{"as_of":"2026-08-07T05:37:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:fd4c07e8d6415b324dcd7c35481cae973cad9948f976c72de6a3a4f052a406f7","coverage":[{"denominator":42,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":42,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-15T10:31:25.051835Z","state":"measured"},{"denominator":42,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":42,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-06T06:34:29.942622+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/2606.27201/citation-record","integrity":"/paper/2606.27201/integrity","json":"/paper/2606.27201/citation-record.json","paper":"/paper/2606.27201"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:4ae74cbcf180cd1a22f08b402b49ac767ed1572e966b74c43f780f25b0d6a7a9","observation_id":"520c3c54-7a98-41b8-9265-03e395bf7a57","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:960c9edc3f9b4087aff63af455019d46eaf83be1a5f36ef92d04f0d84679fdf2","observation_id":"6ee4fda5-e176-46d2-a942-32e99d95c615","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":"Cencetti, G","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:aa6e7fa0e262338ec51b42bd91fedcdd477c58976e6624c414dc52303037cccd","observation_id":"1c524981-0574-44a6-8ef5-16d685f250c1","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:2e2dc83b1d22cabe4083d860e3e0d8cc3e9dc737a0a77865897722c3633595fc","observation_id":"f6bd73b7-8aba-4dff-b24b-507f0da30e2f","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:15743e43a76bb98e427a105ba1009ec910b486af922f8a9f35a177ab2a1d806d","observation_id":"4f0928e2-b186-4683-ac1f-f325d7395bc0","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:35a79736e38f612aa0799b25195805de59b6bd1e42528dbd830af4ab4715bd66","observation_id":"d37b6ec4-a3c1-4ec7-8e43-7130e0875d07","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2606.00557","last_updated":"2026-05-30T06:15:44Z","snapshot_observed_at":"2026-07-06T23:41:15.410587Z","submitted_at":"2026-05-30T06:15:44Z","title":"Normalized Relevance Measure as a Unifying Framework to Explain Neural Network Latent Structures","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2606.00557","snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":"Xiong, T","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"cited_paper":"/paper/2606.00557","citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:5323c50f94f2d34f2b2c9b9a1dcfe66028108efd8f744e610fe1c5ef4d179648","observation_id":"d4eadb0c-6cf6-498e-a82c-1f120fd9748d","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":"Schnake, O","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:c352287d5bb53ef872556ea303d3727996a8e6440feab2c1cdffd4ae650a1a9f","observation_id":"6d80c281-d650-44ed-a327-55507b97a194","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":null,"venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:40f13174c89782e7135cd51fa85715bf78d13d657be23f7705f566519756c371","observation_id":"050aa00c-4f60-4088-9ef4-37c7f5d61fa8","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":"Achtibat, S","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:af9cef6c35746abc2e64faa064524919a78d7914b7ded137ed8a61baa1e1f451","observation_id":"ce57f40a-cc1e-4be4-8b28-165d48c1c199","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":"Kauffmann, J","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:e4cf7c1e135c87a00040f8f3c04ecfc9c1f673db2b96a874f3a9bdd3ebdcce72","observation_id":"d9a9b7a5-c95d-4c4c-9810-621d979cca2d","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":"what is relevant in a text document?","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:565ac7e6ab518bc41aa33461e3932296a35a9d164ad7e571760f2581d2556ab3","observation_id":"5f94e150-f809-4229-a590-7f9809d63658","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:13f2303777dfadb43897592d2369e7069700a835782152632f5585ee74d37808","observation_id":"bbc8ee31-a19a-4e51-a508-ad2549400357","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":"Esders, T","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:59a0355b1b7a4cc9e53e48f2bad531066cf4872138074771320a54bf82652565","observation_id":"43014ce4-f04b-4d31-88e7-56afb0f3d9f9","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":"Montavon, S","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:30538e3d6af05f9f49b8a101a00fca66c191c066096d5d8d91d4e22e050f6361","observation_id":"fe6ef388-1513-40e6-bedd-7e347e090867","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":"Samek, G","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:411ef7b1d5a7324466f8905d8b2df8aca7b414ab5a9973ce60c64b29661f9b87","observation_id":"8494d49a-4fa9-4c28-a1ed-1b31e20006ac","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":"Montavon, A","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:4134c01db0e3acef05a7855cb47842a6161c7c1cbedd453a0ffe50764f8764b2","observation_id":"42515b84-195b-4063-a4ef-8db7c58be812","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":"Arras, J","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:8992cec871eea99d5bc134987cbf13996d58355aa4b48b222d82b8f6751acd65","observation_id":"d9491ecb-e927-4c86-b932-3f3f64520197","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":"Xiong, T","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:ec4ddb951248b58d8b6a64a6b13c9e5d7375166e3c8cb0e4c99def88cebdf0e3","observation_id":"75e020ff-a98f-4367-8370-974d8431b74f","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:5f791fd3ec4b3b9123f2bd65b012bbc4599e2768c80aa501d8a014a62953a5da","observation_id":"32fb36c2-8ca9-43d9-8ade-429cfd201ade","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:e7c6ad12eeeea9fd5231d948e40cea428a0c38c47f024475d12611e7bb1fdb0e","observation_id":"2406b24c-dfb5-4a8b-b0a3-4a87740cf368","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:34dc582b2e31838f930e6d7bd11940c4a12b1415ea7967545f83b8803e7621fc","observation_id":"960e5a44-6549-4fd8-8652-a354ac49631f","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:ec23d2070932ea8808660c7d7bda9b638225f43255d092dd3559a7c99a08540e","observation_id":"833da687-5e5c-4568-b60e-ac7999c41a8c","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:c2c5d664cd556b04f2fff1ea2976791eea4d09b21cfac114a06681377b5aa7f3","observation_id":"8b73e4ab-c9a5-4377-9806-7edbe216a7b3","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:81f94bc6952ff0a39ff40b9ab6669ca874d8491458e413438f33ecb01e775047","observation_id":"d7560303-ffbf-4904-aa33-0ebfc8fa45b3","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":"Monti, D","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:654c75eb1dd5f7e820618bfc632a04ebe7dd240bae85a695596c4f722165dbf1","observation_id":"911f35b8-9dee-497c-9241-282edb9e8288","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10637","last_updated":"2020-10-09T11:39:32Z","snapshot_observed_at":"2026-08-02T05:44:45.513979Z","submitted_at":"2020-06-18T16:06:18Z","title":"Temporal