{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NCT4WY6Z52PEUY4GHZ6YVU224Y","short_pith_number":"pith:NCT4WY6Z","canonical_record":{"source":{"id":"2412.10717","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-14T07:20:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"aac07b1290876f29d59a83bca2a1fdbdaf150f6837e28345e601cc79064de7d2","abstract_canon_sha256":"f8bcfee0741d1bd26f938eb6f4bf070c2d2b5cf2f5ea9da6e0df38aa24ce73e2"},"schema_version":"1.0"},"canonical_sha256":"68a7cb63d9ee9e4a63863e7d8ad35ae60924475f322065acec7a3d39c9671fb1","source":{"kind":"arxiv","id":"2412.10717","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.10717","created_at":"2026-07-05T09:49:20Z"},{"alias_kind":"arxiv_version","alias_value":"2412.10717v1","created_at":"2026-07-05T09:49:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10717","created_at":"2026-07-05T09:49:20Z"},{"alias_kind":"pith_short_12","alias_value":"NCT4WY6Z52PE","created_at":"2026-07-05T09:49:20Z"},{"alias_kind":"pith_short_16","alias_value":"NCT4WY6Z52PEUY4G","created_at":"2026-07-05T09:49:20Z"},{"alias_kind":"pith_short_8","alias_value":"NCT4WY6Z","created_at":"2026-07-05T09:49:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NCT4WY6Z52PEUY4GHZ6YVU224Y","target":"record","payload":{"canonical_record":{"source":{"id":"2412.10717","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-14T07:20:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"aac07b1290876f29d59a83bca2a1fdbdaf150f6837e28345e601cc79064de7d2","abstract_canon_sha256":"f8bcfee0741d1bd26f938eb6f4bf070c2d2b5cf2f5ea9da6e0df38aa24ce73e2"},"schema_version":"1.0"},"canonical_sha256":"68a7cb63d9ee9e4a63863e7d8ad35ae60924475f322065acec7a3d39c9671fb1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:20.346953Z","signature_b64":"G/6uQcp2T64gn1oojDB+rstydTvdxIRlAfP03wNuJuBbLBDoa0UxbpurCVCTEeTy9lmPzDhQkitkYUaldALiBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68a7cb63d9ee9e4a63863e7d8ad35ae60924475f322065acec7a3d39c9671fb1","last_reissued_at":"2026-07-05T09:49:20.346443Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:20.346443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.10717","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:49:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XTBYv/7hbfRZqNUVl4eIXEbg7Or53DJgfiHQPAfe7cAjriJaAagqKXdG9g3NnT/2/QJReTO1F2yJxUDCXBmTDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T07:57:51.722416Z"},"content_sha256":"240a59b7de5917a6c25fb80ca7ccbb781a0ae8d751eae160b19edace166c6166","schema_version":"1.0","event_id":"sha256:240a59b7de5917a6c25fb80ca7ccbb781a0ae8d751eae160b19edace166c6166"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NCT4WY6Z52PEUY4GHZ6YVU224Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HITgram: A Platform for Experimenting with n-gram Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chandan Maity, Debasish Jana, Diptendu Dutta, Rohan Singh, Shibaranjani Dasgupta, Somdip Mukherjee","submitted_at":"2024-12-14T07:20:35Z","abstract_excerpt":"Large language models (LLMs) are powerful but resource intensive, limiting accessibility. HITgram addresses this gap by offering a lightweight platform for n-gram model experimentation, ideal for resource-constrained environments. It supports unigrams to 4-grams and incorporates features like context sensitive weighting, Laplace smoothing, and dynamic corpus management to e-hance prediction accuracy, even for unseen word sequences. Experiments demonstrate HITgram's efficiency, achieving 50,000 tokens/second and generating 2-grams from a 320MB corpus in 62 seconds. HITgram scales efficiently, c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10717","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.10717/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T09:49:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EGIK2kSX5QXnZMu9iQmiq2iRWnwtaGo5jk4sTG/Eb7lWXVtFMYvU3PGHyKZm45exJJBmD7TRjIVl6cVVGMKNBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T07:57:51.723145Z"},"content_sha256":"2a30170f60fae03b7258a23d3ea5dfe943e0ea30b9f5a847ebf80305235de278","schema_version":"1.0","event_id":"sha256:2a30170f60fae03b7258a23d3ea5dfe943e0ea30b9f5a847ebf80305235de278"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NCT4WY6Z52PEUY4GHZ6YVU224Y/bundle.json","state_url":"https://pith.science/pith/NCT