"Lightweight LLM Agent Memory with Small Language Models","version":3},"cited_work":{"arxiv_id":"2604.07798","doi":null,"metadata_source":"pith","pith_arxiv_id":"2604.07798","snapshot_observed_at":"2026-07-04T15:19:55.999542Z","title":"Lightweight LLM Agent Memory with Small Language Models","venue":"cs.AI","work_id":"d479f2d7-04ef-4ea0-abe8-dc76e2cd22ee","year":2026},"citing_paper":{"arxiv_id":"2606.01240","last_updated":"2026-05-31T13:42:36Z","snapshot_observed_at":"2026-08-02T06:51:34.323150Z","submitted_at":"2026-05-31T13:42:36Z","title":"Efficient RAG with Intent-Aware Retrieval and Semantics-Preserving Chunking","version":1},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-06-28T17:38:21.242007Z"},"links":{"cited_paper":"/paper/2604.07798","citing_paper":"/paper/2606.01240"},"observation_digest":"sha256:91719161646559dc8beeb34900e736b5e31dcd53baf0b1ff630ea86eb7024b9e","observation_id":"a6aab863-2241-4326-bbc8-7c828335a62e","resolution":{"observed_at":"2026-07-01T20:56:13.813745Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2604.07798","last_updated":"2026-04-22T11:39:55Z","snapshot_observed_at":"2026-08-03T00:22:12.229929Z","submitted_at":"2026-04-09T04:51:07Z","title":"Lightweight LLM Agent Memory with Small Language Models","version":3},"cited_work":{"arxiv_id":"2604.07798","doi":null,"metadata_source":"pith","pith_arxiv_id":"2604.07798","snapshot_observed_at":"2026-07-04T15:19:55.999542Z","title":"Lightweight LLM Agent Memory with Small Language Models","venue":"cs.AI","work_id":"d479f2d7-04ef-4ea0-abe8-dc76e2cd22ee","year":2026},"citing_paper":{"arxiv_id":"2606.21189","last_updated":"2026-06-19T07:57:43Z","snapshot_observed_at":"2026-08-02T14:28:20.314745Z","submitted_at":"2026-06-19T07:57:43Z","title":"TF-SNO: Time-Frequency Gated Spectral Neural Operators for Learning Non-Stationary Partial Differential Equations","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-06-26T14:29:01.766578Z"},"links":{"cited_paper":"/paper/2604.07798","citing_paper":"/paper/2606.21189"},"observation_digest":"sha256:d8a2012f11549adb26985ffadf95679306c95af5acbdf3e7dcb12c0c83f54bcd","observation_id":"c0c31924-6337-4d18-8115-731e7e65e0c7","resolution":{"observed_at":"2026-07-04T06:29:37.176450Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2604.07798","last_updated":"2026-04-22T11:39:55Z","snapshot_observed_at":"2026-08-03T00:22:12.229929Z","submitted_at":"2026-04-09T04:51:07Z","title":"Lightweight LLM Agent Memory with Small Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2604.07798","snapshot_observed_at":"2026-08-02T13:36:48.927975Z","title":"Lightweight LLM agent memory with small language models,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.18265","last_updated":"2026-05-20T03:33:10Z","snapshot_observed_at":"2026-08-05T08:32:13.022312Z","submitted_at":"2026-05-20T03:33:10Z","title":"State Compression in Two-Agent LLM Relays: A Closed-World Study of Constraint Preservation","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-02T13:36:48.927975Z"},"links":{"cited_paper":"/paper/2604.07798","citing_paper":"/paper/2607.18265"},"observation_digest":"sha256:122e82b344c118d3e4fa19e8d1a254cef5442d973333a7806831c94585cca6ca","observation_id":"2590a806-36d0-4c1f-98b3-1e89cc96911e","resolution":{"observed_at":"2026-08-02T13:36:48.927975Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2604.07798/citation-record","integrity":"/paper/2604.07798/integrity","json":"/paper/2604.07798/citation-record.json","paper":"/paper/2604.07798"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2310.11511","last_updated":"2023-10-17T18:18:32Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-10-17T18:18:32Z","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","version":1},"cited_work":{"arxiv_id":"2310.11511","doi":"10.48550/arxiv.2310.11511","metadata_source":"pith","pith_arxiv_id":"2310.11511","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","venue":"cs.CL","work_id":"7316de4a-d07d-41de-88ee-509f9b52e462","year":2023},"citing_paper":{"arxiv_id":"2604.07798","last_updated":"2026-04-22T11:39:55Z","snapshot_observed_at":"2026-08-03T00:22:12.229929Z","submitted_at":"2026-04-09T04:51:07Z","title":"Lightweight