pub.chive.eprint.submission
Samples
210 randomly sampled records from the AT Protocol firehose
pub.chive.eprint.submission (100 samples)
{
"$type": "pub.chive.eprint.submission",
"abstract": [
{
"$type": "pub.chive.richtext.defs#textItem",
"content": "We present the Universal Decompositional Semantics (UDS) dataset (v1.0), which is bundled with the Decomp toolkit (v0.1). UDS1.0 unifies five high-quality, decompositional semantics-aligned annotation sets within a single semantic graph specification—with graph structures defined by the predicative patterns produced by the PredPatt tool and real-valued node and edge attributes constructed using sophisticated normalization procedures. The Decomp toolkit provides a suite of Python 3 tools for querying UDS graphs using SPARQL. Both UDS1.0 and Decomp0.1 are publicly available at http://decomp.io.",
"type": "text"
}
],
"abstractPlainText": "We present the Universal Decompositional Semantics (UDS) dataset (v1.0), which is bundled with the Decomp toolkit (v0.1). UDS1.0 unifies five high-quality, decompositional semantics-aligned annotation sets within a single semantic graph specification—with graph structures defined by the predicative patterns produced by the PredPatt tool and real-valued node and edge attributes constructed using sophisticated normalization procedures. The Decomp toolkit provides a suite of Python 3 tools for querying UDS graphs using SPARQL. Both UDS1.0 and Decomp0.1 are publicly available at http://decomp.io.",
"authors": [
{
"affiliations": [
{
"children": [
{
"name": "Department of Linguistics"
}
],
"name": "University of Rochester",
"rorId": "https://ror.org/022kthw22"
}
],
"did": "did:plc:34mbm5v3umztwvvgnttvcz6e",
"handle": "aaronstevenwhite.io",
"name": "Aaron Steven White",
"orcid": "0000-0003-0057-9246",
"order": 1
},
{
"did": "did:plc:drvtnoosdjozr7dmv5a4stwt",
"handle": "esteng.bsky.social",
"name": "Elias Stengel-Eskin",
"order": 2
},
{
"name": "Siddharth Vashishtha",
"order": 3
},
{
"name": "Venkata Govindarajan",
"order": 4
},
{
"name": "Dee Ann Reisinger",
"order": 5
},
{
"did": "did:plc:zfimefeinh5lrz3qokgcbtvi",
"handle": "xtimv.bsky.social",
"name": "Tim Vieira",
"order": 6
},
{
"did": "did:plc:sfx3hfp64tkynx46qzwrzkke",
"handle": "keisukesakaguchi.bsky.social",
"name": "Keisuke Sakaguchi",
"order": 7
},
{
"name": "Sheng Zhang",
"order": 8
},
{
"name": "Francis Ferraro",
"order": 9
},
{
"name": "Rachel Rudinger",
"order": 10
},
{
"did": "did:plc:55tu5jixxfgwtit4n6xxmioy",
"handle": "icoson.bsky.social",
"name": "Kyle Rawlins",
"order": 11
},
{
"name": "Benjamin Van Durme",
"order": 12
}
],
"conferencePresentation": {
"conferenceLocation": "Marseille, France",
"conferenceName": "Proceedings of {The} 12th {Language} {Resources} and {Evaluation} {Conference}"
},
"createdAt": "2020-05-01T00:00:00.000Z",
"document": {
"$type": "blob",
"mimeType": "application/pdf",
"ref": {
"$link": "bafkreia4b3zscmprqaze442rytm6et6l7zyc4h56h5zox774vspbc76vfy"
},
"size": 451833
},
"documentFormatSlug": "pdf",
"documentFormatUri": "at://did:plc:5wzpn4a4nbqtz3q45hyud6hd/pub.chive.graph.node/3f96bd05-e848-5465-aca9-0a959f778396",
"fieldUris": [
"at://did:plc:5wzpn4a4nbqtz3q45hyud6hd/pub.chive.graph.node/e5fe0691-fa46-5094-b6bc-a31763d7b94a",
"at://did:plc:5wzpn4a4nbqtz3q45hyud6hd/pub.chive.graph.node/a1a96689-b027-53d4-a546-6da7716abfd8",
"at://did:plc:5wzpn4a4nbqtz3q45hyud6hd/pub.chive.graph.node/f3482b65-fadc-5464-a84f-9bfd6168b291"
],
"keywords": [
"Datasets & Evaluation",
"Information Extraction",
"Natural Language Understanding"
],
"licenseSlug": "CC-BY-4.0",
