{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BKSH35IQQCN4SSZK2LECDXULTB","short_pith_number":"pith:BKSH35IQ","canonical_record":{"source":{"id":"2503.01880","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-26T18:18:37Z","cross_cats_sorted":["cs.AI","cs.SI"],"title_canon_sha256":"c7223b3ad2faf21ebe06e4e56f4be64a31881a8028be18ef9dfd1301230c23e1","abstract_canon_sha256":"e97148c366e73ca60be890e35c730e52506dd4b460f0d73ce3bf9ebd89432d6e"},"schema_version":"1.0"},"canonical_sha256":"0aa47df510809bc94b2ad2c821de8b9857e6d79db6e1cb462cc60117b2eece1d","source":{"kind":"arxiv","id":"2503.01880","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.01880","created_at":"2026-07-05T10:24:03Z"},{"alias_kind":"arxiv_version","alias_value":"2503.01880v1","created_at":"2026-07-05T10:24:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01880","created_at":"2026-07-05T10:24:03Z"},{"alias_kind":"pith_short_12","alias_value":"BKSH35IQQCN4","created_at":"2026-07-05T10:24:03Z"},{"alias_kind":"pith_short_16","alias_value":"BKSH35IQQCN4SSZK","created_at":"2026-07-05T10:24:03Z"},{"alias_kind":"pith_short_8","alias_value":"BKSH35IQ","created_at":"2026-07-05T10:24:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BKSH35IQQCN4SSZK2LECDXULTB","target":"record","payload":{"canonical_record":{"source":{"id":"2503.01880","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-26T18:18:37Z","cross_cats_sorted":["cs.AI","cs.SI"],"title_canon_sha256":"c7223b3ad2faf21ebe06e4e56f4be64a31881a8028be18ef9dfd1301230c23e1","abstract_canon_sha256":"e97148c366e73ca60be890e35c730e52506dd4b460f0d73ce3bf9ebd89432d6e"},"schema_version":"1.0"},"canonical_sha256":"0aa47df510809bc94b2ad2c821de8b9857e6d79db6e1cb462cc60117b2eece1d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:24:03.944675Z","signature_b64":"LnTJejdyGv+fjkdfZJcxiEQA234igfsT6wlI/NIpVf1xAmoFgbcD6mUJy5udy4HkDAsJrClBtHTfCZbsabOtAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0aa47df510809bc94b2ad2c821de8b9857e6d79db6e1cb462cc60117b2eece1d","last_reissued_at":"2026-07-05T10:24:03.944177Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:24:03.944177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.01880","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":"2026-07-05T10:24:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NfFREuZ3tUElW4ZmkvuZcccQQgUxjd6zWu4Eb5nP9h0sUeX12c6AasxbzAvpX/ybnTvK8dlWnjWl5KNxO/aCDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:22:42.687437Z"},"content_sha256":"e77410b64c63a0bc0d956a2d90657070a8f4fe237e45773ab8723a34ba83efb7","schema_version":"1.0","event_id":"sha256:e77410b64c63a0bc0d956a2d90657070a8f4fe237e45773ab8723a34ba83efb7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BKSH35IQQCN4SSZK2LECDXULTB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BEYONDWORDS is All You Need: Agentic Generative AI based Social Media Themes Extractor","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SI"],"primary_cat":"cs.CL","authors_text":"Abdelrahman Farrag, Daehan Won, Mohammed-Khalil Ghali, Sarah Lam","submitted_at":"2025-02-26T18:18:37Z","abstract_excerpt":"Thematic analysis of social media posts provides a major understanding of public discourse, yet traditional methods often struggle to capture the complexity and nuance of unstructured, large-scale text data. This study introduces a novel methodology for thematic analysis that integrates tweet embeddings from pre-trained language models, dimensionality reduction using and matrix factorization, and generative AI to identify and refine latent themes. Our approach clusters compressed tweet representations and employs generative AI to extract and articulate themes through an agentic Chain of Though"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.01880","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/2503.01880/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":"2026-07-05T10:24:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LYseKqXYjtYh32vsbc+aODfJGP+PxhB3nkBIgWEnjxt8DL0oEfN+Fm5kiULFNEPAeLgbDj9qwNY1Pw2ZEqRWAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:22:42.687989Z"},"content_sha256":"f670bbf3f4f841628e9f1594e94992f9454f54680201a9761695c245c45b4aef","schema_version":"1.0","event_id":"sha256:f670bbf3f4f841628e9f1594e94992f9454f54680201a9761695c245c45b4aef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BKSH35IQQCN4SSZK2LECDXULTB/bundle.json","state_url":"https://pith.science/pith