Graph Networks for Deep Learning on Dynamic Graphs","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.10637","snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":"Rossi, B","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"cited_paper":"/paper/2006.10637","citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:99dbb6093774719a977ac6df091aadc749a8b85ac8f852b6dfee6bccf9f924ba","observation_id":"2a04d496-b290-416b-afb9-93b8a0924d48","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:04098f1b64245e95918d359ac3ffddd24216567bb11ba7595db85d51674009cc","observation_id":"1267bcf7-1ffc-44c6-8c7d-7dbbde90a1cc","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":"Kumar, X","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:d87bb8bd1653e036e2a1ab3d95c157954c6b4e2bc47cc1960ec8b8ad8a6ecb38","observation_id":"1d88eb32-c71a-47d0-ae1a-8fa5e4955ae4","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:beb195480d8a320eb3b9b4d8cb7c1cbf3b13e563d788a3dd6e2d9f18999a5ff7","observation_id":"d4865695-babc-45b1-bdef-dc7a3f332c2e","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:15c56b32037331bb79cc1c930f1434bb6890361f1c35056d9a40b79a1a0029ea","observation_id":"86393908-45b8-425c-84af-cb4ff1467ecf","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":"Kocsis, C","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:f90a66aaa3c6685fbd6e672e7ce97e44aef6b0621d671ea4fda4fce9746faa7d","observation_id":"7eb2f911-dbf1-42fb-a616-57cf44f09248","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"physics/0004057","last_updated":"2000-04-24T15:22:30Z","snapshot_observed_at":"2026-07-07T06:44:19.645435Z","submitted_at":"2000-04-24T15:22:30Z","title":"The information bottleneck method","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"physics/0004057","snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":"Tishby, F","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"cited_paper":"/paper/physics/0004057","citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:0f43b61e52bf853bfc0fb075d9da80bc559ffa18f158effaddb733b6aa088180","observation_id":"d3936c46-47c8-4d7c-a7dd-f67ca88b1c92","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":null,"venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:0adfc201d6f242ed9002cccec74f49c09e5909d4194a71e9e459712c31f463e1","observation_id":"47591037-2629-48cd-952d-08e33fbfb2f4","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":"Shrikumar, P","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:e38c23c8f7048b87b125d4582ea381154ea555bff8de9304de3bfc4f6bfb6397","observation_id":"9c5815ba-2b4b-416e-a1d9-c24d20e805ef","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":"Ancona, E","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:b49dcf07a8826e2acacfbd1325a274a39536a9eda429889db0c9e6668574bc28","observation_id":"e302d8f8-967d-413b-8733-a69f34ab91ed","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":"Samek, A","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:800a8f1d95c1ef7b98128ed24859ab8890f25c12a36fa6ba35373be3399dea76","observation_id":"82bb2643-73b1-4a22-9129-d1b807520c55","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":"Blücher, J","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:132b7a6f8987c83bfba1244f193d7d09b74e2fbe585027c63d4e2b6a1a65965e","observation_id":"d7b0bfdf-9fa9-4d6e-9fe7-d0ed1b609d1f","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:a501ff0f36a07d86b0912dc31e2f21a76e0f6ff0ddfe68bfbc2e80ca263d0e67","observation_id":"5616e82f-fc38-434d-b538-b837f9a55c46","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":"Boschee, J","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:81cd8851ff205e7780f5e1d22ed5e4936f34c26ab1632c88a18f365276629ec8","observation_id":"dcb5010d-da86-43ef-9bf3-7867d5810807","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":"Montavon, Gradient-based vs","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:16b90592c0e25e7a04ff33bfe0cf7b34c676b9734432d4f411736e133e39e890","observation_id":"f043187f-f660-4df0-aa52-095acfd0990b","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-15T10:31:25.051835Z","title":"Shinzo Abe−Express intent to meet or negotiate→North Korea","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-07-15T10:31:25.051835Z"},"links":{"citing_paper":"/paper/2606.27201"},"observation_digest":"sha256:3adb34944afe837537cdca67e87d5c7e93fd3abc3c9b121fd079efa4e79c07f6","observation_id":"47edc437-df65-4251-8a23-8b33d1e21586","resolution":{"observed_at":"2026-07-15T10:31:25.051835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2606.27201","last_updated":"2026-07-14T07:24:22Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-01T23:35:01.846196Z","submitted_at":"2026-06-25T16:00:11Z","title":"Explaining Temporal Graph Neural Networks via Feature-induced Information Flow"},"reference_resolution":{"displayed":42,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":42,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":42},"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":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 0 inbound Pith citation observations for arXiv:2606.27201."}