"licenseUri": "at://did:plc:5wzpn4a4nbqtz3q45hyud6hd/pub.chive.graph.node/fc58b045-e186-5081-b7eb-abc5c47ea8a3",
"paperTypeSlug": "conference-paper",
"paperTypeUri": "at://did:plc:5wzpn4a4nbqtz3q45hyud6hd/pub.chive.graph.node/2ab4132d-8c17-59a6-9d15-8317e01784d4",
"publicationStatusSlug": "published",
"publicationStatusUri": "at://did:plc:5wzpn4a4nbqtz3q45hyud6hd/pub.chive.graph.node/3262e011-81ca-52f3-8b68-7d4c012ef9b7",
"repositories": {
"code": [
{
"label": "code + data",
"platformSlug": "github",
"url": "https://github.com/decompositional-semantics-initiative/decomp"
}
]
},
"schemaRevision": 3,
"submittedBy": "did:plc:34mbm5v3umztwvvgnttvcz6e",
"title": "The Universal Decompositional Semantics Dataset and Decomp Toolkit",
"version": {
"major": 1,
"minor": 0,
"patch": 0
}
}did:plc:34mbm5v3umztwvvgnttvcz6e | at://did:plc:34mbm5v3umztwvvgnttvcz6e/pub.chive.eprint.submission/3mufmbpvg7b2k
pub.chive.richtext.defs (nested within pub.chive.eprint.submission) (100 samples)
{
"$type": "pub.chive.eprint.submission",
"abstract": [
{
"$type": "pub.chive.richtext.defs#textItem",
"content": "We propose a novel framework for modeling event-related potentials (ERPs) collected during reading that couples pre-trained convolutional decoders with a language model. Using this framework, we compare the abilities of a variety of existing and novel sentence processing models to reconstruct ERPs. We find that modern contextual word embeddings underperform surprisal-based models but that, combined, the two outperform either on its own.",
"type": "text"
}
],
"abstractPlainText": "We propose a novel framework for modeling event-related potentials (ERPs) collected during reading that couples pre-trained convolutional decoders with a language model. Using this framework, we compare the abilities of a variety of existing and novel sentence processing models to reconstruct ERPs. We find that modern contextual word embeddings underperform surprisal-based models but that, combined, the two outperform either on its own.",
"authors": [
{
"name": "Shaorong Yan",
"order": 1
},
{
"affiliations": [
{
"children": [
{
"name": "Department of Linguistics"
}
],
"name": "University of Rochester",
"rorId": "https://ror.org/022kthw22"
}
],
"did": "did:plc:34mbm5v3umztwvvgnttvcz6e",
"handle": "aaronstevenwhite.io",
"name": "Aaron Steven White",
"orcid": "0000-0003-0057-9246",
"order": 2
}
],
"conferencePresentation": {
"conferenceLocation": "Minneapolis, Minnesota",
"conferenceName": "Proceedings of the {Workshop} on {Cognitive} {Modeling} and {Computational} {Linguistics}",
"proceedingsDoi": "10.18653/v1/W19-2910"
},
"createdAt": "2019-06-01T00:00:00.000Z",
"document": {
"$type": "blob",
"mimeType": "application/pdf",
"ref": {
"$link": "bafkreiccj6qcv6mhvbuuapropyzlkbsnpsw7kkdympj32p4x3tlqixjwxi"
},
"size": 5508521
},
"documentFormatSlug": "pdf",
"documentFormatUri": "at://did:plc:5wzpn4a4nbqtz3q45hyud6hd/pub.chive.graph.node/3f96bd05-e848-5465-aca9-0a959f778396",
"fieldUris": [
"at://did:plc:5wzpn4a4nbqtz3q45hyud6hd/pub.chive.graph.node/57ad99fd-8f7c-58f9-b9eb-f8f644290336",
"at://did:plc:5wzpn4a4nbqtz3q45hyud6hd/pub.chive.graph.node/6fe7359e-8b24-5fce-8bd4-0225a10c899e"
],
"keywords": [
"Computational Psycholinguistics"
],
"licenseSlug": "CC-BY-4.0",
"licenseUri": "at://did:plc:5wzpn4a4nbqtz3q45hyud6hd/pub.chive.graph.node/fc58b045-e186-5081-b7eb-abc5c47ea8a3",
"paperTypeSlug": "conference-paper",
"paperTypeUri": "at://did:plc:5wzpn4a4nbqtz3q45hyud6hd/pub.chive.graph.node/2ab4132d-8c17-59a6-9d15-8317e01784d4",
"publicationStatusSlug": "published",
"publicationStatusUri": "at://did:plc:5wzpn4a4nbqtz3q45hyud6hd/pub.chive.graph.node/3262e011-81ca-52f3-8b68-7d4c012ef9b7",
