{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:IV5ZMSJ6PVTYWMH6T5YW47B2OI","short_pith_number":"pith:IV5ZMSJ6","canonical_record":{"source":{"id":"1611.04822","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-11-15T13:31:28Z","cross_cats_sorted":[],"title_canon_sha256":"374845c4c06a286cc54e246047cb5ba30cad16732723e2d9a7118486f52419e0","abstract_canon_sha256":"b636bb8004286a9cc40746371969c47345798cc8d04151a31209882e6cdef9ce"},"schema_version":"1.0"},"canonical_sha256":"457b96493e7d678b30fe9f716e7c3a72081293a3c01b3ab99a8b6fa88bb233c4","source":{"kind":"arxiv","id":"1611.04822","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.04822","created_at":"2026-05-18T00:30:46Z"},{"alias_kind":"arxiv_version","alias_value":"1611.04822v2","created_at":"2026-05-18T00:30:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.04822","created_at":"2026-05-18T00:30:46Z"},{"alias_kind":"pith_short_12","alias_value":"IV5ZMSJ6PVTY","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_16","alias_value":"IV5ZMSJ6PVTYWMH6","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_8","alias_value":"IV5ZMSJ6","created_at":"2026-05-18T12:30:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:IV5ZMSJ6PVTYWMH6T5YW47B2OI","target":"record","payload":{"canonical_record":{"source":{"id":"1611.04822","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-11-15T13:31:28Z","cross_cats_sorted":[],"title_canon_sha256":"374845c4c06a286cc54e246047cb5ba30cad16732723e2d9a7118486f52419e0","abstract_canon_sha256":"b636bb8004286a9cc40746371969c47345798cc8d04151a31209882e6cdef9ce"},"schema_version":"1.0"},"canonical_sha256":"457b96493e7d678b30fe9f716e7c3a72081293a3c01b3ab99a8b6fa88bb233c4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:46.604303Z","signature_b64":"8Q3pNFNScrebt6nIs+UiDvS7sJv7EA8533oXXJ5cdreGuNOIhX9X9aLf8R+g3loyNDSSlw2+elitgLk7j5uMBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"457b96493e7d678b30fe9f716e7c3a72081293a3c01b3ab99a8b6fa88bb233c4","last_reissued_at":"2026-05-18T00:30:46.603737Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:46.603737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1611.04822","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":"2026-05-18T00:30:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1iAPhIDLPfFwIcTZzpKtjnbwleyQhv4wh3U3K7t7bl8u+9dWhLeIWR/081w97YQXixSoy60fJc+VWLC3qXDaAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T16:31:26.870854Z"},"content_sha256":"31e5af78ad697fa3aabc29a6a0ff216c83ef863d103235d5e7e609bda19423b0","schema_version":"1.0","event_id":"sha256:31e5af78ad697fa3aabc29a6a0ff216c83ef863d103235d5e7e609bda19423b0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:IV5ZMSJ6PVTYWMH6T5YW47B2OI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SimDoc: Topic Sequence Alignment based Document Similarity Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gaurav Maheshwari, Harshita Sahijwani, Jens Lehmann, Kunal Jha, Priyansh Trivedi, Sourish Dasgupta","submitted_at":"2016-11-15T13:31:28Z","abstract_excerpt":"Document similarity is the problem of estimating the degree to which a given pair of documents has similar semantic content. An accurate document similarity measure can improve several enterprise relevant tasks such as document clustering, text mining, and question-answering. In this paper, we show that a document's thematic flow, which is often disregarded by bag-of-word techniques, is pivotal in estimating their similarity. To this end, we propose a novel semantic document similarity framework, called SimDoc. We model documents as topic-sequences, where topics represent latent generative clu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.04822","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":"2026-05-18T00:30:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"evXJ22f2z8YsbRwJO1EsuI0usuJCG4FyL/ghOXbHVW06Y2MgGf2n1rP9XqX4+Rj3d7V6XZONHB7LUzJNFhOFAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T16:31:26.871268Z"},"content_sha256":"a61d297f75523d4ec0bcdd060e54b06f879cd1e5bb6bbc2ae4f0f51d1e359a73","schema_version":"1.0","event_id":"sha256:a61d297f75523d4ec0bcdd060e54b06f879cd1e5bb6bbc2ae4f0f51d1e359a73"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IV5ZMSJ6PVTYWMH6T5YW47B2OI/bundle.json","state_url":"https://pith.science/pith/IV5ZMSJ6PVTYWMH6T5YW47B2OI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IV5ZMSJ6PVTYWMH6T5YW47B2OI/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":"2026-05-30T16:31:26Z","links":{"resolver":"https://pith.science/pith/IV5ZMSJ6PVTYWMH6T5YW47B2OI","bundle":"https://pith.science/pith/IV5ZMSJ6PVTYWMH6T5YW47B2OI/bundle.json","state":"https://pith.science/pith/IV5ZMSJ6PVTYWMH6T5YW47B2OI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IV5ZMSJ6PVTYWMH6T5YW47B2OI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:IV5ZMSJ6PVTYWMH6T5YW47B2OI","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":"b636bb8004286a9cc40746371969c47345798cc8d04151a31209882e6cdef9ce","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-11-15T13:31:28Z","title_canon_sha256":"374845c4c06a286cc54e246047cb5ba30cad16732723e2d9a7118486f52419e0"},"schema_version":"1.0","source":{"id":"1611.04822","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.04822","created_at":"2026-05-18T00:30:46Z"},{"alias_kind":"arxiv_version","alias_value":"1611.04822v2","created_at":"2026-05-18T00:30:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.04822","created_at":"2026-05-18T00:30:46Z"},{"alias_kind":"pith_short_12","alias_value":"IV5ZMSJ6PVTY","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_16","alias_value":"IV5ZMSJ6PVTYWMH6","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_8","alias_value":"IV5ZMSJ6","created_at":"2026-05-18T12:30:22Z"}],"graph_snapshots":[{"event_id":"sha256:a61d297f75523d4ec0bcdd060e54b06f879cd1e5bb6bbc2ae4f0f51d1e359a73","target":"graph","created_at":"2026-05-18T00:30:46Z","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":"Document similarity is the problem of estimating the degree to which a given pair of documents has similar semantic content. An accurate document similarity measure can improve several enterprise relevant tasks such as document clustering, text mining, and question-answering. In this paper, we show that a document's thematic flow, which is often disregarded by bag-of-word techniques, is pivotal in estimating their similarity. To this end, we propose a novel semantic document similarity framework, called SimDoc. We model documents as topic-sequences, where topics represent latent generative clu","authors_text":"Gaurav Maheshwari, Harshita Sahijwani, Jens Lehmann, Kunal Jha, Priyansh Trivedi, Sourish Dasgupta","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-11-15T13:31:28Z","title":"SimDoc: Topic Sequence Alignment based Document Similarity Framework"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.04822","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":"sha256:31e5af78ad697fa3aabc29a6a0ff216c83ef863d103235d5e7e609bda19423b0","target":"record","created_at":"2026-05-18T00:30:46Z","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":"b636bb8004286a9cc40746371969c47345798cc8d04151a31209882e6cdef9ce","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-11-15T13:31:28Z","title_canon_sha256":"374845c4c06a286cc54e246047cb5ba30cad16732723e2d9a7118486f52419e0"},"schema_version":"1.0","source":{"id":"1611.04822","kind":"arxiv","version":2}},"canonical_sha256":"457b96493e7d678b30fe9f716e7c3a72081293a3c01b3ab99a8b6fa88bb233c4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"457b96493e7d678b30fe9f716e7c3a72081293a3c01b3ab99a8b6fa88bb233c4","first_computed_at":"2026-05-18T00:30:46.603737Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:30:46.603737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8Q3pNFNScrebt6nIs+UiDvS7sJv7EA8533oXXJ5cdreGuNOIhX9X9aLf8R+g3loyNDSSlw2+elitgLk7j5uMBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:30:46.604303Z","signed_message":"canonical_sha256_bytes"},"source_id":"1611.04822","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:31e5af78ad697fa3aabc29a6a0ff216c83ef863d103235d5e7e609bda19423b0","sha256:a61d297f75523d4ec0bcdd060e54b06f879cd1e5bb6bbc2ae4f0f51d1e359a73"],"state_sha256":"4c14365a5c6a3843ae56a68b40f41b2222b8b8efe619025754f94e5482b593f9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IGuVWMdoBOdeC1oovgtvGwxMfVuqIV0cVu+xCMIuRyEejLwhP7zoRx1rm9sGazvSymqv/ceZZV4g0iu7AKnfCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T16:31:26.875227Z","bundle_sha256":"b33861724a789db135172b832d0a7f5074b6f54caece5bace924169e09bce20a"}}