{"as_of":"2026-08-08T23:07:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ba2811c6085a2b8a800b7f18a641a74e67355f3ead80ad600f180ccbcbed8efc","coverage":[{"denominator":55,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":55,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T17:30:43.988403Z","state":"measured"},{"denominator":55,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":55,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2607.17621/citation-record","integrity":"/paper/2607.17621/integrity","json":"/paper/2607.17621/citation-record.json","paper":"/paper/2607.17621"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.04614","last_updated":"2024-03-14T03:48:08Z","snapshot_observed_at":"2026-08-07T08:53:54.907757Z","submitted_at":"2024-02-07T06:32:50Z","title":"Faithfulness vs. Plausibility: On the (Un)Reliability of Explanations from Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.04614","snapshot_observed_at":"2026-08-01T17:30:38.471354Z","title":"Faithfulness vs","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:38.471354Z"},"links":{"cited_paper":"/paper/2402.04614","citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:a0b88656145bafd9e016d7bd1f7ff30c9d416ba7d3a70692bdabfb47cfdd2765","observation_id":"479a0402-854e-4705-87ba-8af21c455c77","resolution":{"observed_at":"2026-08-01T17:30:38.471354Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.08679","last_updated":"2026-06-16T17:36:22Z","snapshot_observed_at":"2026-08-07T17:12:11.913580Z","submitted_at":"2025-03-11T17:56:30Z","title":"Chain-of-Thought Reasoning In The Wild Is Not Always Faithful","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.08679","snapshot_observed_at":"2026-08-01T17:30:38.509216Z","title":"Chain-of-thought reasoning in the wild is not always faithful.arXiv preprint arXiv:2503.08679, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:38.509216Z"},"links":{"cited_paper":"/paper/2503.08679","citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:c17ede7fbf32f647fb6658cc73771e9ff4e2b363832ec1e6776123e4d18a93a8","observation_id":"05f8c993-b201-41c7-b42c-5b575121ab38","resolution":{"observed_at":"2026-08-01T17:30:38.509216Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.18574","last_updated":"2025-06-11T11:06:08Z","snapshot_observed_at":"2026-08-07T16:00:11.274793Z","submitted_at":"2025-04-22T16:15:19Z","title":"Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.18574","snapshot_observed_at":"2026-08-01T17:30:38.577174Z","title":"Understanding the skill gap in recurrent language models: The role of the gather-and-aggregate mechanism.arXiv preprint arXiv:2504.18574, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:38.577174Z"},"links":{"cited_paper":"/paper/2504.18574","citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:67c37422b169bd06178774e711867d5e09d3f4c32b99d3334e79fafb65bc5816","observation_id":"28064414-db61-4608-b76e-f90c9d093e90","resolution":{"observed_at":"2026-08-01T17:30:38.577174Z","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":"2026-08-01T17:30:38.630128Z","title":"Flex: Continuous agent evolution via forward learning from experience.arXiv preprint arXiv:2511.06449, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:38.630128Z"},"links":{"citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:c112f2e4327be6e38edde0e78448a22e5b0275d9fc3a8da2f23bce0846db628e","observation_id":"f8afff0b-ca96-4f86-9232-3cc4971c846f","resolution":{"observed_at":"2026-08-01T17:30:38.630128Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2512.10696","last_updated":"2026-04-15T07:24:43Z","snapshot_observed_at":"2026-07-06T22:38:45.907386Z","submitted_at":"2025-12-11T14:40:01Z","title":"Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2512.10696","snapshot_observed_at":"2026-08-01T17:30:38.704584Z","title":"Remember me, refine me: A dynamic procedural memory framework for experience-driven agent evolution.arXiv preprint arXiv:2512.10696, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:38.704584Z"},"links":{"cited_paper":"/paper/2512.10696","citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:5a2455a39826068525efded7f8aaa9380f19b3b9aaa2e8c1146648c9255b4a79","observation_id":"da04e492-e9ce-4182-967f-f97e0b74901a","resolution":{"observed_at":"2026-08-01T17:30:38.704584Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.19413","last_updated":"2025-04-28T01:46:35Z","snapshot_observed_at":"2026-08-02T07:32:11.339534Z","submitted_at":"2025-04-28T01:46:35Z","title":"Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.19413","snapshot_observed_at":"2026-08-01T17:30:38.763287Z","title":"Mem0: Building production-ready ai agents