"publishedVersion": {
"accessType": "open_access",
"doi": "10.18653/v1/W19-2910",
"pages": "86–92",
"publisher": "Association for Computational Linguistics",
"url": "https://www.aclweb.org/anthology/W19-2910"
},
"schemaRevision": 3,
"submittedBy": "did:plc:34mbm5v3umztwvvgnttvcz6e",
"title": "A Framework for Decoding Event-Related Potentials from Text",
"version": {
"major": 1,
"minor": 0,
"patch": 0
}
}did:plc:34mbm5v3umztwvvgnttvcz6e | at://did:plc:34mbm5v3umztwvvgnttvcz6e/pub.chive.eprint.submission/3mufmcedrau2s
pub.chive.richtext.facets (nested within pub.chive.eprint.submission) (8 samples)
{
"$type": "pub.chive.eprint.submission",
"abstract": [
{
"$type": "pub.chive.richtext.defs#textItem",
"content": "Event-keyed summarization (EKS) requires summarizing a specific event described in a document given the document text and an event representation extracted from it. In this work, we extend EKS to the cross-document setting (CDEKS), in which summaries must synthesize information from accounts of the same event as given by multiple sources. We introduce SEAMuS (Summaries of Events Across Multiple Sources), a high-quality dataset for CDEKS based on an expert reannotation of the FAMuS dataset for cross-document argument extraction. We present a suite of baselines on SEAMuS—covering both smaller, fine-tuned models, as well as zero- and few-shot prompted LLMs—along with detailed ablations and a human evaluation study, showing SEAMuS to be a valuable benchmark for this new task.",
"facets": [
{
"features": [
{
"$type": "pub.chive.richtext.facets#bold"
}
],
"index": {
"byteEnd": 360,
"byteStart": 354
}
},
{
"features": [
{
"$type": "pub.chive.richtext.facets#bold"
}
],
"index": {
"byteEnd": 363,
"byteStart": 362
}
},
{
"features": [
{
"$type": "pub.chive.richtext.facets#bold"
}
],
"index": {
"byteEnd": 376,
"byteStart": 375
}
},
{
"features": [
{
"$type": "pub.chive.richtext.facets#bold"
}
],
"index": {
"byteEnd": 383,
"byteStart": 382
}
},
{
"features": [
{
"$type": "pub.chive.richtext.facets#bold"
}
],
"index": {
"byteEnd": 391,
"byteStart": 389
}
},
{
"features": [
{
"$type": "pub.chive.richtext.facets#bold"
}
],
"index": {
"byteEnd": 399,
"byteStart": 398
}
}
],
"type": "text"
}
],
"abstractPlainText": "Event-keyed summarization (EKS) requires summarizing a specific event described in a document given the document text and an event representation extracted from it. In this work, we extend EKS to the cross-document setting (CDEKS), in which summaries must synthesize information from accounts of the same event as given by multiple sources. We introduce SEAMuS (Summaries of Events Across Multiple Sources), a high-quality dataset for CDEKS based on an expert reannotation of the FAMuS dataset for cross-document argument extraction. We present a suite of baselines on SEAMuS—covering both smaller, fine-tuned models, as well as zero- and few-shot prompted LLMs—along with detailed ablations and a human evaluation study, showing SEAMuS to be a valuable benchmark for this new task.",
"authors": [
{
"name": "William Walden",
"order": 1
},
{
"name": "Pavlo Kuchmiichuk",
"order": 2
},
{
"did": "did:plc:sc3nswzryepptw5vdn2aq3uf",
"handle": "alexmartin314.bsky.social",
"name": "Alexander Martin",
"order": 3
},
{
"name": "Chihsheng Jin",
"order": 4
},
{
"name": "Angela Cao",
"order": 5
},
{
"did": "did:plc:dnau5r6cdpnux3ujlaaaw53s",
"handle": "csuncodes.bsky.social",
"name": "Claire Sun",
"order": 6
},
{
"name": "Curisia Allen",
"order": 7
},
{
"affiliations": [
{
"children": [
{
"name": "Department of Linguistics"
}
],
"name": "University of Rochester",
"rorId": "https://ror.org/022kthw22"
