{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:2FD27XR4OF5AQ4HSJBMMPHJ5XQ","short_pith_number":"pith:2FD27XR4","canonical_record":{"source":{"id":"1708.04120","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-07-28T09:35:45Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"31260fee880e5d4980a85408b1451b7610f05450ab179cbd4d290e5c932253ad","abstract_canon_sha256":"4797ab364eefe3e88162bd80216e28fa91470eb1f0be082313342800a113a571"},"schema_version":"1.0"},"canonical_sha256":"d147afde3c717a0870f24858c79d3dbc281399e56351ae08ba0ff689a95eeca3","source":{"kind":"arxiv","id":"1708.04120","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.04120","created_at":"2026-05-18T00:32:00Z"},{"alias_kind":"arxiv_version","alias_value":"1708.04120v2","created_at":"2026-05-18T00:32:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.04120","created_at":"2026-05-18T00:32:00Z"},{"alias_kind":"pith_short_12","alias_value":"2FD27XR4OF5A","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_16","alias_value":"2FD27XR4OF5AQ4HS","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_8","alias_value":"2FD27XR4","created_at":"2026-05-18T12:30:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:2FD27XR4OF5AQ4HSJBMMPHJ5XQ","target":"record","payload":{"canonical_record":{"source":{"id":"1708.04120","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-07-28T09:35:45Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"31260fee880e5d4980a85408b1451b7610f05450ab179cbd4d290e5c932253ad","abstract_canon_sha256":"4797ab364eefe3e88162bd80216e28fa91470eb1f0be082313342800a113a571"},"schema_version":"1.0"},"canonical_sha256":"d147afde3c717a0870f24858c79d3dbc281399e56351ae08ba0ff689a95eeca3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:32:00.979260Z","signature_b64":"9Ca6kpp/3MafNaKVsjbSGkJsQ3uPMRHx/exzDHDlF1qfVqAQB06d/ol+5fVAknOiwrKY1jj8wUKGh9jZba/4Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d147afde3c717a0870f24858c79d3dbc281399e56351ae08ba0ff689a95eeca3","last_reissued_at":"2026-05-18T00:32:00.978903Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:32:00.978903Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1708.04120","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:32:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HyxH812eveDt1Rlm9393DGE8DoaYwUSIrKOo730NJtf3+9afq/v478TG1112Hc80PlfNTv0ztEd6SahUv6HcBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T23:39:48.947118Z"},"content_sha256":"c27cd9cf77065e093aecba81105f6aede8c0d2e6d3bfaee66452e31abb7fab74","schema_version":"1.0","event_id":"sha256:c27cd9cf77065e093aecba81105f6aede8c0d2e6d3bfaee66452e31abb7fab74"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:2FD27XR4OF5AQ4HSJBMMPHJ5XQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Putting Self-Supervised Token Embedding on the Tables","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Gautier Marti, Marc Szafraniec, Philippe Donnat","submitted_at":"2017-07-28T09:35:45Z","abstract_excerpt":"Information distribution by electronic messages is a privileged means of transmission for many businesses and individuals, often under the form of plain-text tables. As their number grows, it becomes necessary to use an algorithm to extract text and numbers instead of a human. Usual methods are focused on regular expressions or on a strict structure in the data, but are not efficient when we have many variations, fuzzy structure or implicit labels. In this paper we introduce SC2T, a totally self-supervised model for constructing vector representations of tokens in semi-structured messages by u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.04120","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:32:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KEGfyrJt1aszmnXal0MtTiKTuxDm23MJdmLKaYi8KQw2fM82gqjeuUWBWXZxDv4dnIyUZxQtjXxrV3d5kzo4CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T23:39:48.947726Z"},"content_sha256":"dcedf448da6c24fcb7ac8a7eb8a47485d14308858d48c926c4f34bf35ddfc262","schema_version":"1.0","event_id":"sha256:dcedf448da6c24fcb7ac8a7eb8a47485d14308858d48c926c4f34bf35ddfc262"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2FD27XR4OF5AQ4HSJBMMPHJ5XQ/bundle.json","state_url":"https://