4WY6Z52PEUY4GHZ6YVU224Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NCT4WY6Z52PEUY4GHZ6YVU224Y/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":"2026-08-17T07:57:51Z","links":{"resolver":"https://pith.science/pith/NCT4WY6Z52PEUY4GHZ6YVU224Y","bundle":"https://pith.science/pith/NCT4WY6Z52PEUY4GHZ6YVU224Y/bundle.json","state":"https://pith.science/pith/NCT4WY6Z52PEUY4GHZ6YVU224Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NCT4WY6Z52PEUY4GHZ6YVU224Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NCT4WY6Z52PEUY4GHZ6YVU224Y","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":"f8bcfee0741d1bd26f938eb6f4bf070c2d2b5cf2f5ea9da6e0df38aa24ce73e2","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-14T07:20:35Z","title_canon_sha256":"aac07b1290876f29d59a83bca2a1fdbdaf150f6837e28345e601cc79064de7d2"},"schema_version":"1.0","source":{"id":"2412.10717","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.10717","created_at":"2026-07-05T09:49:20Z"},{"alias_kind":"arxiv_version","alias_value":"2412.10717v1","created_at":"2026-07-05T09:49:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10717","created_at":"2026-07-05T09:49:20Z"},{"alias_kind":"pith_short_12","alias_value":"NCT4WY6Z52PE","created_at":"2026-07-05T09:49:20Z"},{"alias_kind":"pith_short_16","alias_value":"NCT4WY6Z52PEUY4G","created_at":"2026-07-05T09:49:20Z"},{"alias_kind":"pith_short_8","alias_value":"NCT4WY6Z","created_at":"2026-07-05T09:49:20Z"}],"graph_snapshots":[{"event_id":"sha256:2a30170f60fae03b7258a23d3ea5dfe943e0ea30b9f5a847ebf80305235de278","target":"graph","created_at":"2026-07-05T09:49:20Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2412.10717/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are powerful but resource intensive, limiting accessibility. HITgram addresses this gap by offering a lightweight platform for n-gram model experimentation, ideal for resource-constrained environments. It supports unigrams to 4-grams and incorporates features like context sensitive weighting, Laplace smoothing, and dynamic corpus management to e-hance prediction accuracy, even for unseen word sequences. Experiments demonstrate HITgram's efficiency, achieving 50,000 tokens/second and generating 2-grams from a 320MB corpus in 62 seconds. HITgram scales efficiently, c","authors_text":"Chandan Maity, Debasish Jana, Diptendu Dutta, Rohan Singh, Shibaranjani Dasgupta, Somdip Mukherjee","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-14T07:20:35Z","title":"HITgram: A Platform for Experimenting with n-gram Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10717","kind":"arxiv","version":1},"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":"sha256:240a59b7de5917a6c25fb80ca7ccbb781a0ae8d751eae160b19edace166c6166","target":"record","created_at":"2026-07-05T09:49:20Z","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":"f8bcfee0741d1bd26f938eb6f4bf070c2d2b5cf2f5ea9da6e0df38aa24ce73e2","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-14T07:20:35Z","title_canon_sha256":"aac07b1290876f29d59a83bca2a1fdbdaf150f6837e28345e601cc79064de7d2"},"schema_version":"1.0","source":{"id":"2412.10717","kind":"arxiv","version":1}},"canonical_sha256":"68a7cb63d9ee9e4a63863e7d8ad35ae60924475f322065acec7a3d39c9671fb1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68a7cb63d9ee9e4a63863e7d8ad35ae60924475f322065acec7a3d39c9671fb1","first_computed_at":"2026-07-05T09:49:20.346443Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:49:20.346443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G/6uQcp2T64gn1oojDB+rstydTvdxIRlAfP03wNuJuBbLBDoa0UxbpurCVCTEeTy9lmPzDhQkitkYUaldALiBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:49:20.346953Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.10717","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:240a59b7de5917a6c25fb80ca7ccbb781a0ae8d751eae160b19edace166c6166","sha256:2a30170f60fae03b7258a23d3ea5dfe943e0ea30b9f5a847ebf80305235de278"],"state_sha256":"4b1df8f0e1b8c322bb9c287d7024b8199ce2150c4144f9238d5d6b340c915b94"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CV908JU3W9GqRpf04jgFVhjSGAt1n/HzuI9Nrq7/WJV5+j2dgA666qevBCA0aMXePn2M8OhXp9KosOAz1uNTDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T07:57:51.730386Z","bundle_sha256":"cb04fefcef67b95993ba227ba2bf12637e23dca80764ac3200357006b9f03803"}}