}
],
"did": "did:plc:34mbm5v3umztwvvgnttvcz6e",
"handle": "aaronstevenwhite.io",
"name": "Aaron Steven White",
"orcid": "0000-0003-0057-9246",
"order": 8
}
],
"conferencePresentation": {
"conferenceAcronym": "XLLM",
"conferenceIteration": "XLLM 2025",
"conferenceLocation": "Vienna, Austria",
"conferenceName": "Joint Workshop on Large Language Models and Structure Modeling"
},
"createdAt": "2025-08-01T12:00:00.000Z",
"document": {
"$type": "blob",
"mimeType": "application/pdf",
"ref": {
"$link": "bafkreib27jydfpehg55qnpyjplqrix7axnuq2dguj2x7spox44qkqsl4t4"
},
"size": 882926
},
"documentFormatSlug": "pdf",
"documentFormatUri": "at://did:plc:5wzpn4a4nbqtz3q45hyud6hd/pub.chive.graph.node/3f96bd05-e848-5465-aca9-0a959f778396",
"externalIds": {
"arxivId": "2410.14795"
},
"fieldUris": [
"at://did:plc:5wzpn4a4nbqtz3q45hyud6hd/pub.chive.graph.node/a1a96689-b027-53d4-a546-6da7716abfd8",
"at://did:plc:5wzpn4a4nbqtz3q45hyud6hd/pub.chive.graph.node/e5fe0691-fa46-5094-b6bc-a31763d7b94a"
],
"keywords": [
"Information Extraction",
"Datasets & Evaluation"
],
"licenseSlug": "CC-BY-4.0",
"licenseUri": "at://did:plc:5wzpn4a4nbqtz3q45hyud6hd/pub.chive.graph.node/fc58b045-e186-5081-b7eb-abc5c47ea8a3",
"paperTypeSlug": "conference-paper",
"paperTypeUri": "at://did:plc:5wzpn4a4nbqtz3q45hyud6hd/pub.chive.graph.node/2ab4132d-8c17-59a6-9d15-8317e01784d4",
"publicationStatusSlug": "published",
"publicationStatusUri": "at://did:plc:5wzpn4a4nbqtz3q45hyud6hd/pub.chive.graph.node/3262e011-81ca-52f3-8b68-7d4c012ef9b7",
"publishedVersion": {
"accessType": "open_access",
"doi": "10.18653/v1/2025.xllm-1.19",
"journal": "Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025)",
"pages": "218–241",
"publishedAt": "2025-08-01T12:00:00.000Z",
"publisher": "Association for Computational Linguistics",
"url": "https://aclanthology.org/2025.xllm-1.19/"
},
"repositories": {
"code": [
{
"label": "data + code",
"platformSlug": "github",
"url": "https://github.com/wgantt/SEAMuS"
}
]
},
"schemaRevision": 3,
"submittedBy": "did:plc:34mbm5v3umztwvvgnttvcz6e",
"title": "Cross-Document Event-Keyed Summarization",
"version": {
"major": 1,
"minor": 0,
"patch": 0
}
}did:plc:34mbm5v3umztwvvgnttvcz6e | at://did:plc:34mbm5v3umztwvvgnttvcz6e/pub.chive.eprint.submission/3mufma6ziks2y
pub.chive.richtext.text (nested within pub.chive.eprint.submission) (2 samples)
{
"$type": "pub.chive.eprint.submission",
"abstract": [
{
"$type": "pub.chive.richtext.text",
"content": "A throwaway eprint used to verify that records from other atproto services attach to a paper and render on it. Safe to delete.",
"type": "text"
}
],
"authors": [
{
"did": "did:plc:34mbm5v3umztwvvgnttvcz6e",
"name": "Aaron Steven White",
"order": 1
}
],
"createdAt": "2026-09-04T20:46:45.493081Z",
"document": {
"$type": "blob",
"mimeType": "application/pdf",
"ref": {
"$link": "bafkreidnq2ogmxfudpim4jgg5oneuowmo47odk6zhaxjbgqn5y4qnywjfe"
},
"size": 404
},
"licenseSlug": "cc-by-4.0",
"repositories": {
"code": [
{
"label": "Chive on GitHub",
"platformSlug": "github",
"url": "https://github.com/chive-pub/chive"
},
{
"label": "Probe repo on Tangled",
"platformSlug": "tangled",
"recordUri": "at://did:plc:34mbm5v3umztwvvgnttvcz6e/sh.tangled.repo/interop-probe"
}
],
"data": [
{
"label": "MegaIntensionality",
"platformSlug": "other",
"url": "at://did:plc:y4ussuvobbph4mpieqiszqr6/pub.layers.catalog.collection/2c69416698e7bdd5b2ffc9f7"
}
]
},
"submittedBy": "did:plc:34mbm5v3umztwvvgnttvcz6e",
"title": "[TEST] Interop verification probe — safe to delete"
}did:plc:34mbm5v3umztwvvgnttvcz6e | at://did:plc:34mbm5v3umztwvvgnttvcz6e/pub.chive.eprint.submission/3muptixquo527