pith.science/pith/2FD27XR4OF5AQ4HSJBMMPHJ5XQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2FD27XR4OF5AQ4HSJBMMPHJ5XQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-28T23:39:48Z","links":{"resolver":"https://pith.science/pith/2FD27XR4OF5AQ4HSJBMMPHJ5XQ","bundle":"https://pith.science/pith/2FD27XR4OF5AQ4HSJBMMPHJ5XQ/bundle.json","state":"https://pith.science/pith/2FD27XR4OF5AQ4HSJBMMPHJ5XQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2FD27XR4OF5AQ4HSJBMMPHJ5XQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:2FD27XR4OF5AQ4HSJBMMPHJ5XQ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4797ab364eefe3e88162bd80216e28fa91470eb1f0be082313342800a113a571","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-07-28T09:35:45Z","title_canon_sha256":"31260fee880e5d4980a85408b1451b7610f05450ab179cbd4d290e5c932253ad"},"schema_version":"1.0","source":{"id":"1708.04120","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.04120","created_at":"2026-05-18T00:32:00Z"},{"alias_kind":"arxiv_version","alias_value":"1708.04120v2","created_at":"2026-05-18T00:32:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.04120","created_at":"2026-05-18T00:32:00Z"},{"alias_kind":"pith_short_12","alias_value":"2FD27XR4OF5A","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_16","alias_value":"2FD27XR4OF5AQ4HS","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_8","alias_value":"2FD27XR4","created_at":"2026-05-18T12:30:55Z"}],"graph_snapshots":[{"event_id":"sha256:dcedf448da6c24fcb7ac8a7eb8a47485d14308858d48c926c4f34bf35ddfc262","target":"graph","created_at":"2026-05-18T00:32:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Information distribution by electronic messages is a privileged means of transmission for many businesses and individuals, often under the form of plain-text tables. As their number grows, it becomes necessary to use an algorithm to extract text and numbers instead of a human. Usual methods are focused on regular expressions or on a strict structure in the data, but are not efficient when we have many variations, fuzzy structure or implicit labels. In this paper we introduce SC2T, a totally self-supervised model for constructing vector representations of tokens in semi-structured messages by u","authors_text":"Gautier Marti, Marc Szafraniec, Philippe Donnat","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-07-28T09:35:45Z","title":"Putting Self-Supervised Token Embedding on the Tables"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.04120","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c27cd9cf77065e093aecba81105f6aede8c0d2e6d3bfaee66452e31abb7fab74","target":"record","created_at":"2026-05-18T00:32:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4797ab364eefe3e88162bd80216e28fa91470eb1f0be082313342800a113a571","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-07-28T09:35:45Z","title_canon_sha256":"31260fee880e5d4980a85408b1451b7610f05450ab179cbd4d290e5c932253ad"},"schema_version":"1.0","source":{"id":"1708.04120","kind":"arxiv","version":2}},"canonical_sha256":"d147afde3c717a0870f24858c79d3dbc281399e56351ae08ba0ff689a95eeca3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d147afde3c717a0870f24858c79d3dbc281399e56351ae08ba0ff689a95eeca3","first_computed_at":"2026-05-18T00:32:00.978903Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:32:00.978903Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9Ca6kpp/3MafNaKVsjbSGkJsQ3uPMRHx/exzDHDlF1qfVqAQB06d/ol+5fVAknOiwrKY1jj8wUKGh9jZba/4Dw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:32:00.979260Z","signed_message":"canonical_sha256_bytes"},"source_id":"1708.04120","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c27cd9cf77065e093aecba81105f6aede8c0d2e6d3bfaee66452e31abb7fab74","sha256:dcedf448da6c24fcb7ac8a7eb8a47485d14308858d48c926c4f34bf35ddfc262"],"state_sha256":"4bb652309b143037312af7f76f02b9d29dea7b55277856c26ecb523cd04f9f3b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OMViCVVPzsqBpFZ51imphQVoT8FHKtt9ax+v3D0rvP4SgmsjWcJ8piNN8cw1zzXWV5QiDemnQdxhWEoSutyCBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T23:39:48.950826Z","bundle_sha256":"d2dbbca297fe279151cc4a427e916176325191d6d9619b4238319eef33665414"}}