with scalable long-term memory.arXiv preprint arXiv:2504.19413, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:38.763287Z"},"links":{"cited_paper":"/paper/2504.19413","citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:ff6ab66166110a2e0a11480281bf03f94fb9ea63f69773ef8b4979d4aa1b8ac1","observation_id":"9c2faf83-96d0-4a58-9631-d3215310c6de","resolution":{"observed_at":"2026-08-01T17:30:38.763287Z","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":"2026-08-01T17:30:38.832900Z","title":"FaithLM: Towards faithful explanations for Large Language Models","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:38.832900Z"},"links":{"citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:b674c499ac4c7f04e3f9556265531131596eccd55bd369bac68720659798b73c","observation_id":"d34d0602-2ea0-41b7-bd3c-41a94f7a5f85","resolution":{"observed_at":"2026-08-01T17:30:38.832900Z","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":"2026-08-01T17:30:38.873434Z","title":"Trajectory-informed memory generation for self-improving agent systems","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:38.873434Z"},"links":{"citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:740c079987b233e6822c181c1cf03692ce619fd310478f3aaa95ab540e81cd61","observation_id":"e122bf77-615a-4cf9-b139-02d86028cd23","resolution":{"observed_at":"2026-08-01T17:30:38.873434Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.06433","last_updated":"2026-04-15T17:21:59Z","snapshot_observed_at":"2026-07-06T22:10:07.250122Z","submitted_at":"2025-08-08T16:20:56Z","title":"Memp: Exploring Agent Procedural Memory","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.06433","snapshot_observed_at":"2026-08-01T17:30:38.940315Z","title":"Memp: Exploring agent procedural memory.arXiv preprint arXiv:2508.06433, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:38.940315Z"},"links":{"cited_paper":"/paper/2508.06433","citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:80cb0aba843be9c3f6b69b4d7c3e9cfe6878f77f1fdf079e946222c30a487ff7","observation_id":"9c5918ad-d802-4ee5-84b7-e1a67f65a5e0","resolution":{"observed_at":"2026-08-01T17:30:38.940315Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.12959","last_updated":"2025-02-05T09:35:38Z","snapshot_observed_at":"2026-07-06T20:24:27.525217Z","submitted_at":"2025-01-22T15:33:17Z","title":"Efficient Prompt Compression with Evaluator Heads for Long-Context Transformer Inference","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.12959","snapshot_observed_at":"2026-08-01T17:30:39.088415Z","title":"Efficient prompt compression with evaluator heads for long-context transformer inference.arXiv preprint arXiv:2501.12959, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:39.088415Z"},"links":{"cited_paper":"/paper/2501.12959","citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:69a0760a1af0454d732ab5864cc4a63e48df4283194c884fcf017e67e5977b1a","observation_id":"b2bc5205-1132-45ea-a1eb-6c31a33bf1c9","resolution":{"observed_at":"2026-08-01T17:30:39.088415Z","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":"2026-08-01T17:30:39.200740Z","title":"The Llama 3 herd of models, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:39.200740Z"},"links":{"citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:4a853f7f1d6ff6d0169971c8a059856e8a0f742d2113ebfca9b39edf5cfae590","observation_id":"cdb775a8-7583-42fc-8e1c-7e99bfd73e5c","resolution":{"observed_at":"2026-08-01T17:30:39.200740Z","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":"2026-08-01T17:30:39.299235Z","title":"Hia- gent: Hierarchical working memory management for solving long-horizon agent tasks with Large Language Model","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:39.299235Z"},"links":{"citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:e66dc50ffd354ded2f6882993537d3e64767b73b60b1e4f96e51655236cc9f74","observation_id":"392e14b1-8503-4a5b-adbe-fdcdc44f4b99","resolution":{"observed_at":"2026-08-01T17:30:39.299235Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2512.13564","last_updated":"2026-01-13T09:33:57Z","snapshot_observed_at":"2026-08-06T08:27:07.254588Z","submitted_at":"2025-12-15T17:22:34Z","title":"Memory in the Age of AI Agents","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2512.13564","snapshot_observed_at":"2026-08-01T17:30:39.381309Z","title":"Memory in the age of ai agents.arXiv preprint arXiv:2512.13564, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:39.381309Z"},"links":{"cited_paper":"/paper/2512.13564","citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:e9846c2904d3e1a72f632b72f51ea8680456794a7c96660ea7274f73fc701c3f","observation_id":"d0aa7a9a-3c58-43bc-b9c1-25b113153eaa","resolution":{"observed_at":"2026-08-01T17:30:39.381309Z","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":"2026-08-01T17:30:39.471539Z","title":"Rap: Retrieval-augmented planning with contextual memory for multimodal llm agents, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:39.471539Z"},"links":{"citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:38327bf11c74cc7aed004b279b918b33b7c50cb260d8d9da86c954fc3b9d7148","observation_id":"e483a10e-5aa9-4af8-8c4d-0fdc1477a332","resolution":{"observed_at":"2026-08-01T17:30:39.471539Z","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":"2026-08-01T17:30:39.620479Z","title":"The atlas of in-context learning: How attention heads shape in-context retrieval augmentation.arXiv preprint arXiv:2505.15807, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:39.620479Z"},"links":{"citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:a624ba3197fd3e68ef3cf566f71ce31aa08feb0af373c3c921ddd79a5e1eb5ff","observation_id":"0a0381f0-4aa0-4707-a10d-cb6729649c58","resolution":{"observed_at":"2026-08-01T17:30:39.620479Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2509.04664","last_updated":"2025-09-04T21:26:31Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-09-04T21:26:31Z","title":"Why Language Models Hallucinate","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2509.04664","snapshot_observed_at":"2026-08-01T17:30:39.759498Z","title":"Why language models hallucinate.arXiv preprint arXiv:2509.04664, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:39.759498Z"},"links":{"cited_paper":"/paper/2509.04664","citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:adb86dbce83468e9cba181238cc0bd86f4517549acc24428821bf35722df7714","observation_id":"4be47560-3989-460a-a90a-288c8743c33d","resolution":{"observed_at":"2026-08-01T17:30:39.759498Z","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":"2026-08-01T17:30:39.874247Z","title":"SnapKV: LLM knows what you are looking for before generation.Advances in Neural Information Processing Systems, 37:22947–22970, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:39.874247Z"},"links":{"citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:10bbac0e685493fef3e3a94e0d5b89b9ca5d013e7cbae7dec7a504421e105f08","observation_id":"59f18bd1-abd2-4d21-9f97-593201649851","resolution":{"observed_at":"2026-08-01T17:30:39.874247Z","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":"2026-08-01T17:30:39.963511Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:39.963511Z"},"links":{"citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:fb98e7d7749f2b67637fd2a5c8a4324c4982f0970f735eb384cef98db359c046","observation_id":"74eaf0e2-365b-4541-818a-e0bcb00e32c1","resolution":{"observed_at":"2026-08-01T17:30:39.963511Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2509.25140","last_updated":"2026-03-16T20:49:28Z","snapshot_observed_at":"2026-08-02T12:08:17.149184Z","submitted_at":"2025-09-29T17:51:03Z","title":"ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2509.25140","snapshot_observed_at":"2026-08-01T17:30:40.060884Z","title":"Reasoningbank: Scaling agent self-evolving with reasoning memory.arXiv preprint arXiv:2509.25140, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:40.060884Z"},"links":{"cited_paper":"/paper/2509.25140","citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:b67bf30194c8cf55e5cff806e4ba03b4e086e863f8310f5043a2deb9d39f4f3a","observation_id":"01dd7a66-cbf1-4599-a432-ced96d71b749","resolution":{"observed_at":"2026-08-01T17:30:40.060884Z","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":"2026-08-01T17:30:40.165410Z","title":"MemGPT: towards LLMs as operating systems, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:40.165410Z"},"links":{"citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:e55eeefdb3e186d971915be4d836e46426e46fa0489cba670d105fcd4b63416b","observation_id":"3d9bead5-7615-4b82-be7d-e583d0ae14e9","resolution":{"observed_at":"2026-08-01T17:30:40.165410Z","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":"2026-08-01T17:30:40.264321Z","title":"Generative agents: Interactive simulacra of human behavior","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:40.264321Z"},"links":{"citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:f9c307428feba9d6ec5d2bc007654a6c1c0f46036756cdf53aa87a6688d7e36a","observation_id":"d19d9922-2b27-4a57-afb5-ae4444307dbf","resolution":{"observed_at":"2026-08-01T17:30:40.264321Z","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":"2026-08-01T17:30:40.362999Z","title":"Qwen2.5 technical report, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:40.362999Z"},"links":{"citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:53b83f4e0a86b1dc97776cd243e978c35c5f2764a70b909fffd07c0b35d5de4d","observation_id":"23a1c8a2-7013-4ee6-b07a-a10bda3bff51","resolution":{"observed_at":"2026-08-01T17:30:40.362999Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.13548","last_updated":"2025-05-10T07:10:46Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-10-20T14:46:48Z","title":"Towards Understanding Sycophancy in Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.13548","snapshot_observed_at":"2026-08-01T17:30:40.457707Z","title":"Towards understanding sycophancy in language models.arXiv preprint arXiv:2310.13548, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:40.457707Z"},"links":{"cited_paper":"/paper/2310.13548","citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:23bce5c9e5ebe34f5de2b743814ed904c75dbc2fe1e5956ee7017ebf53df8554","observation_id":"79bc4887-3836-4c1b-884a-f6dde1455415","resolution":{"observed_at":"2026-08-01T17:30:40.457707Z","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":"2026-08-01T17:30:40.556245Z","title":"Reflexion: Language agents with verbal reinforcement learning.Advances in neural information processing systems, 36:8634–8652, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:40.556245Z"},"links":{"citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:c32f0d2732b8d817fe1d020ac01e0531d7f51d48ce2ecdbaf6b82296d010e92c","observation_id":"dbbf6ce4-7da3-4a89-8c4e-5a0f6c20bdb5","resolution":{"observed_at":"2026-08-01T17:30:40.556245Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.03768","last_updated":"2021-03-14T22:44:38Z","snapshot_observed_at":"2026-08-08T17:40:47.037804Z","submitted_at":"2020-10-08T05:13:36Z","title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.03768","snapshot_observed_at":"2026-08-01T17:30:40.649186Z","title":"ALFWorld: Aligning text and embodied environments for interactive learning.arXiv preprint arXiv:2010.03768, 2020","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:40.649186Z"},"links":{"cited_paper":"/paper/2010.03768","citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:cfcc0075b63f5f1c44ce8a8f37acff3201945fc8b645d3cc4fd5b3aea006571f","observation_id":"d146d816-403b-43a8-8ff2-822071629eaa","resolution":{"observed_at":"2026-08-01T17:30:40.649186Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.13988","last_updated":"2025-05-20T06:36:45Z","snapshot_observed_at":"2026-08-08T01:01:49.125904Z","submitted_at":"2025-05-20T06:36:45Z","title":"The Hallucination Tax of Reinforcement Finetuning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.13988","snapshot_observed_at":"2026-08-01T17:30:40.711089Z","title":"The hallucination tax of reinforcement finetuning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:40.711089Z"},"links":{"cited_paper":"/paper/2505.13988","citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:4c3083b785688ebf09216c89bb5da9377140331d150317e112f1eb06fc98af09","observation_id":"a0a77b3d-b3f9-4a9d-8d75-9ebe41e5c81a","resolution":{"observed_at":"2026-08-01T17:30:40.711089Z","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":"2026-08-01T17:30:40.801227Z","title":"Trial and Error: Exploration-based trajectory optimization of LLM agents","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:40.801227Z"},"links":{"citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:5464829b53d8247b4b9b3e32bbef62990889ff9b4e3f37220cb65489c8ce01d5","observation_id":"7d59c59f-1886-408b-b5c5-6c749d8c5ef0","resolution":{"observed_at":"2026-08-01T17:30:40.801227Z","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":"2026-08-01T17:30:40.933678Z","title":"Dynamic Cheatsheet: Test-time learning with adaptive memory","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:40.933678Z"},"links":{"citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:e03a152d723fbcdb2a129fd9be860cf2d5c639d187921a7b2ae58bdd0c8baf83","observation_id":"f31e7284-9de7-435c-82b4-3879478b1040","resolution":{"observed_at":"2026-08-01T17:30:40.933678Z","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":"2026-08-01T17:30:41.024537Z","title":"Language Models don’t always say what they think: Unfaithful explanations in Chain-of-Thought prompting.Advances in Neural Information Processing Systems, 36:74952–74965, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:41.024537Z"},"links":{"citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:901e8d01bde4c9de6d06281cefb84ddb2d0eb0760ab736b0e811b6afa4bde1ae","observation_id":"039cc6ee-f04a-41a7-b2bc-7daf54258319","resolution":{"observed_at":"2026-08-01T17:30:41.024537Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.16291","last_updated":"2023-10-19T16:27:03Z","snapshot_observed_at":"2026-08-07T08:29:46.650400Z","submitted_at":"2023-05-25T17:46:38Z","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.16291","snapshot_observed_at":"2026-08-01T17:30:41.117828Z","title":"V