LLM Agent Memory with Small Language Models","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-10T17:21:59.224547Z"},"links":{"cited_paper":"/paper/2310.11511","citing_paper":"/paper/2604.07798"},"observation_digest":"sha256:71627c12624a406a3237d063a9670e53fd65fd54a1222d5b3a1bf9027bff6d70","observation_id":"627bae43-4199-4910-aeae-9d108b66333a","resolution":{"observed_at":"2026-05-12T14:15:11.779838Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"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":"2502.13923","doi":"10.48550/arxiv.2502.13923","metadata_source":"pith","pith_arxiv_id":"2502.13923","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Qwen2.5-VL Technical Report","venue":"cs.CV","work_id":"69dffacb-bfe8-442d-be86-48624c60426f","year":2025},"citing_paper":{"arxiv_id":"2604.07798","last_updated":"2026-04-22T11:39:55Z","snapshot_observed_at":"2026-08-03T00:22:12.229929Z","submitted_at":"2026-04-09T04:51:07Z","title":"Lightweight LLM Agent Memory with Small Language Models","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-10T17:21:59.224547Z"},"links":{"cited_paper":"/paper/2502.13923","citing_paper":"/paper/2604.07798"},"observation_digest":"sha256:8a601f02c01e351125f44dac03b9be4cd99fdb3cd56da106d7be05d9c0cd52ea","observation_id":"279d783b-4282-4158-bdec-398e9eb07fc1","resolution":{"observed_at":"2026-05-11T06:56:04.135034Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-07-12T05:19:13.082554+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-12T05:19:13.082554+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-07-06T18:55:11.576666Z","submitted_at":"2024-07-31T17:54:27Z","title":"The Llama 3 Herd of Models","version":3},"cited_work":{"arxiv_id":"2407.21783","doi":"10.1016/s0749-0720(15","metadata_source":"pith","pith_arxiv_id":"2407.21783","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"The Llama 3 Herd of Models","venue":"cs.AI","work_id":"1549a635-88af-4ac1-acfe-51ae7bb53345","year":2024},"citing_paper":{"arxiv_id":"2604.07798","last_updated":"2026-04-22T11:39:55Z","snapshot_observed_at":"2026-08-03T00:22:12.229929Z","submitted_at":"2026-04-09T04:51:07Z","title":"Lightweight LLM Agent Memory with Small Language Models","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-10T17:21:59.224547Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2604.07798"},"observation_digest":"sha256:d5129755e60480eb2f9ea6b1abc5917faaa55d8b328a5bce2470fbadbeeb040f","observation_id":"87c25150-710b-4fa8-8478-9e55fa661d48","resolution":{"observed_at":"2026-05-11T06:56:04.141093Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.02716","last_updated":"2024-02-05T04:25:24Z","snapshot_observed_at":"2026-07-06T17:25:14.115360Z","submitted_at":"2024-02-05T04:25:24Z","title":"Understanding the planning of LLM agents: A survey","version":1},"cited_work":{"arxiv_id":"2402.02716","doi":"10.48550/arxiv.2402.02716","metadata_source":"pith","pith_arxiv_id":"2402.02716","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Understanding the planning of LLM agents: A survey","venue":"cs.AI","work_id":"6daa5311-7f56-401d-94db-17be43e95cbc","year":2024},"citing_paper":{"arxiv_id":"2604.07798","last_updated":"2026-04-22T11:39:55Z","snapshot_observed_at":"2026-08-03T00:22:12.229929Z","submitted_at":"2026-04-09T04:51:07Z","title":"Lightweight LLM Agent Memory with Small Language Models","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-10T17:21:59.224547Z"},"links":{"cited_paper":"/paper/2402.02716","citing_paper":"/paper/2604.07798"},"observation_digest":"sha256:067d7d95ac9c3233eefa08633b29eef5ba7f2439a547ebb7dc6812b8da31719b","observation_id":"8ca85c01-2e09-439e-a378-a44651e800ae","resolution":{"observed_at":"2026-05-13T18:12:57.765583Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-07-11T20:20:12.598477+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T20:20:12.598477+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.21276","last_updated":"2024-10-25T17:43:01Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-10-25T17:43:01Z","title":"GPT-4o System