/BKSH35IQQCN4SSZK2LECDXULTB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BKSH35IQQCN4SSZK2LECDXULTB/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":"2026-08-07T16:22:42Z","links":{"resolver":"https://pith.science/pith/BKSH35IQQCN4SSZK2LECDXULTB","bundle":"https://pith.science/pith/BKSH35IQQCN4SSZK2LECDXULTB/bundle.json","state":"https://pith.science/pith/BKSH35IQQCN4SSZK2LECDXULTB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BKSH35IQQCN4SSZK2LECDXULTB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BKSH35IQQCN4SSZK2LECDXULTB","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":"e97148c366e73ca60be890e35c730e52506dd4b460f0d73ce3bf9ebd89432d6e","cross_cats_sorted":["cs.AI","cs.SI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-26T18:18:37Z","title_canon_sha256":"c7223b3ad2faf21ebe06e4e56f4be64a31881a8028be18ef9dfd1301230c23e1"},"schema_version":"1.0","source":{"id":"2503.01880","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.01880","created_at":"2026-07-05T10:24:03Z"},{"alias_kind":"arxiv_version","alias_value":"2503.01880v1","created_at":"2026-07-05T10:24:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01880","created_at":"2026-07-05T10:24:03Z"},{"alias_kind":"pith_short_12","alias_value":"BKSH35IQQCN4","created_at":"2026-07-05T10:24:03Z"},{"alias_kind":"pith_short_16","alias_value":"BKSH35IQQCN4SSZK","created_at":"2026-07-05T10:24:03Z"},{"alias_kind":"pith_short_8","alias_value":"BKSH35IQ","created_at":"2026-07-05T10:24:03Z"}],"graph_snapshots":[{"event_id":"sha256:f670bbf3f4f841628e9f1594e94992f9454f54680201a9761695c245c45b4aef","target":"graph","created_at":"2026-07-05T10:24:03Z","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/2503.01880/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Thematic analysis of social media posts provides a major understanding of public discourse, yet traditional methods often struggle to capture the complexity and nuance of unstructured, large-scale text data. This study introduces a novel methodology for thematic analysis that integrates tweet embeddings from pre-trained language models, dimensionality reduction using and matrix factorization, and generative AI to identify and refine latent themes. Our approach clusters compressed tweet representations and employs generative AI to extract and articulate themes through an agentic Chain of Though","authors_text":"Abdelrahman Farrag, Daehan Won, Mohammed-Khalil Ghali, Sarah Lam","cross_cats":["cs.AI","cs.SI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-26T18:18:37Z","title":"BEYONDWORDS is All You Need: Agentic Generative AI based Social Media Themes Extractor"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.01880","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:e77410b64c63a0bc0d956a2d90657070a8f4fe237e45773ab8723a34ba83efb7","target":"record","created_at":"2026-07-05T10:24:03Z","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":"e97148c366e73ca60be890e35c730e52506dd4b460f0d73ce3bf9ebd89432d6e","cross_cats_sorted":["cs.AI","cs.SI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-26T18:18:37Z","title_canon_sha256":"c7223b3ad2faf21ebe06e4e56f4be64a31881a8028be18ef9dfd1301230c23e1"},"schema_version":"1.0","source":{"id":"2503.01880","kind":"arxiv","version":1}},"canonical_sha256":"0aa47df510809bc94b2ad2c821de8b9857e6d79db6e1cb462cc60117b2eece1d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0aa47df510809bc94b2ad2c821de8b9857e6d79db6e1cb462cc60117b2eece1d","first_computed_at":"2026-07-05T10:24:03.944177Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:24:03.944177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LnTJejdyGv+fjkdfZJcxiEQA234igfsT6wlI/NIpVf1xAmoFgbcD6mUJy5udy4HkDAsJrClBtHTfCZbsabOtAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:24:03.944675Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.01880","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e77410b64c63a0bc0d956a2d90657070a8f4fe237e45773ab8723a34ba83efb7","sha256:f670bbf3f4f841628e9f1594e94992f9454f54680201a9761695c245c45b4aef"],"state_sha256":"d4009b494c318fcc94fca56f373a9d1c166b9aa2f49798de133a0d714ed6d80d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p2E0y3PBj1n00EFpPbUr4aLPY0/vdHEN7roxydvQ4JERiXyawcuRVhUJu8Vv/LBpPiKaIiJ0ApFirRDkmfWQDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T16:22:42.692762Z","bundle_sha256":"a0d690c45ae376eafa8dad5d60626c27803aebac2f2cf8629a6946c2eb8db105"}}