oyager: An open-ended embodied agent with Large Language Models.arXiv preprint arXiv:2305.16291, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:41.117828Z"},"links":{"cited_paper":"/paper/2305.16291","citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:edaa7f89907b7ab5f4f0e209782e46541ed10d2e9e2dd1090c6712c18abe7c29","observation_id":"eda68e6e-fade-4734-a729-72ebb5dde806","resolution":{"observed_at":"2026-08-01T17:30:41.117828Z","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":"2026-08-01T17:30:41.250230Z","title":"ScienceWorld: Is your agent smarter than a 5th grader? InProceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 11279–11298, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:41.250230Z"},"links":{"citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:b61cc332b031552b7fa184def1c9695cf64a4ac97d3d51bde6a4be8c20f0b1cf","observation_id":"c8b660c2-e162-4d0e-9669-34062222d7d0","resolution":{"observed_at":"2026-08-01T17:30:41.250230Z","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":"2026-08-01T17:30:41.386980Z","title":"Quito: Accelerat- ing long-context reasoning through query-guided context compression","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:41.386980Z"},"links":{"citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:cb1865ed6fbe3bddcbe71343b2dad32ae6bbc4f0c67bf232c96b4a703f7be4b1","observation_id":"c2f0532a-d5c9-4a84-97be-6dc0f7855454","resolution":{"observed_at":"2026-08-01T17:30:41.386980Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.07429","last_updated":"2024-09-11T17:21:00Z","snapshot_observed_at":"2026-08-07T15:35:11.892405Z","submitted_at":"2024-09-11T17:21:00Z","title":"Agent Workflow Memory","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.07429","snapshot_observed_at":"2026-08-01T17:30:41.523862Z","title":"Agent workflow memory","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:41.523862Z"},"links":{"cited_paper":"/paper/2409.07429","citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:825a8319bf475747d2b2a43a1a3b23ac48c6bd2eab98675fc9f5a9f602443a62","observation_id":"54c31288-3f7c-4520-86be-d691642621f8","resolution":{"observed_at":"2026-08-01T17:30:41.523862Z","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":"2026-08-01T17:30:41.655199Z","title":"Retrieval head mecha- nistically explains long-context factuality","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:41.655199Z"},"links":{"citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:a4f466f263be3952e216b8e16c41c78a6bf25ad271b615fbd6f4f72592f6a3e9","observation_id":"1b63929e-0fa4-4cdf-80f9-e29bbf162303","resolution":{"observed_at":"2026-08-01T17:30:41.655199Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.12110","snapshot_observed_at":"2026-08-01T17:30:41.747583Z","title":"A-mem: Agentic memory for LLM agents.arXiv preprint arXiv:2502.12110, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:41.747583Z"},"links":{"cited_paper":"/paper/2502.12110","citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:4d1f0715be9011bcb467ec681fd7605b1c53b31ca4b97baed02fb8d7b63992b1","observation_id":"6f21cf4f-dd9e-46a9-b853-d97c51b72469","resolution":{"observed_at":"2026-08-01T17:30:41.747583Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.19828","last_updated":"2026-01-14T14:21:21Z","snapshot_observed_at":"2026-07-06T22:19:28.487854Z","submitted_at":"2025-08-27T12:26:55Z","title":"Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.19828","snapshot_observed_at":"2026-08-01T17:30:41.878456Z","title":"Memory-r1: Enhancing large language model agents to manage and utilize memories via reinforcement learning.arXiv preprint arXiv:2508.19828, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:41.878456Z"},"links":{"cited_paper":"/paper/2508.19828","citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:30bbc5c3df48d319788f2764955900c7729887f02395816b41710b9c168e6e59","observation_id":"3c3a1c51-1f6a-4009-a740-674313c20ff4","resolution":{"observed_at":"2026-08-01T17:30:41.878456Z","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":"2026-08-01T17:30:42.012497Z","title":"Webshop: Towards scalable real-world web interaction with grounded language agents.Advances in Neural Information Processing Systems, 