Card","version":1},"cited_work":{"arxiv_id":"2410.21276","doi":"10.1177/15248380231178756","metadata_source":"pith","pith_arxiv_id":"2410.21276","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"GPT-4o System Card","venue":"cs.CL","work_id":"f37bf1c7-4964-4e56-9762-d20da8d9009f","year":2024},"citing_paper":{"arxiv_id":"2604.07798","last_updated":"2026-04-22T11:39:55Z","snapshot_observed_at":"2026-08-03T00:22:12.229929Z","submitted_at":"2026-04-09T04:51:07Z","title":"Lightweight LLM Agent Memory with Small Language Models","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-10T17:21:59.224547Z"},"links":{"cited_paper":"/paper/2410.21276","citing_paper":"/paper/2604.07798"},"observation_digest":"sha256:d5d18d7e53f9c7ecc319a5e79e4f52c86adb1fb21c16167057562e966db74af1","observation_id":"eb9e65b7-0381-4b37-b628-f60b9eb7f1c6","resolution":{"observed_at":"2026-05-11T06:56:04.099387Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2406.13144","doi":"10.48550/arxiv.2406.13144","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"arXiv preprint arXiv:2406.13144 , year=","venue":"arXiv (Cornell University)","work_id":"294c911f-5519-46ad-8c80-a61d1549e263","year":2024},"citing_paper":{"arxiv_id":"2604.07798","last_updated":"2026-04-22T11:39:55Z","snapshot_observed_at":"2026-08-03T00:22:12.229929Z","submitted_at":"2026-04-09T04:51:07Z","title":"Lightweight LLM Agent Memory with Small Language Models","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-10T17:21:59.224547Z"},"links":{"citing_paper":"/paper/2604.07798"},"observation_digest":"sha256:ee9fa6d100f28769fb61c83e706a35c3ae24d8979c7bf4160ea109a12d46639c","observation_id":"339250f1-1c62-44d2-ae65-2bc96251eb30","resolution":{"observed_at":"2026-05-11T06:56:04.108728Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"InForty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27","venue":null,"work_id":"c850d14a-bb6a-42d2-9a3b-c29a5d8c80aa","year":2024},"citing_paper":{"arxiv_id":"2604.07798","last_updated":"2026-04-22T11:39:55Z","snapshot_observed_at":"2026-08-03T00:22:12.229929Z","submitted_at":"2026-04-09T04:51:07Z","title":"Lightweight LLM Agent Memory with Small Language Models","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-10T17:21:59.224547Z"},"links":{"citing_paper":"/paper/2604.07798"},"observation_digest":"sha256:6858bb29eb5254a24c81108bc1290218722dabcbb5c3008b916b225bdb44e5a8","observation_id":"70af2f17-40dc-4d9d-af21-0f919dacc0a2","resolution":{"observed_at":"2026-05-17T10:49:28.132266Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"In Proceedings of the 5th Workshop on Trustworthy NLP (TrustNLP 2025), pages 56–65","venue":null,"work_id":"3b417afb-df40-41a2-b1ee-53cb612cdd4f","year":2025},"citing_paper":{"arxiv_id":"2604.07798","last_updated":"2026-04-22T11:39:55Z","snapshot_observed_at":"2026-08-03T00:22:12.229929Z","submitted_at":"2026-04-09T04:51:07Z","title":"Lightweight LLM Agent Memory with Small Language Models","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-10T17:21:59.224547Z"},"links":{"citing_paper":"/paper/2604.07798"},"observation_digest":"sha256:429f6529f3f66905135b0d98df6807875708fac91f7162acc5025cdbfc774e72","observation_id":"f852c3dd-f5c3-4d96-bd74-7efa37fbda12","resolution":{"observed_at":"2026-05-17T10:49:28.123249Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"7a6b2c13-83d6-42b8-a950-094fceb6f8bd","year":2024},"citing_paper":{"arxiv_id":"2604.07798","last_updated":"2026-04-22T11:39:55Z","snapshot_observed_at":"2026-08-03T00:22:12.229929Z","submitted_at":"2026-04-09T04:51:07Z","title":"Lightweight LLM Agent Memory with Small Language Models","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-10T17:21:59.224547Z"},"links":{"citing_paper":"/paper/2604.07798"},"observation_digest":"sha256:db3b53d16895799eaac116826e4a6ed27c318f08cefda0a5638e91d8ef977769","observation_id":"f94481a5-c547-4bb3-87b1-3725ddd9a0db","resolution":{"observed_at":"2026-05-17T10:49:28.126165Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"Haoran Tan, Zeyu Zhang, Chen Ma, Xu Chen, Quanyu Dai, and Zhenhua