35:20744–20757, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:42.012497Z"},"links":{"citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:69d6e15ec28eba5159f64ed1085fc29ac5ea539b67f86f81eea6a69dfb435f3c","observation_id":"8b5bc7fb-2c0b-4dcc-9d64-42f6325b3e21","resolution":{"observed_at":"2026-08-01T17:30:42.012497Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.03629","last_updated":"2023-03-10T01:00:17Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-10-06T01:00:32Z","title":"ReAct: Synergizing Reasoning and Acting in Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.03629","snapshot_observed_at":"2026-08-01T17:30:42.140986Z","title":"React: Synergizing reasoning and acting in Language Models.arXiv preprint arXiv:2210.03629, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:42.140986Z"},"links":{"cited_paper":"/paper/2210.03629","citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:11158fbc6343f4e63b6d013d69ba57cd25e9cd00d3ca2d6af16819dd1b2229d5","observation_id":"b805a31f-f3a6-4e69-91d5-aaa33607f156","resolution":{"observed_at":"2026-08-01T17:30:42.140986Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2510.04618","last_updated":"2026-03-29T09:18:02Z","snapshot_observed_at":"2026-07-06T22:31:49.574184Z","submitted_at":"2025-10-06T09:30:18Z","title":"Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2510.04618","snapshot_observed_at":"2026-08-01T17:30:42.258401Z","title":"Agentic context engineering: Evolving contexts for self-improving language models.arXiv preprint arXiv:2510.04618, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:42.258401Z"},"links":{"cited_paper":"/paper/2510.04618","citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:36cd2f36727b678c42bf4349cc328f3db5a5509e014c4b71d7ff837c180bf631","observation_id":"e45b9afe-c5ff-4088-9e4c-1b91040fcc7d","resolution":{"observed_at":"2026-08-01T17:30:42.258401Z","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":"2026-08-01T17:30:42.325130Z","title":"Query-focused Retrieval Heads improve long-context reasoning and re-ranking","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:42.325130Z"},"links":{"citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:88ce801827c7c0be10ec0e9189a8db3cad010f0415e28cddeefa26abdbf4fe89","observation_id":"97bb8b18-76a3-45ef-8b8d-19331e15ebe9","resolution":{"observed_at":"2026-08-01T17:30:42.325130Z","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":"2026-08-01T17:30:42.422977Z","title":"H2o: Heavy-hitter oracle for efficient generative inference of large language models.Advances in Neural Information Processing Systems, 36:34661–34710, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:42.422977Z"},"links":{"citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:07c38f412ac2004aa582a63fb62b9779d5f58a1881f6d1541780be31f08e8eb9","observation_id":"eccd9d55-df92-46bb-8b00-fba43fcd77d5","resolution":{"observed_at":"2026-08-01T17:30:42.422977Z","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":"2026-08-01T17:30:42.521621Z","title":"Expel: LLM agents are experiential learners","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:42.521621Z"},"links":{"citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:0733c782352c4011ef01115d925ab2976a545df27341e720e79979e532809835","observation_id":"11d9e3dc-80c6-4d37-9db3-9de4f107c59a","resolution":{"observed_at":"2026-08-01T17:30:42.521621Z","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":"2026-08-01T17:30:42.620258Z","title":"Leveraging attention to effectively compress prompts for long-context llms","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:42.620258Z"},"links":{"citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:ad16fc6b914855abb082692f6ebb6881c74390440adb8a0788eb05b9b9beb313","observation_id":"74f36396-6d0b-4b53-bd95-467fe6c35d61","resolution":{"observed_at":"2026-08-01T17:30:42.620258Z","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":"2026-08-01T17:30:42.714906Z","title":"Synapse: Trajectory-as-exemplar prompting with memory for computer control","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:42.714906Z"},"links":{"citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:82a0b1204f04ccf2e3534a4a94ab364323d14ab227404682872c540111ad9cf7","observation_id":"ead344e0-0dec-49e4-9efd-599f6403e1c0","resolution":{"observed_at":"2026-08-01T17:30:42.714906Z","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":"2026-08-01T17:30:42.815020Z","title":"Memorybank: Enhancing Large Language Models with long-term