Dong","venue":null,"work_id":"3d1e3d68-eb5d-4b3e-aa39-bf6c2a70e2a4","year":2025},"citing_paper":{"arxiv_id":"2604.07798","last_updated":"2026-04-22T11:39:55Z","snapshot_observed_at":"2026-08-03T00:22:12.229929Z","submitted_at":"2026-04-09T04:51:07Z","title":"Lightweight LLM Agent Memory with Small Language Models","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-10T17:21:59.224547Z"},"links":{"citing_paper":"/paper/2604.07798"},"observation_digest":"sha256:3c2fe5dea9559ecf1b4e5a3db8f0ed66e5d91c94e64e4d74aac13ffb10549b3c","observation_id":"c9a59cdc-e953-4fc3-81fb-5511f1bf83a2","resolution":{"observed_at":"2026-05-17T10:49:28.129213Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"InFindings of the Association for Computational Linguistics, ACL 2025, Vienna, Aus- tria, July 27 - August 1, 2025, pages 19336–19352","venue":null,"work_id":"9d7a8d9d-2039-4eba-8a08-c2689dde4c74","year":2025},"citing_paper":{"arxiv_id":"2604.07798","last_updated":"2026-04-22T11:39:55Z","snapshot_observed_at":"2026-08-03T00:22:12.229929Z","submitted_at":"2026-04-09T04:51:07Z","title":"Lightweight LLM Agent Memory with Small Language Models","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-10T17:21:59.224547Z"},"links":{"citing_paper":"/paper/2604.07798"},"observation_digest":"sha256:02276a4c496666f0acbb817fd691eb0538ca30d2516dc7ee4b672a7ae1c5def2","observation_id":"564debf8-4c1d-47a3-9658-08cf4fe7757c","resolution":{"observed_at":"2026-05-17T10:49:28.119655Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2603.12933","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-01T20:56:13.846421Z","title":"arXiv preprint arXiv:2603.12933 , year=","venue":null,"work_id":"79cd164b-33c6-4907-be00-7fe474726c96","year":2026},"citing_paper":{"arxiv_id":"2604.07798","last_updated":"2026-04-22T11:39:55Z","snapshot_observed_at":"2026-08-03T00:22:12.229929Z","submitted_at":"2026-04-09T04:51:07Z","title":"Lightweight LLM Agent Memory with Small Language Models","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-10T17:21:59.224547Z"},"links":{"citing_paper":"/paper/2604.07798"},"observation_digest":"sha256:799468c3720a42938bb56f821347468caa4e86109e7ced11b97cd118cfc5bf6f","observation_id":"5ee62c3c-388f-4f54-8f4f-d656713d3b84","resolution":{"observed_at":"2026-05-11T06:56:04.117217Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.12110","last_updated":"2025-10-08T01:46:37Z","snapshot_observed_at":"2026-08-03T02:27:06.991396Z","submitted_at":"2025-02-17T18:36:14Z","title":"A-MEM: Agentic Memory for LLM Agents","version":11},"cited_work":{"arxiv_id":"2502.12110","doi":"10.48550/arxiv.2502.12110","metadata_source":"pith","pith_arxiv_id":"2502.12110","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"A-MEM: Agentic Memory for LLM Agents","venue":"cs.CL","work_id":"3b98feb2-fdb1-479a-bbe4-2c298a4592e2","year":2025},"citing_paper":{"arxiv_id":"2604.07798","last_updated":"2026-04-22T11:39:55Z","snapshot_observed_at":"2026-08-03T00:22:12.229929Z","submitted_at":"2026-04-09T04:51:07Z","title":"Lightweight LLM Agent Memory with Small Language Models","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-10T17:21:59.224547Z"},"links":{"cited_paper":"/paper/2502.12110","citing_paper":"/paper/2604.07798"},"observation_digest":"sha256:fd1bbfeabe5580c7a7f131878f64e688ee825eb9d75ba60ddb5a91dfdd2eb908","observation_id":"f0b63809-0471-420d-9997-f5de4f59c546","resolution":{"observed_at":"2026-05-11T06:56:04.092975Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2604.07798","last_updated":"2026-04-22T11:39:55Z","latest_version":3,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-03T00:22:12.229929Z","submitted_at":"2026-04-09T04:51:07Z","title":"Lightweight LLM Agent Memory with Small Language Models"},"reference_resolution":{"displayed":13,"state_counts":{"malformed_identifier":0,"metadata_mismatch":5,"parse_uncertain":0,"unresolved":1,"verified_exact":3,"verified_fuzzy":4},"total_outbound_references":13},"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":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"thesis":"As of 5 August 2026, this Paper Citation Record lists 13 of 13 outbound references and 10 inbound Pith citation observations for arXiv:2604.07798."}