memory","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:42.815020Z"},"links":{"citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:21c127c4c571eb8baa6f27754900917f6d040e3177eca0b0cbc67e625bfcea93","observation_id":"e1655d92-b614-4b39-aed5-f0ebf839a3b9","resolution":{"observed_at":"2026-08-01T17:30:42.815020Z","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":"2026-08-01T17:30:42.882971Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:42.882971Z"},"links":{"citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:bbba24b2a57bf609a1e4ff7862fa00121fdf90a623c916c3506d7f1f2dd12d9e","observation_id":"e979c0da-42d7-4b9d-a28c-b1cefc79cf62","resolution":{"observed_at":"2026-08-01T17:30:42.882971Z","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":"2026-08-01T17:30:42.973158Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:42.973158Z"},"links":{"citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:5981ae95dddbb936f13a798433bed162b91aed2020ead0b7e197cef54024b8f5","observation_id":"afce07aa-e111-46d2-a3ae-ae503311b5d7","resolution":{"observed_at":"2026-08-01T17:30:42.973158Z","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":"2026-08-01T17:30:43.038451Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:43.038451Z"},"links":{"citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:e639e41bbf5b7082d90571c921753fd550bc532e3a60012fd1532f945aafa493","observation_id":"a3cbe607-763b-4bb1-8d3e-7c599f6d5e7a","resolution":{"observed_at":"2026-08-01T17:30:43.038451Z","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":"2026-08-01T17:30:43.134775Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:43.134775Z"},"links":{"citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:b6213fca1342ecbe9b65fd488a034360d6ad8805c699ae53c73e03e7d09dd971","observation_id":"06a29e2d-7491-4227-8770-47c15f80d4e3","resolution":{"observed_at":"2026-08-01T17:30:43.134775Z","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":"2026-08-01T17:30:43.236904Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:43.236904Z"},"links":{"citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:78acb3e3bef588a5de1ce4faf055784f9520c911405986f0a4779c0a873325b8","observation_id":"5312ff60-7f92-463a-b113-4aae39238a37","resolution":{"observed_at":"2026-08-01T17:30:43.236904Z","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":"2026-08-01T17:30:43.358630Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:43.358630Z"},"links":{"citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:8499506c01ca4ddd148ef4826a7d969b2ec763fafd13697c9b965e83de979abd","observation_id":"c86d67a7-32e7-4bb2-85ef-166645c368ad","resolution":{"observed_at":"2026-08-01T17:30:43.358630Z","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":"2026-08-01T17:30:43.540889Z","title":"[Erroneous Step Context] From [Task Trajectory]","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:43.540889Z"},"links":{"citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:5c9e7fb9675250c103235498d175a166a72df3176dcf3c44cb65574169d1385a","observation_id":"bc6883ae-4f4e-4e81-ac57-9be74ad369c3","resolution":{"observed_at":"2026-08-01T17:30:43.540889Z","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":"2026-08-01T17:30:43.707296Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:43.707296Z"},"links":{"citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:ae72c89a815b23568b21f0f0e805085240f28da63106e8d4977fc92d7206231f","observation_id":"87a8765c-bbee-4e09-a888-b43edea6359f","resolution":{"observed_at":"2026-08-01T17:30:43.707296Z","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":"2026-08-01T17:30:43.854983Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:43.854983Z"},"links":{"citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:0a513181e7f836d63a354c905676d91b312fb6539636dc67b428d353d2348e0b","observation_id":"76341979-0b42-4356-bc40-235beedb251b","resolution":{"observed_at":"2026-08-01T17:30:43.854983Z","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":"2026-08-01T17:30:43.988403Z","title":"[/INST] Thought","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-01T17:30:43.988403Z"},"links":{"citing_paper":"/paper/2607.17621"},"observation_digest":"sha256:62ca83d39e28648490cce2e0e521c4cdd8f9b9e13b0cae5a9f5eb38ca8c72ac3","observation_id":"d03a45c1-c6ad-4155-ac9a-74e75fe8ae82","resolution":{"observed_at":"2026-08-01T17:30:43.988403Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.17621","last_updated":"2026-07-20T07:17:50Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-07T22:58:38.461590Z","submitted_at":"2026-07-20T07:17:50Z","title":"Mechanistic Attention Guidance for Agent Memory Refinement"},"reference_resolution":{"displayed":55,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":55,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":55},"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 55 of 55 outbound references and 0 inbound Pith citation observations for arXiv:2607.17621."}